Skip to content

An always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vault. Runs 24/7 on the Claude subscription you already have.

docs: sanitize all skill files — replace personal data with generic templates

smixse2efc6dcca63
diff --git a/vault/.claude-plugin/plugin.json b/vault/.claude-plugin/plugin.json
index 7746e3c..6bf2b0c 100644
--- a/vault/.claude-plugin/plugin.json
+++ b/vault/.claude-plugin/plugin.json
@@ -3,8 +3,8 @@
"version": "2.0.0",
"description": "Voice-first personal assistant for capturing thoughts and tasks via Telegram, with goal tracking and Obsidian integration",
"author": {
- "name": "Shima",
- "url": "https://github.com/shima"
+ "name": "[Your Name]",
+ "url": "https://github.com/[yourusername]"
},
"license": "MIT",
"capabilities": {
diff --git a/vault/.claude/skills/dbrain-processor/SKILL.md b/vault/.claude/skills/dbrain-processor/SKILL.md
index 66886c8..f00e116 100644
--- a/vault/.claude/skills/dbrain-processor/SKILL.md
+++ b/vault/.claude/skills/dbrain-processor/SKILL.md
@@ -1,12 +1,17 @@
---
-name: second-brain-processor
-description: Personal assistant for processing daily voice/text entries from Telegram. Classifies content, creates Todoist tasks aligned with goals, saves thoughts to Obsidian with wiki-links, generates HTML reports. Triggers on /process command or daily 21:00 cron.
+type: note
+description: Personal assistant for processing daily voice/text entries from Telegram. Classifies content, creates Todoist tasks aligned with goals, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.
+name: dbrain-processor
+allowed-tools: Bash(mcp-cli:*)
+depends_on: [graph-builder, todoist-ai, agent-memory, vault-health]
---
-# Second Brain Processor
+# d-brain Processor
Process daily entries → tasks (Todoist) + thoughts (Obsidian) + HTML report (Telegram).
+Integrates with Your Business data for business context.
+
## CRITICAL: Output Format
**ALWAYS return RAW HTML. No exceptions. No markdown. Ever.**
@@ -27,151 +32,291 @@ WRONG:
CORRECT:
<b>Title</b>
-## MCP Tools Required
+## Todoist через mcp-cli
+
+**ВСЕГДА используй mcp-cli для Todoist.** Не используй прямые MCP tools.
+
+### Базовые команды:
+
+```bash
+# Задачи на сегодня (проверка workload)
+mcp-cli call todoist find-tasks-by-date '{"startDate": "today"}'
+
+# Создать задачу
+mcp-cli call todoist add-tasks '{"tasks": [{"content": "Task", "dueString": "tomorrow", "priority": 2}]}'
-mcp__todoist__add-tasks — Create tasks
-mcp__todoist__find-tasks — Check duplicates
-mcp__todoist__find-tasks-by-date — Check workload
+# Найти задачи по label
+mcp-cli call todoist find-tasks '{"labels": ["process-goal"]}'
-## CRITICAL: MCP Tool Usage
+# Завершить задачи
+mcp-cli call todoist complete-tasks '{"ids": ["task_id"]}'
-**СНАЧАЛА ВЫЗОВИ TOOL. ПОТОМ ДУМАЙ.**
+# Обзор
+mcp-cli call todoist get-overview '{}'
+```
+
+### Приоритеты:
+- 1 = p1 (highest)
+- 2 = p2 (high)
+- 3 = p3 (medium)
+- 4 = p4 (default)
+
+## CRITICAL: mcp-cli Usage
-У тебя ЕСТЬ доступ к MCP tools:
-- `mcp__todoist__add-tasks`
-- `mcp__todoist__find-tasks`
-- `mcp__todoist__find-tasks-by-date`
-- `mcp__todoist__complete-tasks`
-- `mcp__todoist__update-tasks`
+**СНАЧАЛА ВЫЗОВИ КОМАНДУ. ПОТОМ ДУМАЙ.**
### Обязательный алгоритм:
-1. ВЫЗОВИ: mcp__todoist__find-tasks-by-date
+```
+1. ВЫЗОВИ: mcp-cli call todoist find-tasks-by-date '{"startDate": "today"}'
↓
Получил результат? → Продолжай
↓
Ошибка? → Читай файлы 30 секунд, потом ВЫЗОВИ СНОВА
↓
3 ошибки подряд? → Покажи ТОЧНЫЙ текст ошибки
+```
### ЗАПРЕЩЕНО:
-- ❌ Писать "MCP недоступен"
-- ❌ Предлагать "добавь вручную"
-- ❌ Использовать subprocess для вызова CLI
-- ❌ Делать HTTP запросы к API напрямую
-- ❌ Выводить команды для копирования
-- ❌ Решать что не работает БЕЗ вызова tool
+
+- ❌ "Todoist недоступен"
+- ❌ "mcp-cli не работает"
+- ❌ "добавь вручную"
+- ❌ Решать что не работает БЕЗ вызова команды
### ОБЯЗАТЕЛЬНО:
-- ✅ Вызывать MCP tool напрямую
+
+- ✅ ВЫЗВАТЬ команду через Bash
- ✅ Если ошибка — подождать, вызвать снова
- ✅ 3 retry перед любыми выводами
-- ✅ Если task создан — включить task ID в отчёт
-
-При ошибке MCP tool — показать ТОЧНУЮ ошибку от tool, не придумывать отговорки.
+- ✅ Показать task ID если создан
## Processing Flow
-1. Load context — Read goals/3-weekly.md (ONE Big Thing), goals/2-monthly.md
-2. Check workload — find-tasks-by-date for 7 days
-3. **Check process goals** — find-tasks with labels: ["process-goal"]
-4. Read daily — daily/YYYY-MM-DD.md
-5. Process entries — Classify → task or thought
-6. Build links — Connect notes with [[wiki-links]]
-7. **Log actions to daily** — append action log entry
-8. **Evolve MEMORY.md** — update long-term memory if needed
-9. Generate HTML report — RAW HTML for Telegram
+1. **Load personal context** — Read goals/1-yearly, goals/2-monthly, goals/3-weekly
+2. **Load business context**:
+ - Read `business/_index.md` — Your Business (клиенты, проекты, CRM)
+ - Read `projects/_index.md` — личные проекты (если релевантно)
+3. **Read daily** — daily/YYYY-MM-DD.md
+4. **Check workload** — `mcp-cli call todoist find-tasks-by-date '{"startDate": "today", "daysCount": 7}'`
+5. **CHECK PROCESS GOALS** — `mcp-cli call todoist find-tasks '{"labels": ["process-goal"]}'`
+ → If empty or stale: generate from goals, create recurring tasks
+6. **Process entries** — Classify → task or thought, detect business mentions
+7. **Build links** — Connect notes with [[wiki-links]], link to business entities
+8. **Generate HTML report** — include process goals status + business activity
+9. **Log actions to daily** — append action log entry (see below)
+10. **Evolve MEMORY.md** — update long-term memory if needed (see below)
+11. **Capture observations** — record friction signals to handoff.md (see below)
+
+## ОБЯЗАТЕЛЬНО: Логирование в daily/
-## Process Goals Check (Step 3)
+**После ЛЮБЫХ изменений в vault — СРАЗУ пиши в `daily/YYYY-MM-DD.md`:**
-**ОБЯЗАТЕЛЬНО выполни при каждом /process:**
+Формат:
+```
+## HH:MM [text]
+{Описание действий}
-### 1. Проверь существующие process goals
-Используй mcp__todoist__find-tasks с labels: ["process-goal"]
+**Создано/Обновлено:**
+- [[path/to/file|Name]] — описание
+```
-### 2. Если отсутствуют — создай
-Читай goals/ и генерируй process commitments:
+**Что логировать:**
+- Создание файлов в thoughts/
+- Обновление business/ или projects/
+- Создание задач в Todoist (с task ID)
+- Синхронизация с внешними системами
-| Goal Level | Source | Process Pattern |
-|------------|--------|-----------------|
-| Weekly ONE Big Thing | goals/3-weekly.md | 2h deep work ежедневно |
-| Monthly Top 3 | goals/2-monthly.md | 1 action/день на приоритет |
-| Yearly Focus | goals/1-yearly-*.md | 30 мин/день на стратегию |
+**Пример:**
+```
+## 14:30 [text]
+Обработка ежедневных записей
-Создавай recurring tasks с label "process-goal" (max 5-7 активных).
+**Создано задач:** 3
+- "Follow-up Acme Corp" (id: 8501234567, p2, завтра)
+- "Подготовить КП Unilever" (id: 8501234568, p2, пятница)
-### 3. Включи в отчёт
+**Сохранено мыслей:** 1
+- [[thoughts/ideas/product-launch|Product Launch]] — идея запуска
+```
-```html
-<b>📋 Process Goals:</b>
-• 2h deep work → ✅ активен
-• 1 outreach/день → ⚠️ просрочен
-{N} активных | {M} требуют внимания
+**Зачем:** Audit trail + контекст для будущих обработок.
+
+## Evolve MEMORY.md (Step 10 Detail)
+
+**ЦЕЛЬ:** Поддерживать MEMORY.md актуальным. Не добавлять, а ЭВОЛЮЦИОНИРОВАТЬ.
+
+### Когда обновлять MEMORY.md
+
+Проверь после обработки entries — есть ли информация достойная долгосрочной памяти?
+
+### Write Rules: Что достойно MEMORY.md
+
+**ПИСАТЬ:**
+- ✅ Key decisions с impact (pivot, tool choice, architecture change)
+- ✅ Изменения в pipeline (новый лид, закрытая сделка, изменение статуса)
+- ✅ Финансовые изменения (оплаты получены, долги, новые контракты)
+- ✅ Новые паттерны/инсайты (learnings)
+- ✅ Изменения в Active Context (новый ONE Big Thing, Hot Projects)
+- ✅ Новые ключевые контакты (с context)
+
+**НЕ ПИСАТЬ:**
+- ❌ Ежедневные мелочи (встречи, звонки без impact)
+- ❌ Временные заметки (оставить в daily/)
+- ❌ Дубликаты того что уже есть
+- ❌ Детали проектов (оставить в business/crm/, projects/)
+- ❌ Тривиальные задачи
+
+### Как обновлять (evolve, не append)
+
+**Принцип:** Новое ЗАМЕНЯЕТ устаревшее, не добавляется рядом.
+
+| Ситуация | Действие |
+|----------|----------|
+| Новое противоречит старому | ЗАМЕНИТЬ старую информацию |
+| Новое дополняет старое | Добавить в существующую секцию |
+| Информация устарела | Удалить или архивировать |
+
+**Пример 1 — Изменение статуса проекта:**
+```
+Old: "| Acme Corp NCP Meals | p1 | Активная разработка | $XXK |"
+New info: "Acme Corp NCP Meals сдан клиенту"
+→ ЗАМЕНИТЬ на: "| Acme Corp NCP Meals | ✅ | Завершён | $XXK |"
```
-See: references/process-goals.md for patterns and examples.
+**Пример 2 — Новое решение:**
+```
+Добавить в Key Decisions таблицу:
+| 2026-02-01 | Отказ от X в пользу Y | причина | impact |
+```
-## Logging to daily/ (Step 7)
+**Пример 3 — Изменение в pipeline:**
+```
+Old: "| LogisticsLead | Hot | $XXK |"
+New info: "LogisticsLead подписал контракт"
+→ Удалить из Pipeline
+→ Добавить в Hot Projects или Financial Context
+```
-**После ЛЮБЫХ изменений в vault — СРАЗУ пиши в `daily/YYYY-MM-DD.md`:**
+### Секции MEMORY.md для обновления
+
+| Секция | Когда обновлять |
+|--------|-----------------|
+| Active Context | Изменение ONE Big Thing, Hot Projects, Pipeline |
+| Key Decisions | Новое решение с impact |
+| Financial Context | Оплаты, долги, контракты |
+| Key People | Новый важный контакт |
+| Learnings | Новый паттерн/инсайт |
+| Current Crisis | Изменение в текущей критической ситуации |
+
+### Формат Edit
+
+Используй Edit tool для точечных изменений:
-Format:
```
-## HH:MM [text]
-{Description of actions}
+Edit MEMORY.md:
+old_string: "| LogisticsLead | Hot | $XXK |"
+new_string: "| LogisticsLead | ✅ Signed | $XXK |"
+```
+
+### В отчёте
-**Created/Updated:**
-- [[path/to/file|Name]] — description
+Если обновил MEMORY.md, добавь секцию:
+
+```html
+<b>🧠 MEMORY.md обновлён:</b>
+• Active Context → Hot Projects updated
+• Key Decisions → +1 новое решение
```
-What to log:
-- Files created in thoughts/
-- Tasks created in Todoist (with task ID)
-- Links built between notes
+## Capture Observations (Step 11 Detail)
-Example:
+**ЦЕЛЬ:** Записывать friction signals, паттерны и идеи для улучшения системы.
+
+### Когда записывать
+
+После обработки проверь — были ли проблемы или наблюдения?
+
+| Тип | Когда |
+|-----|-------|
+| `[friction]` | mcp-cli errors, timeouts, empty daily, broken links, unexpected data |
+| `[pattern]` | Повторяющийся паттерн (задачи всегда overdue, daily пустой по выходным) |
+| `[idea]` | Идея для улучшения pipeline, schema, отчёта |
+
+### Формат
+
+Append в `vault/.session/handoff.md` секцию `## Observations`:
+
+```markdown
+## Observations
+- [friction] YYYY-MM-DD: mcp-cli timeout 3x на todoist — retry спас, но -60 сек
+- [pattern] YYYY-MM-DD: daily без entries 2 дня подряд — выходные?
+- [idea] YYYY-MM-DD: CRM карточки без deal_deadline = невидимые дедлайны
```
-## 14:30 [text]
-Daily processing complete
-**Created tasks:** 3
-- "Follow-up client" (id: 8501234567, p2, tomorrow)
-- "Prepare proposal" (id: 8501234568, p2, friday)
+### Правила
+
+- Одна строка на наблюдение (конкретика, не абстракции)
+- Дата обязательна
+- Не повторять уже записанные observations
+- Когда observations ≥10 → сигнал для system improvement session
+
+### В отчёте
+
+Если записаны observations, добавь:
+
+```html
+<b>👁 Observations:</b>
+• [friction] mcp-cli timeout 3x
+```
+
+---
+
+## Process Goals Check (Step 5 Detail)
+
+**ОБЯЗАТЕЛЬНО выполни этот шаг при каждом /process:**
+
+### 1. Проверь существующие process goals
-**Saved thoughts:** 1
-- [[thoughts/ideas/product-launch|Product Launch]] — new idea
+```bash
+mcp-cli call todoist find-tasks '{"labels": ["process-goal"], "limit": 20}'
```
-## Evolve MEMORY.md (Step 8)
+### 2. Если process goals ОТСУТСТВУЮТ — создай их
+
+Читай goals файлы и генерируй process commitments:
-**GOAL:** Keep MEMORY.md current. Don't append — EVOLVE.
+| Goal Level | Source | Process Pattern |
+|------------|--------|-----------------|
+| Weekly ONE Big Thing | goals/3-weekly.md | 2h deep work ежедневно |
+| Monthly Top 3 | goals/2-monthly.md | 1 action/день на приоритет |
+| Yearly Focus | goals/1-yearly-*.md | 30 мин/день на стратегию |
-### When to update:
-- ✅ Key decisions with impact (pivot, tool choice, architecture change)
-- ✅ New patterns/insights (learnings)
-- ✅ Changes in Active Context (new ONE Big Thing, Hot Projects)
+**Создай recurring tasks:**
-### When NOT to update:
-- ❌ Daily trivia (meetings, calls without impact)
-- ❌ Temporary notes (stay in daily/)
-- ❌ Duplicates of what's already there
+```bash
+mcp-cli call todoist add-tasks '{"tasks": [
+ {"content": "2h deep work: [ONE Big Thing]", "dueString": "every weekday at 6am", "priority": 2, "labels": ["process-goal"]},
+ {"content": "1 outreach/день: [monthly priority]", "dueString": "every weekday", "priority": 3, "labels": ["process-goal"]},
+ {"content": "30 мин продуктовые идеи", "dueString": "every day", "priority": 4, "labels": ["process-goal"]}
+]}'
+```
-### How to update (evolve, not append):
+**Лимит:** Max 5-7 активных process goals.
-| Situation | Action |
-|-----------|--------|
-| New contradicts old | REPLACE old information |
-| New complements old | Add to existing section |
-| Info is outdated | Delete or archive |
+### 3. Если process goals ЕСТЬ — проверь статус
-Use Edit tool for precise changes.
+- Активные (upcoming) → ✅ показать в отчёте
+- Просроченные (overdue) → ⚠️ предупредить
+- Устаревшие (не связаны с текущими целями) → рекомендовать удалить
-### In report (if updated):
+### 4. Включи в отчёт
```html
-<b>🧠 MEMORY.md updated:</b>
-• Active Context → Hot Projects changed
-• Key Decisions → +1 new decision
+<b>📋 Process Goals:</b>
+• 2h deep work: [Client Project] → ✅ активен
+• 1 outreach/день → ⚠️ просрочен
+{N} активных | {M} требуют внимания
```
## Entry Format
@@ -181,10 +326,121 @@ Content
Types: [voice], [text], [forward from: Name], [photo]
+## Business Context Integration
+
+**ТОЧКА ВХОДА:** `business/_index.md` — читай для понимания бизнес-контекста.
+
+### Структура:
+```
+business/
+├── _index.md ← Статистика, обзор
+├── crm/ ← ВСЁ: компании + сделки + проекты в одном файле
+├── network/ ← Структура холдинга
+└── events/ ← Мероприятия
+```
+
+### Распознавание упоминаний
+
+При обработке entries ищи упоминания клиентов и проектов:
+
+| Паттерн | Действие |
+|---------|----------|
+| "звонил [Client]" | Найти `business/crm/{client}.md`, добавить связь |
+| "по проекту [Client]" | Найти `business/crm/{client}.md` |
+| "встреча с [Client]" | Создать задачу + связать с `business/crm/{client}.md` |
+| "отправил КП для [Client]" | Связать с `business/crm/{client}.md` |
+
+### Поиск клиента по имени
+
+1. Имя → kebab-case: "Acme Corp" → `acme-corp`, "Bi Group" → `bi-group`
+2. Искать: `business/crm/{kebab-case}.md`
+3. Если не найден — fuzzy search по `grep -l "{name}" business/crm/`
+
+### Создание связей
+
+Когда упомянут клиент/проект, добавляй wiki-links:
+
+**В задачу:**
+```
+"Follow-up [[business/crm/acme-corp|Acme Corp]] по снекам"
+```
+
+**В thought:**
+```
+Связано с: [[business/crm/techco|TechCo]], [[business/crm/phonebrand-smm|PhoneBrand SMM]]
+```
+
+### Приоритет задач с бизнесом
+
+| Условие | Приоритет |
+|---------|-----------|
+| Клиент с priority: High + deadline | p1 |
+| Активный проект (In progress) | p2 |
+| Клиент с priority: High | p2 |
+| Клиент с priority: Mid | p3 |
+| Prospect без срочности | p4 |
+
## Classification
task → Todoist (see references/todoist.md)
idea/reflection/learning → thoughts/ (see references/classification.md)
+client/project mention → link to Business/Projects + create task if actionable
+
+## Projects Context Integration
+
+**Точка входа:** `projects/_index.md`
+
+### Структура:
+```
+projects/
+├── _index.md # Clients overview
+├── clients/ # Clients
+└── leads/ # Leads
+```
+
+### Распознавание упоминаний
+
+| Паттерн | Файл |
+|---------|------|
+| "[Client A]" | projects/clients/{client-a}.md |
+| "[Client B]" | projects/clients/{client-b}.md |
+| "AI обучение", "воркшоп" | projects/ контекст |
+
+### Отличие от Business
+
+- **Business** = основной бизнес
+- **Projects** = личные проекты (консалтинг, обучение)
+
+Если entry упоминает AI/ML обучение — ищи в projects/ сначала.
+
+## Contacts Context Integration
+
+**Точка входа:** `contacts/_index.md`
+
+### Распознавание имён в entries
+
+Ищи паттерны:
+- "созвонился с [Contact] из [Client]"
+- "встреча с @username"
+- "Имя Фамилия написал"
+
+### Классификация
+
+| Индикатор | Категория | Vault Link |
+|-----------|-----------|------------|
+| Known business clients | business | `business/crm/{client}` |
+| AI/обучение expertise, known leads | projects | `projects/leads/{name}` |
+| Остальные | personal | — |
+
+### В отчёте
+
+Если в entries упомянуты люди, добавь секцию:
+
+```html
+<b>👤 Упомянуто контактов:</b>
+• [Contact Name] (business → [[business/crm/acme-corp]])
+• [Contact Name] (personal)
+```
## Priority Rules
@@ -193,6 +449,27 @@ p2 — Aligns with ONE Big Thing or monthly priority
p3 — Aligns with yearly goal
p4 — Operational, no goal alignment
+## Process Goals Preference
+
+When creating tasks, prefer PROCESS over OUTCOME formulations.
+
+**Outcome (less effective):**
+- "Закрыть сделку с X"
+- "Запустить продукт"
+- "Подготовить программу"
+
+**Process (more effective):**
+- "Отправить follow-up клиенту X" (actionable, controllable)
+- "2h deep work на MVP" (time-bounded)
+- "Показать драфт программы коллеге" (checkpoint)
+
+**When to transform:**
+- Entry sounds vague/outcome-focused → make it specific/process-focused
+- User says "нужно сделать X" → create actionable next step, not X itself
+- Goal mentioned → create task that MOVES TOWARD goal, not goal itself
+
+See: references/process-goals.md for patterns and examples.
+
## Thought Categories
💡 idea → thoughts/ideas/
@@ -215,10 +492,16 @@ Output RAW HTML (no markdown, no code blocks):
<b>✅ Создано задач:</b> {M}
• {task} <i>({priority}, {due})</i>
+<b>🏢 Business Activity:</b>
+• {client} — {action}
+• {project} — {status update}
+<i>Упомянуто клиентов: {N} | Проектов: {M}</i>
+
<b>📋 Process Goals:</b>
• {process goal 1} → {status}
• {process goal 2} → {status}
{N} активных | {M} требуют внимания
+<i>Создано новых: {K}</i>
<b>📅 Загрузка на неделю:</b>
Пн: {n} | Вт: {n} | Ср: {n} | Чт: {n} | Пт: {n} | Сб: {n} | Вс: {n}
@@ -239,7 +522,7 @@ Output RAW HTML (no markdown, no code blocks):
<b>🧠 MEMORY.md:</b>
• {section} → {change description}
-<i>(if updated)</i>
+<i>(если обновлено)</i>
---
<i>Обработано за {duration}</i>
@@ -296,9 +579,42 @@ Max length: 4096 characters.
Read these files as needed:
- references/about.md — User profile, decision filters
- references/classification.md — Entry classification rules
-- references/todoist.md — Task creation details
+- references/todoist.md — Task creation details + recurring patterns
- references/goals.md — Goal alignment logic
- references/process-goals.md — Process vs outcome goals, transformation patterns
- references/links.md — Wiki-links building
- references/rules.md — Mandatory processing rules
- references/report-template.md — Full HTML report spec
+- references/business.md — Business client/project context, search patterns
+- references/contacts.md — Contacts search and classification
+
+## Business Quick Reference
+
+**Точка входа:** `business/_index.md`
+
+**Поиск клиента:**
+```
+grep -l "Acme Corp" business/crm/
+→ business/crm/acme-corp.md
+```
+
+**Активные сделки:**
+```
+grep -l "deal_status:" business/crm/
+```
+
+**High priority клиенты:**
+```
+grep -l "priority: High" business/crm/
+```
+
+**Frontmatter полей:**
+- type: crm
+- industry, priority, status, region, owner, responsible
+- deal_status, deal_deadline (для активных сделок)
+- updated
+
+## Relevant Skills
+
+- [[vault/.claude/skills/graph-builder/SKILL|graph-builder]] — Vault graph analysis
+- [[vault/.claude/skills/todoist-ai/SKILL|todoist-ai]] — Todoist task management
diff --git a/vault/.claude/skills/dbrain-processor/references/about.md b/vault/.claude/skills/dbrain-processor/references/about.md
index f82e3e5..1046694 100644
--- a/vault/.claude/skills/dbrain-processor/references/about.md
+++ b/vault/.claude/skills/dbrain-processor/references/about.md
@@ -1,98 +1,28 @@
-# About User - System Profile
-
-<!--
-╔══════════════════════════════════════════════════════════════════╗
-║ КАК ЗАПОЛНИТЬ ЭТОТ ФАЙЛ ║
-╠══════════════════════════════════════════════════════════════════╣
-║ Это ваш профиль для AI-агента. Чем лучше заполните — ║
-║ тем точнее агент понимает контекст ваших записей. ║
-║ ║
-║ 1. Замените все [плейсхолдеры] на свою информацию ║
-║ 2. Удалите ненужные секции или добавьте свои ║
-║ 3. Обновляйте файл при изменении целей/приоритетов ║
-║ 4. Удалите этот комментарий после заполнения ║
-║ ║
-║ 💡 Совет: Используйте ChatGPT или Claude для заполнения. ║
-║ Отправьте ему этот шаблон и попросите задать вопросы. ║
-╚══════════════════════════════════════════════════════════════════╝
--->
-
-## Core Identity
-
-**[Your Name], [Age]** — [Your Role/Position]
-
-- [Your company/occupation]
-- [Key clients or projects]
-- [Years of experience]
-- [Primary role description]
-
-## Primary Operating Mode
-
-- [How you think and work]
-- [Your decision-making style]
-- [What you value in work]
-- [Communication preferences]
-
-## Strategic Focus
-
-1. [Primary goal]
-2. [Secondary goal]
-3. [Third goal]
-
-## Work Domains
-
-Key contexts for classifying notes:
-
-| Domain | Examples |
-|--------|----------|
-| **Work** | projects, tasks, meetings, deadlines |
-| **Learning** | courses, books, insights, skills |
-| **Ideas** | product ideas, improvements, innovations |
-| **Personal** | health, family, hobbies, routines |
-
-## Personal Context
-
-- Family: [situation]
-- Interests: [hobbies]
-- Work style: [morning person, etc.]
-- Languages: [languages you use]
-
-## Goals Hierarchy
-
-1. [Primary life goal]
-2. [Secondary goal]
-3. [Third goal]
-4. [Fourth goal]
-
-## Decision Filters
-
-When evaluating ideas and tasks:
-- [Question 1]
-- [Question 2]
-- [Question 3]
-- [Question 4]
-
-## Notes Processing Preferences
-
-### Language and Style
-- [Your language preferences]
-- [Terminology preferences]
-- [Formatting preferences]
-
-### Structure
-Preferred format:
-```
-Context → Insight → Implication → Next Action
-```
-
-### Prioritization
-- **Urgent**: [what counts as urgent] → p1-p2
-- **Strategic**: [what counts as strategic] → p3-p4
-
-## Anti-Patterns (AVOID)
-
-When processing entries DO NOT:
-- Create abstract notes without action items
-- Make tasks too vague like "think about..."
-- Duplicate content without synthesis
-- Create lists without priorities
+# About [Your Name]
+
+## Who I Am
+[Your Name], [age]. [Your role/title] at [Your Company].
+
+## What I Do
+- [Main business activity]
+- [Side projects/interests]
+
+## My Team
+| Name | Role |
+|------|------|
+| [Your Name] | [Your Role] |
+| [Team Member] | [Their Role] |
+
+## Working Style
+- Timezone: [Your Timezone]
+- Working hours: [Your preferred hours]
+- Languages: [Your languages]
+
+## Values
+- [Value 1]
+- [Value 2]
+- [Value 3]
+
+## Key Clients/Projects
+- [Client/Project 1] — [Brief description]
+- [Client/Project 2] — [Brief description]
diff --git a/vault/.claude/skills/dbrain-processor/references/business-context.md b/vault/.claude/skills/dbrain-processor/references/business-context.md
new file mode 100644
index 0000000..db0e4ff
--- /dev/null
+++ b/vault/.claude/skills/dbrain-processor/references/business-context.md
@@ -0,0 +1,26 @@
+# Business Context
+
+## Company Overview
+[Your Company Name] — [what the company does].
+
+## CRM Structure
+```
+business/
+├── _index.md ← Start here (stats, overview)
+├── crm/ ← Client records (companies + deals)
+└── network/ ← Company structure, partners
+```
+
+## Key Metrics
+- Total CRM records: [N]
+- Active deals: [N]
+- Industries: [list your industries]
+
+## Deal Tracking Fields
+| Field | Values |
+|-------|--------|
+| status | Active, Prospect, Dormant |
+| deal_status | In Progress, Tender, Proposal Sent |
+| priority | High, Mid, Low |
+| region | [Your regions] |
+| owner | [Your Name] |
diff --git a/vault/.claude/skills/dbrain-processor/references/classification.md b/vault/.claude/skills/dbrain-processor/references/classification.md
index 15a9b43..54a2fd2 100644
--- a/vault/.claude/skills/dbrain-processor/references/classification.md
+++ b/vault/.claude/skills/dbrain-processor/references/classification.md
@@ -1,17 +1,5 @@
# Entry Classification
-<!--
-╔══════════════════════════════════════════════════════════════════╗
-║ КАК НАСТРОИТЬ ЭТОТ ФАЙЛ ║
-╠══════════════════════════════════════════════════════════════════╣
-║ 1. Замените [Your Client Names] на имена ваших клиентов ║
-║ 2. Замените [Your Company] на название вашей компании ║
-║ 3. Замените [@your_channel] на ваш Telegram-канал ║
-║ 4. Добавьте свои домены работы, если они отличаются ║
-║ 5. Удалите этот комментарий после настройки ║
-╚══════════════════════════════════════════════════════════════════╝
--->
-
## Work Domains → Categories
Based on user's work context (see [ABOUT.md](ABOUT.md)):
@@ -19,8 +7,7 @@ Based on user's work context (see [ABOUT.md](ABOUT.md)):
### Client Work
Брифы, стратегии, креатив, кампании, KPI, предложения
-<!-- Добавьте имена ваших клиентов через запятую -->
-**Keywords:** [Your Client Names], клиент, бриф, презентация, дедлайн, KPI
+**Keywords:** [Client A], [Client B], [Client C], клиент, бриф, презентация, дедлайн, KPI
**→ Category:** task (p1-p2) → Todoist
@@ -41,16 +28,14 @@ Based on user's work context (see [ABOUT.md](ABOUT.md)):
### Company Ops
Команда, процессы, автоматизация, найм, управление, финансы
-<!-- Замените [Your Company] на название вашей компании/проекта -->
-**Keywords:** команда, найм, процесс, HR, финансы, [Your Company]
+**Keywords:** команда, найм, процесс, HR, финансы, [Your Business], агентство
**→ Category:** task или project (depends on urgency)
### Content
Посты, идеи, тезисы для Telegram и LinkedIn
-<!-- Замените [@your_channel] на ваш Telegram-канал или удалите если не нужно -->
-**Keywords:** пост, [@your_channel], LinkedIn, контент, тезис, статья
+**Keywords:** пост, @yourbrand, LinkedIn, контент, тезис, статья
**→ Category:** idea → thoughts/ideas/ или task если с дедлайном
@@ -62,7 +47,7 @@ Based on user's work context (see [ABOUT.md](ABOUT.md)):
Entry text contains...
│
├─ Client brand or deadline? ────────────────────> TASK (p1-p2)
-│ ([Your Clients], клиент, дедлайн, презентация)
+│ ([Client A], [Client B], клиент, дедлайн, презентация)
│
├─ Operational/urgent? ──────────────────────────> TASK (p2-p3)
│ (нужно сделать, не забыть, позвонить, встреча)
@@ -83,6 +68,30 @@ Entry text contains...
(пост, тезис, контент)
```
+---
+
+## Business Client Detection
+
+Entry mentions a known client (see business-context.md)?
+
+```
+├─ + deadline/urgency? → TASK (p1-p2) + client label
+├─ + статус ("отправили КП", "выиграли")? → TASK + flag for CRM note
+├─ + встреча/звонок? → TASK (p2) + [[client]] link
+└─ просто упоминание? → Add [[client]] link only
+```
+
+### CRM Status Keywords (для информации в отчёте)
+
+| Keywords | Интерпретация |
+|----------|---------------|
+| "подписали", "выиграли", "получили" | Позитивный исход |
+| "отказали", "проиграли", "не пошли" | Негативный исход |
+| "отправили КП", "подали" | В процессе |
+| "ждём ответ", "на рассмотрении" | Ожидание |
+
+---
+
## Apply Decision Filters
Перед сохранением спроси:
@@ -156,8 +165,7 @@ tags: [tag1, tag2]
[Ключевая идея]
## Implication
-<!-- Замените [Your Company] на название вашей компании -->
-[Что это значит для [Your Company]/продукта/стратегии]
+[Что это значит для [Your Business]/продукта/стратегии]
## Next Action
[Конкретный шаг — не абстрактный]
@@ -169,7 +177,7 @@ tags: [tag1, tag2]
При создании мыслей НЕ делать:
- Абстрактные рассуждения без Next Action
-- Академическая теория без применения к вашему проекту/продукту
+- Академическая теория без применения к [Your Business]/продукту
- Повторы без синтеза (кластеризуй похожие!)
- Хаотичные списки без приоритетов
- Задачи типа "подумать о..." (конкретизируй!)
diff --git a/vault/.claude/skills/dbrain-processor/references/contacts.md b/vault/.claude/skills/dbrain-processor/references/contacts.md
new file mode 100644
index 0000000..4c6783c
--- /dev/null
+++ b/vault/.claude/skills/dbrain-processor/references/contacts.md
@@ -0,0 +1,12 @@
+# Contacts
+
+## Search Protocol
+When looking for a person or contact:
+1. Search vault CRM files by name
+2. Check daily files for recent mentions
+3. Search by company association
+
+## Contact Sources
+- CRM cards in `business/crm/`
+- Project records in `projects/`
+- Daily logs for recent interactions
diff --git a/vault/.claude/skills/dbrain-processor/references/goals.md b/vault/.claude/skills/dbrain-processor/references/goals.md
index 79fd7ad..1d99743 100644
--- a/vault/.claude/skills/dbrain-processor/references/goals.md
+++ b/vault/.claude/skills/dbrain-processor/references/goals.md
@@ -124,8 +124,8 @@ Entry: "Нужно подготовить презентацию для клие
Check:
- ONE Big Thing: "Ship MVP" → Not related
-- Monthly #1: "Client deliverables" → ✅ Related
-- Yearly: "Client Revenue" → ✅ Related
+- Monthly #1: "Client deliverables" → Related
+- Yearly: "Client Revenue" → Related
Result:
```
diff --git a/vault/.claude/skills/dbrain-processor/references/links.md b/vault/.claude/skills/dbrain-processor/references/links.md
index 52543ff..d919653 100644
--- a/vault/.claude/skills/dbrain-processor/references/links.md
+++ b/vault/.claude/skills/dbrain-processor/references/links.md
@@ -43,15 +43,15 @@ Read goals/1-yearly-2025.md
Find matching goal areas
```
-### Step 4: Add Links to Note
+### Step 4: Add Links to Note (with context)
-In the thought file, add:
+In the thought file, add **typed relationships** — each link explains WHY it's connected:
-**In frontmatter:**
+**In frontmatter (for graph analysis):**
```yaml
related:
- - "[[thoughts/ideas/2024-12-15-voice-agents.md]]"
- - "[[goals/1-yearly-2025#AI Development]]"
+ - "[[thoughts/ideas/2024-12-15-voice-agents]]"
+ - "[[goals/1-yearly-2026#AI Development]]"
```
**In content (inline):**
@@ -59,14 +59,27 @@ related:
This connects to [[Voice Agents Architecture]] we explored earlier.
```
-**In Related section:**
+**In Related section (with context phrases):**
```markdown
## Related
-- [[Previous related thought]]
-- [[Project this belongs to]]
-- [[Goal this supports]]
+- [[thoughts/ideas/voice-agents-architecture|Voice Agents]] — extends: real-time TTS pipeline
+- [[business/crm/acme-corp|Acme Corp]] — context: NCP campaign uses similar approach
+- [[goals/1-yearly-2026#AI Development]] — supports: yearly AI skill goal
```
+### Relationship Types
+
+Use context phrases after `—` to explain the connection:
+
+| Type | When to use | Example |
+|------|------------|---------|
+| extends | Builds on another idea | `— extends: adds TTS to voice pipeline` |
+| context | Background/origin of idea | `— context: emerged from client project` |
+| supports | Aligns with a goal | `— supports: Q1 revenue target` |
+| contradicts | Challenges existing note | `— contradicts: previous approach was sync` |
+| enables | Makes something possible | `— enables: automated daily reports` |
+| requires | Dependency | `— requires: mcp-cli working` |
+
### Step 5: Update MOC Index
Add new note to appropriate MOC:
@@ -103,6 +116,41 @@ In related notes, add backlink to new note if highly relevant.
[[goals/3-weekly]] — ONE Big Thing
```
+---
+
+## Business Entity Links
+
+### Формат связей
+
+| Тип | Формат | Пример |
+|-----|--------|--------|
+| Клиент | `[[business/crm/{name}\|Display]]` | `[[business/crm/acme-corp\|Acme Corp]]` |
+| Проект | `[[projects/{name}\|Display]]` | `[[projects/project-alpha\|Project Alpha]]` |
+| CRM Lead | `[[business/crm/{name}\|Display]]` | `[[business/crm/techco\|TechCo]]` |
+
+### Где добавлять связи (с typed context)
+
+**В daily file (комментарий):**
+```markdown
+## 10:30 [voice]
+Позвонил в Acme Corp по проекту
+<!-- связь: [[business/crm/acme-corp]] -->
+```
+
+**В thoughts (Related section с context phrases):**
+```markdown
+## Related
+- [[business/crm/techco|TechCo]] — context: обсуждение BTL стратегии
+- [[business/crm/phonebrand|PhoneBrand]] — extends: SMM стратегия 2026
+```
+
+**В задаче Todoist (description):**
+```
+Description: "Клиент: [[business/crm/acme-corp|Acme Corp]]"
+```
+
+---
+
## Report Section
Track new links created:
@@ -115,36 +163,36 @@ Track new links created:
## Example Workflow
-<!-- Это пример — замените на свои реальные темы -->
-New thought: "Новый инструмент X можно использовать для проекта Y"
+New thought: "Chatterbox TTS can be used for voice agents"
1. **Search:**
- - Grep "keyword" in thoughts/ → finds related notes
- - Grep "tool" in thoughts/ → no results
+ - Grep "voice" in thoughts/ → finds [[Voice Agents Architecture]]
+ - Grep "TTS" in thoughts/ → no results
+ - Grep "Chatterbox" → no results
2. **Check MOC:**
- - MOC-learnings.md has relevant section
+ - MOC-learnings.md has "AI & Voice" section
3. **Goals:**
- - 1-yearly-2025.md has matching goal
+ - 1-yearly-2025.md has "AI Development" goal
4. **Create links:**
```yaml
related:
- - "[[thoughts/ideas/related-note.md]]"
- - "[[goals/1-yearly-2025#Your Goal]]"
+ - "[[thoughts/ideas/voice-agents-architecture.md]]"
+ - "[[goals/1-yearly-2025#AI Development]]"
```
5. **Update MOC-learnings.md:**
```markdown
- ### Your Category
- - [[thoughts/learnings/2024-12-20-new-learning.md]] — Description
+ ### AI & Voice
+ - [[thoughts/learnings/2024-12-20-chatterbox-tts.md]] — TTS for voice agents
```
6. **Report:**
```
<b>🔗 Новые связи:</b>
- • [[New Note]] ↔ [[Related Note]]
+ • [[Chatterbox TTS]] ↔ [[Voice Agents Architecture]]
```
## Orphan Detection
diff --git a/vault/.claude/skills/dbrain-processor/references/process-goals.md b/vault/.claude/skills/dbrain-processor/references/process-goals.md
index d3c5ea2..d20f2c7 100644
--- a/vault/.claude/skills/dbrain-processor/references/process-goals.md
+++ b/vault/.claude/skills/dbrain-processor/references/process-goals.md
@@ -24,46 +24,46 @@ Based on research (meta-analysis of 27 experiments in sports):
| Outcome Goal | Process Goal |
|--------------|--------------|
-| "Close the deal with X" | "Send 1 follow-up per day to client X" |
-| "Launch product" | "2h deep work on MVP every morning" |
-| "Get 10 clients" | "Write 5 outreach messages per day" |
-| "Prepare the program" | "30 min research analogs daily" |
-| "Find a partner" | "1 networking message per day" |
+| "Закрыть сделку с [Client A]" | "Отправлять 1 follow-up в день клиенту [Client A]" |
+| "Запустить продукт" | "2h deep work на MVP каждое утро" |
+| "Привлечь 10 клиентов" | "Написать 5 outreach сообщений в день" |
+| "Подготовить программу" | "30 мин research аналогов ежедневно" |
+| "Найти партнёра" | "1 нетворкинг сообщение в день" |
## Patterns for Process Goals
### Time Blocks
Regular dedicated time for deep work:
-- "2h deep work on [project] every morning 6-8am"
-- "1h research [topic] after lunch"
+- "2h deep work на [project] каждое утро 6-8am"
+- "1h research [topic] после обеда"
### Frequency Commitments
Consistent action cadence:
-- "1 outreach message per day"
-- "3 customer calls per week"
-- "5 proposals per week"
+- "1 outreach message в день"
+- "3 customer calls в неделю"
+- "5 proposals в неделю"
### Checkpoints
Review milestones:
-- "Show draft to 1 person before Friday"
-- "Review progress with mentor on Wednesday"
+- "Показать драфт 1 человеку до пятницы"
+- "Review прогресс с ментором в среду"
### Streaks
Daily habits:
-- "30 min movement every day"
-- "10 min journaling in the morning"
+- "30 мин движения каждый день"
+- "10 мин journaling утром"
## When Processing Voice Entries
If user says outcome goal, consider transforming:
```
-User: "Need to close the deal with client X"
+User: "Нужно закрыть сделку с [Client A]"
-BAD: Create task "Close deal with client X" p1
+BAD: Create task "Закрыть сделку с [Client A]" p1
→ Vague, creates anxiety, unclear next action
-GOOD: Create task "Send follow-up to client X with updated proposal" p1 due:tomorrow
+GOOD: Create task "Отправить follow-up [Client A] с обновлённым КП" p1 due:tomorrow
→ Specific, actionable, controllable
```
@@ -82,19 +82,19 @@ Map process goals to Todoist dueString:
| Process | dueString |
|---------|-----------|
-| "every morning" | "every day at 6am" |
-| "every day" | "every day" |
-| "every workday" | "every weekday" |
-| "3 times per week" | "every monday, wednesday, friday" |
-| "once a week" | "every week" |
-| "by Friday" | "friday" (one-time) |
+| "каждое утро" | "every day at 6am" |
+| "каждый день" | "every day" |
+| "каждый рабочий день" | "every weekday" |
+| "3 раза в неделю" | "every monday, wednesday, friday" |
+| "раз в неделю" | "every week" |
+| "до пятницы" | "friday" (one-time) |
## Anti-Patterns
Avoid creating process goals that are:
-- Too vague: "Work on project" (how much? when?)
+- Too vague: "Работать над проектом" (how much? when?)
- Too ambitious: "4h deep work 5 days a week" (unsustainable)
-- Untrackable: "Think about strategy" (not measurable)
+- Untrackable: "Думать о стратегии" (not measurable)
Good process goals are:
- Specific in action
diff --git a/vault/.claude/skills/dbrain-processor/references/report-template.md b/vault/.claude/skills/dbrain-processor/references/report-template.md
index 6103607..a549e6f 100644
--- a/vault/.claude/skills/dbrain-processor/references/report-template.md
+++ b/vault/.claude/skills/dbrain-processor/references/report-template.md
@@ -44,6 +44,10 @@ NO unsupported tags: div, span, br, p, table, tr, td
<b>✅ Создано задач:</b> {M}
• {task_name} <i>({priority}, {due})</i>
+<b>🏢 Business:</b>
+• {client_name} — {action/status}
+<i>{N} клиентов упомянуто</i>
+
<b>📅 Загрузка на неделю:</b>
Пн: {n} | Вт: {n} | Ср: {n} | Чт: {n} | Пт: {n} | Сб: {n} | Вс: {n}
@@ -79,6 +83,13 @@ Count saved, list with category emoji:
Count created, list with priority and due date.
Format: • Task name <i>(p2, friday)</i>
+### Business Activity (🏢)
+Show ONLY if client/project mentions exist.
+- Max 5 clients
+- If CRM status changed → add note
+- Format: • {Client} — {action}
+- Footer: <i>{N} клиентов упомянуто</i>
+
### Week Load (📅)
Call find-tasks-by-date for 7 days.
Format: Пн: 4 | Вт: 2 | ...
diff --git a/vault/.claude/skills/dbrain-processor/references/rules.md b/vault/.claude/skills/dbrain-processor/references/rules.md
index baac161..d26ca17 100644
--- a/vault/.claude/skills/dbrain-processor/references/rules.md
+++ b/vault/.claude/skills/dbrain-processor/references/rules.md
@@ -57,7 +57,7 @@ For tasks with details:
Before saving any thought or task, check:
- Это масштабируется?
- Это можно автоматизировать?
-- Это усиливает экспертизу/бренд?
+- Это усиливает экспертизу [Your Business]?
- Это приближает к продукту/SaaS?
If 2+ yes → boost priority.
diff --git a/vault/.claude/skills/dbrain-processor/references/todoist.md b/vault/.claude/skills/dbrain-processor/references/todoist.md
index 996ada7..310f9c2 100644
--- a/vault/.claude/skills/dbrain-processor/references/todoist.md
+++ b/vault/.claude/skills/dbrain-processor/references/todoist.md
@@ -1,28 +1,47 @@
# Todoist Integration
-<!--
-╔══════════════════════════════════════════════════════════════════╗
-║ КАК НАСТРОИТЬ ЭТОТ ФАЙЛ ║
-╠══════════════════════════════════════════════════════════════════╣
-║ 1. Замените [Your Clients] на имена ваших клиентов ║
-║ 2. Замените [Your Company] на название вашей компании ║
-║ 3. Замените [@your_channel] на ваш Telegram-канал ║
-║ 4. Измените примеры задач на релевантные для вас ║
-║ 5. Удалите этот комментарий после настройки ║
-╚══════════════════════════════════════════════════════════════════╝
--->
-
-## Available MCP Tools
+## Task Links Format
+
+ВАЖНО: Todoist изменил формат ссылок. Используй НОВЫЙ формат:
+
+✅ Правильно: `https://app.todoist.com/app/task/{task_id}`
+❌ Устарело: `https://todoist.com/showTask?id={task_id}`
+❌ Устарело: `https://todoist.com/app/task/{task_id}`
+
+Если MCP tool вернул task с `url` полем — используй его напрямую.
+Если нужно построить ссылку из task_id — используй формат выше.
+
+---
+
+## Todoist через mcp-cli
+
+**ВСЕГДА используй mcp-cli. НЕ используй MCP tools напрямую.**
### Reading Tasks
-- `get-overview` — all projects with hierarchy
-- `find-tasks` — search by text, project, section
-- `find-tasks-by-date` — tasks by date range
+
+```bash
+# Обзор всех проектов
+mcp-cli call todoist get-overview '{}'
+
+# Поиск по тексту, проекту, секции
+mcp-cli call todoist find-tasks '{"searchText": "keyword"}'
+
+# Задачи по дате
+mcp-cli call todoist find-tasks-by-date '{"startDate": "today", "daysCount": 7}'
+```
### Writing Tasks
-- `add-tasks` — create new tasks
-- `complete-tasks` — mark as done
-- `update-tasks` — modify existing
+
+```bash
+# Создать задачу
+mcp-cli call todoist add-tasks '{"tasks": [{"content": "Task", "dueString": "tomorrow", "priority": 2}]}'
+
+# Завершить задачу
+mcp-cli call todoist complete-tasks '{"ids": ["task_id"]}'
+
+# Обновить задачу
+mcp-cli call todoist update-tasks '{"tasks": [{"id": "task_id", "content": "New title"}]}'
+```
---
@@ -30,11 +49,8 @@
### 1. Check Workload (REQUIRED)
-```
-find-tasks-by-date:
- startDate: "today"
- daysCount: 7
- limit: 50
+```bash
+mcp-cli call todoist find-tasks-by-date '{"startDate": "today", "daysCount": 7, "limit": 50}'
```
Build workload map:
@@ -50,9 +66,8 @@ Sun: 0 tasks
### 2. Check Duplicates (REQUIRED)
-```
-find-tasks:
- searchText: "key words from new task"
+```bash
+mcp-cli call todoist find-tasks '{"searchText": "key words from new task"}'
```
If similar exists → mark as duplicate, don't create.
@@ -86,7 +101,7 @@ Based on user's work context (see [ABOUT.md](ABOUT.md)):
If entry matches 2+ filters → boost priority by 1 level:
- Это масштабируется?
- Это можно автоматизировать?
-- Это усиливает экспертизу/бренд?
+- Это усиливает экспертизу [Your Business]?
- Это приближает к продукту/SaaS?
---
@@ -120,24 +135,23 @@ If entry matches 2+ filters → boost priority by 1 level:
## Task Creation
+```bash
+mcp-cli call todoist add-tasks '{"tasks": [{"content": "Task title", "dueString": "friday", "priority": 4}]}'
```
-add-tasks:
- tasks:
- - content: "Task title"
- dueString: "friday" # MANDATORY
- priority: "p4" # based on domain
- projectId: "..." # if known
+
+С projectId:
+```bash
+mcp-cli call todoist add-tasks '{"tasks": [{"content": "Task title", "dueString": "friday", "priority": 4, "projectId": "..."}]}'
```
### Task Title Style
User prefers: прямота, ясность, конкретика
-<!-- Замените примеры на релевантные для вас -->
✅ Good:
-- "Отправить презентацию клиенту"
-- "Созвон с командой по проекту"
-- "Написать пост про [тема]"
+- "Отправить презентацию [Client A]"
+- "Созвон с командой по AI-агентам"
+- "Написать пост про Claude MCP"
❌ Bad:
- "Подумать о презентации"
@@ -155,22 +169,41 @@ If target day has 3+ tasks:
## Project Detection
-<!--
-Настройте под свои проекты в Todoist.
-Замените примеры клиентов и название канала.
--->
+Based on work domains:
| Keywords | Project |
|----------|---------|
-| [Your Client Names], клиент, бренд | Client Work |
-| [Your Company], команда, найм, процессы | Company Ops |
+| [Client A], [Client B], клиент, бренд | Client Work |
+| [Your Business], агентство, команда, найм | Agency Ops |
| продукт, SaaS, MVP | Product |
-| пост, [@your_channel], контент | Content |
+| пост, @yourbrand, контент | Content |
If unclear → use Inbox (no projectId).
---
+## Client Labels
+
+При создании задач связанных с клиентом, добавляй label.
+
+### Format
+`client:{kebab-case-name}`
+
+### Примеры
+- client:acme-corp
+- client:techco
+- client:phonebrand
+
+### Использование
+```bash
+mcp-cli call todoist add-tasks '{"tasks": [{"content": "Follow-up [Client A] по проекту", "labels": ["client:acme-corp", "deadline"]}]}'
+```
+
+### Фильтр в Todoist
+`@client:acme-corp` — все задачи по [Client A]
+
+---
+
## Anti-Patterns (НЕ СОЗДАВАТЬ)
Based on user preferences:
@@ -198,3 +231,50 @@ WRONG output:
CORRECT output:
"Ошибка создания задачи: [exact error from MCP tool]"
+
+---
+
+## Recurring Tasks for Process Goals
+
+When creating process commitments → use dueString with recurring pattern.
+
+### Recurring Patterns
+
+| Process Description | dueString |
+|---------------------|-----------|
+| каждое утро в 6 | every day at 6am |
+| каждый день | every day |
+| каждый рабочий день | every weekday |
+| 3 раза в неделю | every monday, wednesday, friday |
+| раз в неделю | every week |
+| каждый понедельник | every monday |
+| каждую пятницу | every friday |
+
+### Example: Creating Process Goal Tasks
+
+```bash
+mcp-cli call todoist add-tasks '{"tasks": [
+ {"content": "2h deep work: программа [Client B]", "dueString": "every day at 6am", "priority": 2, "labels": ["process-goal"]},
+ {"content": "1 outreach для поиска 2го спикера", "dueString": "every weekday", "priority": 3, "labels": ["process-goal"]}
+]}'
+```
+
+### Label for Process Goals
+
+Use label `process-goal` for recurring tasks created from Process Commitments.
+This allows easy filtering and cleanup.
+
+### When to Create Recurring
+
+Create recurring tasks when:
+- Generating weekly digest (new week planning)
+- User explicitly asks for process goal setup
+- Transforming outcome goal to process (if user confirms)
+
+### Cleanup Stale Recurring
+
+In weekly digest, check:
+```bash
+mcp-cli call todoist find-tasks '{"labels": ["process-goal"]}'
+```
+If task from previous week → warn user to complete or delete
diff --git a/vault/.claude/skills/graph-builder/SKILL.md b/vault/.claude/skills/graph-builder/SKILL.md
index a694e7f..3dc5fd6 100644
--- a/vault/.claude/skills/graph-builder/SKILL.md
+++ b/vault/.claude/skills/graph-builder/SKILL.md
@@ -1,75 +1,210 @@
---
name: graph-builder
-description: Analyze and build knowledge graph links in Obsidian vault. Find orphan notes, suggest connections, add backlinks, visualize link structure. Triggers on /graph, "analyze links", "find orphans", "suggest connections".
+description: Analyze and build knowledge graph links in Obsidian vault. Runs a deterministic script for analysis, then the agent adds semantic links to orphan files. Three domains: Personal, Business, Projects.
+allowed-tools: Bash(uv run:*), Bash(rg:*), Read, Edit
+depends_on: []
---
# Graph Builder
Analyze vault link structure and build meaningful connections between notes.
-## Use Cases
+## Architecture
-1. **Analyze** — Statistics and insights about vault graph
-2. **Find Orphans** — Notes without incoming/outgoing links
-3. **Suggest Links** — AI-powered connection recommendations
-4. **Add Links** — Batch link creation based on content analysis
-5. **Visualize** — Export graph data for visualization
+```
++------------------------------------------+
+| 1. SCRIPT analyze.py (deterministic) |
+| -> vault-graph.json + report.md |
++-----------------+------------------------+
+ |
+ v
++------------------------------------------+
+| 2. AGENT (you) |
+| -> orphan analysis |
+| -> semantic links |
+| -> frontmatter updates |
+| -> HTML report |
++------------------------------------------+
+```
-## Quick Commands
+## Trigger
-| Command | Action |
-|---------|--------|
-| `/graph analyze` | Full vault analysis with stats |
-| `/graph orphans` | List unconnected notes |
-| `/graph suggest` | Get link suggestions |
-| `/graph add` | Apply suggested links |
+- `/graph` -- manual run
+- After `dbrain-processor` in chain (optional)
+- Weekly: full rebuild
+
+---
-## Analysis Output
+## STEP 1: Run the script
+```bash
+uv run vault/.claude/skills/graph-builder/scripts/analyze.py
```
-📊 Vault Graph Analysis
-Total notes: 247
-Total links: 892
-Orphan notes: 12
-Most connected: [[MEMORY]] (47 links)
-Weakest domain: learnings/ (avg 1.2 links/note)
+**Script does:**
+1. Traverses all .md files in vault/
+2. Parses frontmatter
+3. Extracts wiki-links `[[path]]` and `[[path|alias]]`
+4. Determines domain (business, projects, personal)
+5. Finds orphan files (no links)
+6. Finds broken links
+7. Generates `vault/.graph/vault-graph.json`
+8. Generates `vault/.graph/report.md`
+
+**CRITICAL:** Always run the script first! It provides up-to-date data.
+
+---
-🔗 Suggested connections:
-• [[Project A]] ↔ [[Client X]] (mentioned 5x)
-• [[Idea B]] → [[MOC/Ideas]] (category match)
+## STEP 2: Read script output
+
+Read `vault/.graph/vault-graph.json`:
+
+```json
+{
+ "stats": {
+ "total_files": 331,
+ "orphan_files": 147,
+ "broken_links": 167
+ },
+ "orphans": ["path/to/file.md", ...],
+ "broken_links": [{"from": "...", "to": "..."}, ...]
+}
```
-## Domain Configuration
+---
+
+## STEP 3: Analyze orphan files
-Domains are configured in `references/domains.md`. Default structure:
+For each orphan file (start with **non-daily** files):
-- **daily/** — Daily journal entries
-- **thoughts/** — Processed ideas, reflections, learnings
-- **goals/** — Goal cascade files
-- **MOC/** — Maps of Content (index pages)
-- **projects/** — Project notes
+1. **Read the file content**
+2. **Find potential links:**
+ - Company mentions -> `business/crm/{company}.md`
+ - People mentions -> search in contacts/
+ - Tags -> files with matching tags
+ - Dates -> daily/ for that day
+ - Topics -> thoughts/learnings/, MOC/
-## Link Building Strategy
+3. **Suggest links** -- add to frontmatter `related: []`
-1. **Entity extraction** — Find mentions of existing notes
-2. **Category mapping** — Connect notes to relevant MOCs
-3. **Temporal links** — Link daily entries to related thoughts
-4. **Cross-domain** — Bridge domains (project ↔ goal ↔ daily)
+### Link search patterns
-## Scripts
+| Mention | Link |
+|---------|------|
+| Acme Corp, Acme | `[[business/crm/acme-corp]]` |
+| PhoneBrand | `[[business/crm/phone-brand]]` |
+| TechCo | `[[business/crm/tech-co]]` |
+| SchoolCo | `[[projects/leads/school-co]]` |
+| AutoDealer | `[[projects/leads/auto-dealer]]` |
+| AI, Claude, GPT | thoughts/learnings/ with AI topic |
-- `scripts/analyze.py` — Graph statistics and orphan detection
-- `scripts/add_links.py` — Batch link insertion
+---
-## References
+## STEP 4: Update frontmatter
+
+**Link format in frontmatter:**
+
+```yaml
+---
+type: learning
+domain: personal
+tags: [ai, marketing]
+related:
+ - "[[business/crm/acme-corp]]"
+ - "[[projects/leads/school-co]]"
+ - "[[thoughts/learnings/agent-memory-system]]"
+---
+```
+
+**Rules:**
+- Only add real links (file exists)
+- Do not duplicate existing links
+- Maximum 5-7 links per file
+- Use `"[[path]]"` format with quotes
+
+---
+
+## STEP 5: Update MOC (if needed)
+
+Check MOC files:
+- `MOC/MOC-learnings.md` -- add new learnings
+- `MOC/MOC-projects.md` -- create if missing
+
+---
-- `references/domains.md` — Domain definitions and rules
-- `references/frontmatter.md` — Frontmatter schema for notes
+## STEP 6: HTML report
+
+**Return RAW HTML for Telegram:**
+
+<b>Graph Builder Report</b>
+
+<b>Analyzed:</b>
+- Files: {total_files}
+- Links: {total_links}
+- Orphans: {orphan_files}
+- Broken links: {broken_links}
+
+<b>Business:</b> {files} files, {links} links
+<b>Projects:</b> {files} files, {links} links
+<b>Personal:</b> {files} files, {links} links
+
+<b>Links added:</b> {count}
+- {file1} -> {file2}
+- {file3} -> {file4}
+
+<b>Needs attention:</b>
+- {broken_count} broken links
+- {orphan_count} orphan files
+
+<i>Details: vault/.graph/report.md</i>
+
+---
+
+## Three domains
+
+### Personal
+- `thoughts/` -- learnings, ideas, reflections
+- `goals/` -- yearly, monthly, weekly
+- `daily/` -- raw entries
+- **Hub:** `MEMORY.md`
+
+### Business
+- `business/crm/` -- clients + deals (N files)
+- `business/network/` -- org structure
+- **Hub:** `business/_index.md`
+
+### Projects
+- `projects/clients/` -- project clients
+- `projects/leads/` -- leads
+- **Hub:** `projects/_index.md`
+
+---
+
+## Orphan processing priority
+
+1. **business/crm/** -- business-critical, many orphans
+2. **thoughts/learnings/** -- valuable knowledge
+3. **projects/** -- active projects
+4. **daily/** -- old entries (low priority)
+
+---
+
+## Do not
+
+- Do not change file content (only frontmatter)
+- Do not add links to non-existent files
+- Do not process files in .obsidian/, attachments/, backup/
+- Do not create new files without reason
+
+---
+
+## References
-## Output Format
+- `references/domains.md` -- domain details
+- `references/entities.md` -- entity patterns
+- `references/frontmatter.md` -- frontmatter schema
-Reports use plain markdown (for vault notes) or HTML (for Telegram).
+## Relevant Skills
-For vault: Standard markdown with [[wiki-links]]
-For Telegram: HTML tags (b, i, code only)
+- [[vault/.claude/skills/vault-health/SKILL|vault-health]] -- Health scoring, MOC generation, link repair (depends on this skill)
+- [[vault/.claude/skills/dbrain-processor/SKILL|dbrain-processor]] -- Daily entry processing
diff --git a/vault/.claude/skills/graph-builder/references/domains.md b/vault/.claude/skills/graph-builder/references/domains.md
index 47255f9..0052055 100644
--- a/vault/.claude/skills/graph-builder/references/domains.md
+++ b/vault/.claude/skills/graph-builder/references/domains.md
@@ -1,82 +1,123 @@
-# Domain Configuration
-
-Domains define the organizational structure of the vault. Each domain has specific linking rules and priorities.
-
-## Core Domains
-
-### daily/
-**Purpose:** Daily journal entries, raw captures
-**Format:** `YYYY-MM-DD.md`
-**Linking:**
-- Outgoing to thoughts/ when content is processed
-- Outgoing to projects/ when project mentioned
-- Should reference MOCs for categorization
-
-### thoughts/
-**Purpose:** Processed and refined ideas
-**Subdirectories:**
-- `ideas/` — Creative concepts, innovations
-- `reflections/` — Personal insights, lessons learned
-- `learnings/` — Knowledge captured from reading/experience
-- `projects/` — Project-specific notes
-
-**Linking:**
-- Incoming from daily/ (source entries)
-- Outgoing to MOC/ (categorization)
-- Cross-links within thoughts/ (related concepts)
-
-### goals/
-**Purpose:** Goal hierarchy and tracking
-**Files:**
-- `0-vision-3y.md` — Long-term vision
-- `1-yearly-YYYY.md` — Annual goals
-- `2-monthly.md` — Monthly priorities
-- `3-weekly.md` — Weekly focus
-
-**Linking:**
-- Incoming from thoughts/ (ideas aligned with goals)
-- Incoming from daily/ (progress updates)
-- Should be highly connected as navigation hubs
-
-### MOC/
-**Purpose:** Maps of Content — index pages
-**Linking:**
-- Incoming from all domains (everything should have a MOC)
-- Outgoing to related MOCs
-- Central navigation hubs
-
-### projects/
-**Purpose:** Active project documentation
-**Linking:**
-- Incoming from daily/ (work logs)
-- Incoming from thoughts/ (related ideas)
-- Outgoing to goals/ (alignment)
-
-## Link Priority Rules
-
-When suggesting links, prioritize:
-
-1. **Orphan → MOC** — Every note should belong to a Map of Content
-2. **Daily → Thought** — Processed entries link to their refined notes
-3. **Thought → Goal** — Ideas should align with goals
-4. **Cross-domain** — Bridge related concepts across domains
-
-## Custom Domains
-
-Add custom domains by creating subdirectories and documenting them here:
-
-```markdown
-### your-domain/
-**Purpose:** Description
-**Linking:** Rules for incoming/outgoing links
+# Domains
+
+Three knowledge organization domains in the vault.
+
+## Personal
+
+**Path:** `thoughts/`, `goals/`, `daily/`, `MOC/`, `MEMORY.md`
+
+**Content:**
+- Personal thoughts and reflections
+- Goals (yearly -> monthly -> weekly)
+- Daily entries
+- Learnings and ideas
+
+**Hub:** `MEMORY.md` -- central context
+
+**Frontmatter:**
+```yaml
+domain: personal
+type: learning | reflection | idea | project
```
-## Entity Patterns
+---
+
+## Business
+
+**Path:** `business/`
+
+**Structure:**
+```
+business/
++-- _index.md # Entry point, dataview queries
++-- crm/ # Clients + deals
+| +-- acme-corp.md
+| +-- client-b.md
+| +-- ...
++-- network/ # Org structure (Your Holding)
+| +-- founders.md
+| +-- partner-a.md
+| +-- partner-b.md
++-- events/ # Events
+```
+
+**Hub:** `business/_index.md`
+
+**Frontmatter (CRM):**
+```yaml
+domain: business
+type: crm
+industry: FMCG | Electronics | Banks | Pharma | Retail
+priority: High | Mid | Low
+status: Active | Prospect | Dormant | Declined
+region: UZ | KZ | BY
+owner: [Your Name] | [Team Member]
+deal_status: In progress | Tender | Proposal sent
+deal_deadline: YYYY-MM-DD
+```
+
+**Key clients:**
+- Client-A (FMCG, High, Active)
+- Client-B (Electronics, High, Active)
+- Client-C (Electronics, Mid, Active)
+- Client-D (FMCG, Mid, Prospect)
+
+---
-Common patterns to detect for auto-linking:
+## Projects
-- `[[Note Name]]` — Existing wiki-links
-- `@mention` — People/contacts (if contacts domain exists)
-- `#tag` — Tags that may map to notes
-- Project names — Match against projects/ directory
-- Dates — Link to daily/ entries
+**Path:** `projects/`
+
+**Structure:**
+```
+projects/
++-- _index.md # Entry point
++-- clients/ # Project clients
+| +-- client-a.md
+| +-- client-b.md
+| +-- client-c.md
+| +-- client-d.md
++-- leads/ # Leads
+ +-- lead-a.md
+ +-- lead-b.md
+```
+
+**Hub:** `projects/_index.md`
+
+**Frontmatter:**
+```yaml
+domain: projects
+type: client | lead
+company: Name
+industry: Auto | IT | Retail | Education
+status: APPROVED | Proposal sent | Hot | Cold
+responsible: Name
+```
+
+**Difference from Business:**
+- Business = main business (agency, services)
+- Projects = personal side projects (consulting, training)
+
+---
+
+## Cross-domain links
+
+| Link | Example |
+|------|---------|
+| Projects -> Business | `lead-a` -> `partner-b` (partner) |
+| Personal -> Business | `learning` -> `acme-corp` (case from practice) |
+| Personal -> Projects | `learning` -> `client-a` (insight from training) |
+| Business -> Contacts | `acme-corp` -> contacts (contacts) |
+
+---
+
+## Determining domain by path
+
+```python
+def get_domain(path: Path) -> str:
+ if "business" in path.parts:
+ return "business"
+ elif "projects" in path.parts:
+ return "projects"
+ return "personal"
+```
diff --git a/vault/.claude/skills/graph-builder/references/entities.md b/vault/.claude/skills/graph-builder/references/entities.md
new file mode 100644
index 0000000..09cca3e
--- /dev/null
+++ b/vault/.claude/skills/graph-builder/references/entities.md
@@ -0,0 +1,157 @@
+# Entity Extraction Patterns
+
+Patterns for finding entities in text.
+
+## Companies (Business CRM)
+
+### Exact matches
+
+| Pattern | File |
+|---------|------|
+| Client-A, ClientA | `business/crm/client-a.md` |
+| Client-B | `business/crm/client-b.md` |
+| Client-C | `business/crm/client-c.md` |
+| Client-D | `business/crm/client-d.md` |
+| Client-E | `business/crm/client-e.md` |
+| Client-F | `business/crm/client-f.md` |
+| Client-G | `business/crm/client-g.md` |
+| Client-H | `business/crm/client-h.md` |
+| Client-I | `business/crm/client-i.md` |
+| Client-J | `business/crm/client-j.md` |
+
+### Regex for companies
+
+```python
+COMPANY_PATTERNS = [
+ r'\b(Client-A|ClientA)\b',
+ r'\b(Client-B)\b',
+ r'\b(Client-C)\b',
+ r'\b(Client-D)\b',
+ r'\b(Client-E)\b',
+ r'\bClient-F\b',
+ r'\b(Client-G)\b',
+ r'\bClient-H\b',
+ r'\bClient-I\b',
+]
+```
+
+---
+
+## Companies (Projects)
+
+| Pattern | File |
+|---------|------|
+| Project-Client-A | `projects/clients/project-client-a.md` |
+| Project-Client-B | `projects/clients/project-client-b.md` |
+| Project-Client-C | `projects/clients/project-client-c.md` |
+| Project-Client-D | `projects/clients/project-client-d.md` |
+| Lead-A | `projects/leads/lead-a.md` |
+| Lead-B | `projects/leads/lead-b.md` |
+
+---
+
+## People
+
+### Name format
+
+```python
+# Names in your language
+LOCAL_NAME = r'[A-Z][a-z]+\s+[A-Z][a-z]+'
+# Examples: [First Name] [Last Name]
+
+# English names
+ENGLISH_NAME = r'[A-Z][a-z]+\s+[A-Z][a-z]+'
+# Examples: [First Name] [Last Name]
+```
+
+### Telegram handles
+
+```python
+TELEGRAM_HANDLE = r'@([a-zA-Z0-9_]+)'
+# Examples: @username1, @username2, @username3
+```
+
+---
+
+## Projects
+
+### Project patterns
+
+```python
+PROJECT_PATTERNS = [
+ r'project\s+([A-Za-z0-9\s]+)',
+ r'(?:NCP|SMM|BTL|ATL)\s+([A-Za-z]+)',
+ r'tender\s+([A-Za-z]+)',
+]
+```
+
+### Active projects
+
+| Mention | Link |
+|---------|------|
+| Client-A Campaign | `business/crm/client-a.md` |
+| Client-B SMM | `business/crm/client-b.md` |
+| Client-C Project | `business/crm/client-c.md` |
+
+---
+
+## Topics (for learnings)
+
+| Keywords | Links to |
+|----------|----------|
+| Claude, AI agent, LLM | `thoughts/learnings/` with AI |
+| Second Brain, Obsidian, PKM | Methodology |
+| Zettelkasten, graph | Knowledge organization |
+| Prompt, prompt engineering | AI techniques |
+| Marketing, SMM, content | Business |
+
+---
+
+## Finding file for entity
+
+```python
+def find_file_for_entity(entity: str, vault_path: Path) -> Path | None:
+ """Find file for an entity."""
+
+ # Normalize: Client-A -> client-a
+ slug = entity.lower().replace(" ", "-")
+
+ # Search in CRM
+ crm_path = vault_path / "business" / "crm" / f"{slug}.md"
+ if crm_path.exists():
+ return crm_path
+
+ # Search in Projects
+ for subdir in ["clients", "leads"]:
+ path = vault_path / "projects" / subdir / f"{slug}.md"
+ if path.exists():
+ return path
+
+ # Fuzzy search by filename
+ for f in vault_path.rglob("*.md"):
+ if slug in f.stem.lower():
+ return f
+
+ return None
+```
+
+---
+
+## Link normalization
+
+```python
+def normalize_link(link: str) -> str:
+ """Normalize wiki-link."""
+
+ # Remove section: [[file#section]] -> file
+ link = link.split("#")[0]
+
+ # Remove alias: [[file|alias]] -> file
+ link = link.split("|")[0]
+
+ # Add .md if missing
+ if not link.endswith(".md"):
+ link = link + ".md"
+
+ return link
+```
diff --git a/vault/.claude/skills/graph-builder/references/frontmatter.md b/vault/.claude/skills/graph-builder/references/frontmatter.md
index e24cbcc..eab5a9a 100644
--- a/vault/.claude/skills/graph-builder/references/frontmatter.md
+++ b/vault/.claude/skills/graph-builder/references/frontmatter.md
@@ -1,110 +1,252 @@
# Frontmatter Schema
-Standard YAML frontmatter for vault notes.
+YAML frontmatter schema for vault files.
-## Basic Schema
+## Basic schema (all files)
```yaml
---
-title: Note Title
-created: YYYY-MM-DD
-modified: YYYY-MM-DD
-tags: [tag1, tag2]
-aliases: [alternate-name]
+type: string # Record type (see below)
+domain: string # business | projects | personal
+description: string # Retrieval filter ~150 chars (NOT summary -- adds scope/mechanism/implication beyond title)
+tags: [string] # Tags for categorization
+related: [string] # Wiki-links to related files
+created: date # Creation date (YYYY-MM-DD)
+updated: date # Update date
---
```
-## Extended Schema
+### Description field
+
+**NOT a summary** -- description adds information BEYOND the title, does not repeat it.
+This is a **retrieval filter**: the agent reads title + description and decides whether to open the file.
+
+**Rules:**
+- ~150 characters max
+- Adds scope, mechanism or implication
+- Does NOT repeat the title
+- Specifics > abstractions
+
+**Examples:**
```yaml
----
-title: Note Title
-created: YYYY-MM-DD
-modified: YYYY-MM-DD
-tags: [tag1, tag2]
-aliases: [alternate-name]
-type: idea | reflection | learning | project | moc | daily
-domain: thoughts | goals | projects | daily
-status: draft | active | archived
-links:
- - "[[Related Note]]"
- - "[[Another Note]]"
----
+# CRM (title = acme-corp.md):
+description: "Major FMCG client, Project $XXK active deal, promo codes in progress"
+
+# Thought (title = 2026-02-05-hormonal-agent-algorithm.md):
+description: "4 hormones as sine waves + noise -> mood -> intentions. Gives agent free will."
+
+# Learning (title = 2026-01-30-session-persistence.md):
+description: "JSONL append-only files for interaction history. Pattern from Clawdbot."
```
-## Field Definitions
+---
+
+## Record types
+
+### Personal domain
+
+| type | Folder | Description |
+|------|--------|-------------|
+| learning | thoughts/learnings/ | Knowledge, discoveries, TIL |
+| idea | thoughts/ideas/ | Ideas, concepts |
+| reflection | thoughts/reflections/ | Reflections, conclusions |
+| project | thoughts/projects/ | Project notes |
+
+### Business domain
+
+| type | Folder | Description |
+|------|--------|-------------|
+| crm | business/crm/ | Client + deals |
+| network | business/network/ | Org structure |
+| event | business/events/ | Events |
+
+### Projects domain
-| Field | Type | Required | Description |
-|-------|------|----------|-------------|
-| title | string | Yes | Display title for the note |
-| created | date | Yes | Creation date (YYYY-MM-DD) |
-| modified | date | No | Last modification date |
-| tags | array | No | Categorization tags |
-| aliases | array | No | Alternative names for linking |
-| type | enum | No | Note type classification |
-| domain | enum | No | Primary domain |
-| status | enum | No | Note lifecycle status |
-| links | array | No | Explicit related notes |
+| type | Folder | Description |
+|------|--------|-------------|
+| client | projects/clients/ | Project client |
+| lead | projects/leads/ | Lead |
-## Type Values
+---
+
+## CRM Schema (business/crm/)
-- `idea` — Creative concept or innovation
-- `reflection` — Personal insight or lesson
-- `learning` — Knowledge from external source
-- `project` — Project documentation
-- `moc` — Map of Content index
-- `daily` — Daily journal entry
+```yaml
+---
+type: crm
+domain: business
+description: string # Retrieval filter: key client context (~150 chars)
+industry: FMCG | Electronics | Banks | Pharma | Retail | Auto | IT | Telecom
+priority: High | Mid | Low
+status: Active | Prospect | Dormant | Declined
+region: UZ | KZ | BY | Global
+owner: [Your Name] | [Team Member]
+responsible: string # Responsible person on client side
+
+# Active deal (if any)
+deal_status: In progress | Tender | Proposal sent | Meeting held
+deal_deadline: YYYY-MM-DD
+
+# Links
+related:
+ - "[[thoughts/learnings/...]]"
+
+updated: YYYY-MM-DD
+---
+```
-## Status Values
+**Example:**
-- `draft` — Work in progress
-- `active` — Current and maintained
-- `archived` — No longer active, kept for reference
+```yaml
+---
+type: crm
+domain: business
+industry: FMCG
+priority: High
+status: Active
+region: UZ, KZ
+owner: [Your Name]
+deal_status: In progress
+deal_deadline: 2026-02-09
+updated: 2026-01-29
+---
+```
-## Usage in Graph Analysis
+---
-The graph analyzer uses frontmatter to:
+## Learning Schema (thoughts/learnings/)
-1. **Classify notes** by type and domain
-2. **Detect orphans** based on links field
-3. **Suggest connections** using tags and aliases
-4. **Track freshness** via modified date
+```yaml
+---
+type: learning
+domain: personal
+description: string # Retrieval filter: key insight (~150 chars)
+tags: [ai, marketing, automation, ...]
+source: daily/YYYY-MM-DD.md | URL | @mention
+related:
+ - "[[business/crm/acme-corp]]"
+ - "[[projects/leads/lead-a]]"
+created: YYYY-MM-DD
+---
+```
-## Example Notes
+**Example:**
-### Thought Note
```yaml
---
-title: API Design Principles
-created: 2025-01-15
-tags: [development, architecture]
type: learning
-domain: thoughts
+domain: personal
+tags: [ai, marketing, panel]
+source: event
+related:
+ - "[[projects/leads/lead-a]]"
+ - "[[business/network/partner-a]]"
+created: 2026-01-27
---
```
-### MOC Note
+---
+
+## Projects Client Schema
+
```yaml
---
-title: Development Index
-created: 2024-06-01
-modified: 2025-01-20
-tags: [index, development]
-type: moc
-aliases: [Dev MOC, Development Map]
+type: client
+domain: projects
+description: string # Retrieval filter: client type and status (~150 chars)
+company: string
+industry: Auto | IT | Retail | Pharma | Education | Finance
+region: BY | UZ | KZ | RU
+status: APPROVED | Proposal sent | In progress | Completed
+responsible: string
+budget: string # Optional
+related:
+ - "[[thoughts/learnings/...]]"
+updated: YYYY-MM-DD
---
```
-### Project Note
+---
+
+## Projects Lead Schema
+
```yaml
---
-title: Project Alpha
-created: 2025-01-01
-tags: [project, active]
-type: project
-status: active
-links:
- - "[[goals/3-weekly]]"
- - "[[MOC/Projects]]"
+type: lead
+domain: projects
+description: string # Retrieval filter: who and why (~150 chars)
+company: string
+industry: Education | IT | ...
+region: UZ | ...
+status: Hot | Warm | Cold | Contacted | Proposal sent
+source: string # Where lead came from
+responsible: string
+next_action: string # Next step
+related: []
+updated: YYYY-MM-DD
+---
+```
+
+---
+
+## Related format
+
+**Correct:**
+
+```yaml
+related:
+ - "[[business/crm/acme-corp]]"
+ - "[[thoughts/learnings/agent-memory-system]]"
+```
+
+**Incorrect:**
+
+```yaml
+# Without quotes (may break YAML)
+related:
+ - [[business/crm/acme-corp]]
+
+# With alias in frontmatter (redundant)
+related:
+ - "[[business/crm/acme-corp|Acme Corp]]"
+```
+
---
+
+## Adding links by agent
+
+When updating frontmatter:
+
+1. **Read** existing frontmatter
+2. **Get** current `related: []`
+3. **Add** new links (no duplicates)
+4. **Verify** that files exist
+5. **Write** updated frontmatter
+
+```python
+def add_related(content: str, new_links: list[str]) -> str:
+ """Add links to frontmatter."""
+
+ # Parse frontmatter
+ match = re.match(r'^---\n(.*?)\n---', content, re.DOTALL)
+ if not match:
+ return content
+
+ fm = yaml.safe_load(match.group(1)) or {}
+
+ # Get current links
+ existing = set(fm.get("related", []))
+
+ # Add new (format with quotes)
+ for link in new_links:
+ formatted = f'[[{link}]]' if not link.startswith('[[') else link
+ existing.add(formatted)
+
+ # Update
+ fm["related"] = sorted(list(existing))
+
+ # Write
+ new_fm = yaml.dump(fm, allow_unicode=True, default_flow_style=False)
+ return f"---\n{new_fm}---\n" + content[match.end():]
```
diff --git a/vault/.claude/skills/todoist-ai/SKILL.md b/vault/.claude/skills/todoist-ai/SKILL.md
index 6cc2fb0..d15b575 100644
--- a/vault/.claude/skills/todoist-ai/SKILL.md
+++ b/vault/.claude/skills/todoist-ai/SKILL.md
@@ -1,15 +1,34 @@
---
name: todoist-ai
-description: MCP server and tools for connecting AI agents to Todoist
+description: Todoist integration via mcp-cli for task management
+depends_on: []
---
# todoist-ai
-MCP server and tools for connecting AI agents to Todoist
+Todoist integration via mcp-cli.
+
+## CRITICAL
+
+**ALWAYS use mcp-cli. DO NOT use MCP tools directly.**
+
+```bash
+# Today's tasks
+mcp-cli call todoist find-tasks-by-date '{"startDate": "today"}'
+
+# Create task
+mcp-cli call todoist add-tasks '{"tasks": [{"content": "Task", "dueString": "tomorrow", "priority": 2}]}'
+
+# Complete task
+mcp-cli call todoist complete-tasks '{"ids": ["task_id"]}'
+
+# Overview
+mcp-cli call todoist get-overview '{}'
+```
## Description
-A set of tools to connect to AI agents, to allow them to use Todoist on a user's behalf. Includes MCP support.
+A set of tools to connect to AI agents, to allow them to use Todoist on a user's behalf. Uses mcp-cli wrapper for stable connections.
**Repository:** [Doist/todoist-ai](https://github.com/Doist/todoist-ai)
**Language:** TypeScript
@@ -19,17 +38,16 @@ A set of tools to connect to AI agents, to allow them to use Todoist on a user's
## When to Use This Skill
Use this skill when you need to:
-- Understand how to use todoist-ai
+- Create, update, or complete tasks in Todoist
+- Check workload or task status
- Look up API documentation
- Find usage examples
-- Check for known issues or recent changes
-- Review release history
## Quick Reference
### Repository Info
-- **Homepage:**
-- **Topics:**
+- **Homepage:**
+- **Topics:**
- **Open Issues:** 18
- **Last Updated:** 2025-12-13
@@ -57,3 +75,7 @@ See README.md for complete usage instructions and examples.
---
**Generated by Skill Seeker** | GitHub Repository Scraper
+
+## Relevant Skills
+
+- [[vault/.claude/skills/dbrain-processor/SKILL|dbrain-processor]] — Daily entry processing