Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.
Python agent-loopagent-pluginsagent-skillsagenticai-agentsclaude-codeclosed-loopcursorgarry-tangbraingstackknowledge-managementloop-engineeringobsidianpeople-crmproductivitysecond-brainself-evolvingverification-harnessworker-agents
feat: ELI5-first rule for explanations in no-ai-slop (v3.15.0)
Huy Tieu36ac9d78d66e
diff --git a/.claude/skills/no-ai-slop/SKILL.md b/.claude/skills/no-ai-slop/SKILL.mdindex 5272ed5..9ed1bea 100644--- a/.claude/skills/no-ai-slop/SKILL.md+++ b/.claude/skills/no-ai-slop/SKILL.md@@ -56,6 +56,8 @@ The rules that carry over at 80%:The 20% we keep outside STE: technical terms, product names, and code identifiers as they are; the writer's own voice when editing a human draft (Editing principles win over STE for a personal blog, chat, or email voice); hedges that express real uncertainty. Do not apply STE word limits to quoted material or code.+**ELI5 first for explanations.** When the job is to explain a concept, a mechanism, or a decision to someone who did not build it, open with an ELI5 paragraph: three sentences max, everyday words, one concrete analogy, no jargon. Then give the technical detail in STE. Skip the ELI5 for status updates, instructions, and replies to the person who wrote the code.+## Output format ladder (adopted 2026-10-02)Same source. When the job is to make the reader understand something, prose is the lowest rung. Pick the highest rung the content and the medium support:diff --git a/.claude/skills/no-ai-slop/eval.md b/.claude/skills/no-ai-slop/eval.mdindex 7957595..4bcc7f7 100644--- a/.claude/skills/no-ai-slop/eval.md+++ b/.claude/skills/no-ai-slop/eval.md@@ -38,7 +38,8 @@ For detect requests, make sure the response names each pattern found with a quot1. For agent-authored text: are instructions 20 words max with one instruction each, descriptive sentences 25 words max, paragraphs 6 sentences max, voice active, and each term used with one meaning?2. Are noun clusters three words max, with articles and connectors kept?-3. Is the output on the right rung of the format ladder, or does the reply offer the next rung in one line when a diagram, page, or video would explain it better?+3. For an explanation to a non-author: does it open with an ELI5 paragraph of three sentences max, with one everyday analogy and no jargon?+4. Is the output on the right rung of the format ladder, or does the reply offer the next rung in one line when a diagram, page, or video would explain it better?## Structural slopdiff --git a/CHANGELOG.md b/CHANGELOG.mdindex f61d91b..10d9a37 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -10,8 +10,9 @@ All notable changes to COG (Cognition + Obsidian + Git) will be documented in thAdapted from [Andrej Karpathy's post of 2026-10-02](https://x.com/karpathy/status/2105819303471976479) on how to read model output faster.- `no-ai-slop` gains a **Controlled-language target**: agent-authored text aims for about 80% of ASD-STE100, the controlled English from aerospace maintenance manuals. Instructions are 20 words max with one action each, descriptive sentences 25 words max, paragraphs 6 sentences max, active voice, one term per meaning, noun clusters three words max, articles kept. Technical terms, code, quotes, and the writer's own voice in edits stay outside the limits.+- `no-ai-slop` gains **ELI5 first for explanations**: an explanation for someone who did not build the thing opens with three sentences of everyday words and one analogy, then the technical detail in STE.- `no-ai-slop` gains an **Output format ladder**: when the goal is understanding, the agent picks the richest rung the content and medium support (prose, diagram, HTML page, explainer video via `release-video`) and offers the next rung in one line instead of building it unasked.-- `eval.md` gains three checks for sentence limits, term consistency, and format choice.+- `eval.md` gains four checks for sentence limits, term consistency, the ELI5 opener, and format choice.- `CLAUDE.md` and `.cursorrules` Response Style carry both rules, so agents that never load the skill still follow them.## [3.14.0] - 2026-09-28diff --git a/CLAUDE.md b/CLAUDE.mdindex ef2001e..abdc68b 100644--- a/CLAUDE.md+++ b/CLAUDE.md@@ -7,7 +7,7 @@Optimize for **information gain, not apparent completeness**. The failure mode is framework slop: ordinary reasoning dressed as a consulting memo. Full pattern list: `.claude/skills/no-ai-slop/SKILL.md` § Structural slop.- Start with the answer or strongest finding; no introduction announcing how you will answer.-- Write at 80% ASD-STE100: instructions 20 words max with one instruction each, descriptive sentences 25 words max, paragraphs 6 sentences max, active voice, one term per meaning, noun clusters three words max, keep articles. Technical terms and the writer's own voice in edits stay as they are. Rules: `.claude/skills/no-ai-slop/SKILL.md` § Controlled-language target.+- Write at 80% ASD-STE100: instructions 20 words max with one instruction each, descriptive sentences 25 words max, paragraphs 6 sentences max, active voice, one term per meaning, noun clusters three words max, keep articles. Technical terms and the writer's own voice in edits stay as they are. Rules: `.claude/skills/no-ai-slop/SKILL.md` § Controlled-language target. An explanation for someone who did not build the thing opens with an ELI5 paragraph: three sentences, everyday words, one analogy.- When the goal is understanding, climb the format ladder: STE prose, then a diagram, then an HTML page, then an explainer video. Use the highest rung the content and medium support, and offer the next rung in one line when it would help. § Output format ladder in the same skill.- Never invent named frameworks, gates, layers, pillars, lenses, or numbered taxonomies unless they exist in the source material or the categorization materially simplifies a complex subject.- No sections for 1-2 paragraphs; default to continuous prose with occasional descriptive headings.diff --git a/skills/no-ai-slop/SKILL.md b/skills/no-ai-slop/SKILL.mdindex 5272ed5..9ed1bea 100644--- a/skills/no-ai-slop/SKILL.md+++ b/skills/no-ai-slop/SKILL.md@@ -56,6 +56,8 @@ The rules that carry over at 80%:The 20% we keep outside STE: technical terms, product names, and code identifiers as they are; the writer's own voice when editing a human draft (Editing principles win over STE for a personal blog, chat, or email voice); hedges that express real uncertainty. Do not apply STE word limits to quoted material or code.+**ELI5 first for explanations.** When the job is to explain a concept, a mechanism, or a decision to someone who did not build it, open with an ELI5 paragraph: three sentences max, everyday words, one concrete analogy, no jargon. Then give the technical detail in STE. Skip the ELI5 for status updates, instructions, and replies to the person who wrote the code.+## Output format ladder (adopted 2026-10-02)Same source. When the job is to make the reader understand something, prose is the lowest rung. Pick the highest rung the content and the medium support:diff --git a/skills/no-ai-slop/eval.md b/skills/no-ai-slop/eval.mdindex 7957595..4bcc7f7 100644--- a/skills/no-ai-slop/eval.md+++ b/skills/no-ai-slop/eval.md@@ -38,7 +38,8 @@ For detect requests, make sure the response names each pattern found with a quot1. For agent-authored text: are instructions 20 words max with one instruction each, descriptive sentences 25 words max, paragraphs 6 sentences max, voice active, and each term used with one meaning?2. Are noun clusters three words max, with articles and connectors kept?-3. Is the output on the right rung of the format ladder, or does the reply offer the next rung in one line when a diagram, page, or video would explain it better?+3. For an explanation to a non-author: does it open with an ELI5 paragraph of three sentences max, with one everyday analogy and no jargon?+4. Is the output on the right rung of the format ladder, or does the reply offer the next rung in one line when a diagram, page, or video would explain it better?## Structural slop