Skip to content

Create, Evaluate, and Connect AI Skills

docs: revert extra release and dependency notes

Icarus-Chen57032e8b860d
diff --git a/README.md b/README.md
index 905c935..986c6ae 100644
--- a/README.md
+++ b/README.md
@@ -41,10 +41,6 @@ SkillNet provides unified infrastructure for the agent skill lifecycle:
## News
-- **[2026-09-22]** [**skillnet-ai 0.1.1**](https://pypi.org/project/skillnet-ai/0.1.1/)
- is available on PyPI, with updated local skill analysis and task routing through
- Claude or Codex Agent SDKs.
-
- **[2026-08-20]** The updated [**SkillNet report**](https://arxiv.org/abs/2603.04448) presents
**SkillNet-Gym**, with executable benchmarks for skill construction, retrieval, and composition,
and **SkillNet-Fabric**, which routes tasks through a Wiki built for each task.
@@ -93,20 +89,17 @@ https://github.com/user-attachments/assets/9f9d35b0-36fd-4d7d-a072-39afa380b241
Requires Python 3.10 or newer.
```bash
-pip install -U skillnet-ai
+pip install skillnet-ai
```
-Choose optional dependencies for analysis and routing. Each command includes the base package:
+Install optional dependencies for analysis and routing:
```bash
-pip install -U "skillnet-ai[graph]" # scenario analysis
-pip install -U "skillnet-ai[graph,claude]" # analysis and routing via Claude
-pip install -U "skillnet-ai[graph,codex]" # analysis and routing via Codex
+pip install "skillnet-ai[graph]" # scenario analysis
+pip install "skillnet-ai[graph,claude]" # analysis and routing via Claude
+pip install "skillnet-ai[graph,codex]" # analysis and routing via Codex
```
-Use `skillnet-ai[graph,claude,codex]` to install both routing backends. Select one
-with `backend="claude"` or `backend="codex"` (CLI: `--backend`); Claude is the default.
-
### Initialize
```python
@@ -259,10 +252,9 @@ check without a model call.
## Configuration
Search and public downloads need no API key. Create, evaluate, and analyze use an
-OpenAI-compatible Chat Completions endpoint. Analyze and route generate vectors
-through the configured Embedding API and use NumPy to index and compare them
-locally. Route uses the same embedding endpoint and model as analyze, plus a
-separately configured Claude or Codex Agent SDK.
+OpenAI-compatible Chat Completions endpoint. Analyze also needs an embedding
+endpoint; route uses that same embedding endpoint and a separately configured
+Claude or Codex Agent SDK.
Settings resolve in this order: explicit arguments → environment variables →
user configuration → defaults. Load any `.env` file into your environment before
diff --git a/skillnet-ai/README.md b/skillnet-ai/README.md
index 3119046..778e114 100644
--- a/skillnet-ai/README.md
+++ b/skillnet-ai/README.md
@@ -41,20 +41,17 @@ For the full project overview, research context, integrations, and roadmap, see
Requires Python 3.10 or newer.
```bash
-pip install -U skillnet-ai
+pip install skillnet-ai
```
-Choose optional dependencies for analysis and routing. Each command includes the base package:
+Install optional dependencies for analysis and routing:
```bash
-pip install -U "skillnet-ai[graph]" # scenario analysis
-pip install -U "skillnet-ai[graph,claude]" # analysis and routing via Claude
-pip install -U "skillnet-ai[graph,codex]" # analysis and routing via Codex
+pip install "skillnet-ai[graph]" # scenario analysis
+pip install "skillnet-ai[graph,claude]" # analysis and routing via Claude
+pip install "skillnet-ai[graph,codex]" # analysis and routing via Codex
```
-Use `skillnet-ai[graph,claude,codex]` to install both routing backends. Select one
-with `backend="claude"` or `backend="codex"` (CLI: `--backend`); Claude is the default.
-
---
## Quick Start
@@ -258,8 +255,7 @@ comparable capabilities for a task or subtask, subject to their own constraints.
Place each skill in a direct child folder containing a YAML-frontmatter `SKILL.md`.
Folder names are stable IDs; display names may repeat. Analysis reads the full
SKILL.md but does not execute or automatically inspect linked scripts/references.
-Vectors are generated through the configured Embedding API. The `graph` extra
-provides NumPy to store and compare those vectors locally; BM25 requires SQLite FTS5.
+The `graph` extra provides NumPy; BM25 requires SQLite FTS5.
See [endpoint configuration](#analysis-and-routing-endpoints) for the analysis
model and embedding settings.