docs: update changelog, readme, and docs for v3.5.0
- Add CHANGELOG.md entry for v3.5.0 with all PR #336 changes - Update README.md: version 3.5.0, agent-agnostic examples, marketplace pipeline, SPA discovery - Update CLAUDE.md: AgentClient architecture, 40 MCP tools, new modules - Update docs/: UML architecture, MCP reference (40 tools, new tool categories), enhancement modes (multi-provider/multi-agent), FAQ - Update src/skill_seekers/mcp/README.md: accurate tool count and paths Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
yusyus
38
CHANGELOG.md
38
CHANGELOG.md
@@ -7,17 +7,55 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
## [3.5.0] - 2026-04-01
|
||||
|
||||
**Theme:** Agent-agnostic architecture, marketplace pipeline, smart SPA discovery, dynamic routing refactor, and removal of artificial limits. 60+ files changed across the codebase (#336).
|
||||
|
||||
### Added
|
||||
- **Agent-agnostic `AgentClient` abstraction** — all 5 enhancers now support Claude, Kimi, Codex, Copilot, OpenCode, and custom agents via a unified interface. Auto-detects agent from API keys instead of hardcoding (#336)
|
||||
- **Kimi CLI integration** with stdin piping and output parsing (#336)
|
||||
- **`MarketplacePublisher`** — publish skills to Claude Code plugin marketplace repos (#336)
|
||||
- **`MarketplaceManager`** — register and manage marketplace repositories (#336)
|
||||
- **`ConfigPublisher`** — push configs to registered config source repos (#336)
|
||||
- **`push_config` MCP tool** for automated config publishing (#336)
|
||||
- **Smart SPA discovery engine** — three-layer discovery: sitemap.xml, llms.txt, SPA nav rendering (#336)
|
||||
- **`"browser": true` config support** for JavaScript SPA sites with browser renderer timeout defaults (60s, domcontentloaded) (#336)
|
||||
- **Dynamic routing via `_build_argv()`** — replaced manual arg forwarding with dynamic forwarder, added 7 missing CLI flags (#336)
|
||||
- **Kotlin language support for codebase analysis** — Full C3.x pipeline support: AST parsing (classes, objects, functions, data/sealed classes, extension functions, coroutines), dependency extraction, design pattern recognition (object declaration→Singleton, companion object→Factory, sealed class→Strategy), test example extraction (JUnit, Kotest, MockK, Spek), language detection patterns, config detection (build.gradle.kts), and extension maps across all analyzers (#287)
|
||||
- **Headless browser rendering** (`--browser` flag) — uses Playwright to render JavaScript SPA sites (React, Vue, etc.) that return empty HTML shells. Auto-installs Chromium on first use. Optional dep: `pip install "skill-seekers[browser]"` (#321)
|
||||
- **`skill-seekers doctor` command** — 8 diagnostic checks (Python version, package install, git, core/optional deps, API keys, MCP server, output dir) with pass/warn/fail status and `--verbose` flag (#316)
|
||||
- **Prompt injection check workflow** — bundled `prompt-injection-check` workflow scans scraped content for injection patterns (role assumption, instruction overrides, delimiter injection, hidden instructions). Added as first stage in `default` and `security-focus` workflows. Flags suspicious content without removing it (#324)
|
||||
- **6 behavioral UML diagrams** — 3 sequence (create pipeline, GitHub+C3.x flow, MCP invocation), 2 activity (source detection, enhancement pipeline), 1 component (runtime dependencies with interface contracts)
|
||||
- **134 new tests** — `test_agent_client.py`, `test_config_publisher.py`, `_build_argv` tests. Total: 3194 passed, 39 expected skips (#336)
|
||||
|
||||
### Changed
|
||||
- **Renamed `claude-enhanced` merge mode to `ai-enhanced`** — backward compatibility alias kept (#336)
|
||||
- **Removed 118+ hardcoded Claude references** across 60+ files (#336)
|
||||
- **Refactored 5 enhancers** to use `AgentClient` abstraction (#336)
|
||||
- **Removed 50-file GitHub API analysis limit** (#336)
|
||||
- **Removed 100-file config extraction limit** (#336)
|
||||
- **Fixed unified scraper default `max_pages`** from 100 to 500 (#336)
|
||||
- **Centralized enhancement timeouts** to 45min default with unlimited support (#336)
|
||||
|
||||
### Fixed
|
||||
- **`scraped_data` list-vs-dict bug** in conflict detection (#336)
|
||||
- **`base_url` passthrough** to doc scraper subprocess (#336)
|
||||
- **URL filtering** now uses base directory correctly (#336)
|
||||
- **C3.x analysis data loss** (#336)
|
||||
- **`--enhance-level` flag** not passed correctly (#336)
|
||||
- **`guide_enhancer` method rename** — `_call_claude_api` renamed to `_call_ai` (#336)
|
||||
- **11 pre-existing test failures** fixed (#336)
|
||||
- **Per-file language detection** in GitHub scraper (#336)
|
||||
- **GitHub language detection crashes with `TypeError`** when API response contains non-integer metadata keys (e.g., `"url"`) — now filters to integer values only (#322)
|
||||
- **C3.x codebase analysis crashes with `TypeError`** — `_run_c3_analysis()` and `_analyze_c3x()` passed removed `enhance_with_ai`/`ai_mode` kwargs to `analyze_codebase()` instead of `enhance_level` (#323)
|
||||
|
||||
### Security
|
||||
- **Removed command injection** via cloned repo script execution (#336)
|
||||
- **Replaced `git add -A`** with targeted staging in marketplace publisher (#336)
|
||||
- **Clear auth tokens** from cached `.git/config` after clone (#336)
|
||||
- **Use `defusedxml`** for sitemap XML parsing (XXE protection) (#336)
|
||||
- **Path traversal validation** for config names (#336)
|
||||
|
||||
## [3.4.0] - 2026-03-21
|
||||
|
||||
### Added
|
||||
|
||||
16
CLAUDE.md
16
CLAUDE.md
@@ -133,13 +133,21 @@ Local codebase analysis features, all opt-out (`--skip-*` flags):
|
||||
|
||||
### MCP Server
|
||||
|
||||
`src/skill_seekers/mcp/server_fastmcp.py` - 26+ tools via FastMCP. Transport: stdio (Claude Code) or HTTP (Cursor/Windsurf). Optional dependency: `pip install -e ".[mcp]"`
|
||||
`src/skill_seekers/mcp/server_fastmcp.py` - 40 tools via FastMCP. Transport: stdio (Claude Code) or HTTP (Cursor/Windsurf). Optional dependency: `pip install -e ".[mcp]"`
|
||||
|
||||
### Enhancement Modes
|
||||
Supporting modules:
|
||||
- `marketplace_publisher.py` - Publish skills to plugin marketplace repositories
|
||||
- `marketplace_manager.py` - Manage marketplace registry
|
||||
- `config_publisher.py` - Push configs to registered config source repositories
|
||||
|
||||
- **API mode** (if `ANTHROPIC_API_KEY` set): Direct Claude API calls
|
||||
- **LOCAL mode** (fallback): Uses Claude Code CLI (free with Max plan)
|
||||
### Enhancement Modes (via AgentClient)
|
||||
|
||||
Enhancement now uses the `AgentClient` abstraction (`src/skill_seekers/cli/agent_client.py`) instead of direct Claude API calls:
|
||||
|
||||
- **API mode** (if API key set): Supports Anthropic, Moonshot/Kimi, Google Gemini, OpenAI
|
||||
- **LOCAL mode** (fallback): Supports Claude Code, Kimi Code, Codex, Copilot, OpenCode, custom agents
|
||||
- Control: `--enhance-level 0` (off) / `1` (SKILL.md only) / `2` (default, balanced) / `3` (full)
|
||||
- Agent selection: `--agent claude|codex|copilot|opencode|kimi|custom`
|
||||
|
||||
## Key Implementation Details
|
||||
|
||||
|
||||
40
README.md
40
README.md
@@ -6,7 +6,7 @@
|
||||
|
||||
English | [简体中文](README.zh-CN.md) | [日本語](README.ja.md) | [한국어](README.ko.md) | [Español](README.es.md) | [Français](README.fr.md) | [Deutsch](README.de.md) | [Português](README.pt-BR.md) | [Türkçe](README.tr.md) | [العربية](README.ar.md) | [हिन्दी](README.hi.md) | [Русский](README.ru.md)
|
||||
|
||||
[](https://github.com/yusufkaraaslan/Skill_Seekers/releases)
|
||||
[](https://github.com/yusufkaraaslan/Skill_Seekers/releases)
|
||||
[](https://opensource.org/licenses/MIT)
|
||||
[](https://www.python.org/downloads/)
|
||||
[](https://modelcontextprotocol.io)
|
||||
@@ -100,6 +100,13 @@ skill-seekers package output/django --target claude
|
||||
|
||||
**That's it!** You now have `output/django-claude.zip` ready to use.
|
||||
|
||||
```bash
|
||||
# Use a different AI agent for enhancement (default: claude)
|
||||
skill-seekers create https://docs.django.com/ --agent kimi
|
||||
skill-seekers create https://docs.django.com/ --agent codex
|
||||
skill-seekers create https://docs.django.com/ --agent-cmd "my-custom-agent run"
|
||||
```
|
||||
|
||||
### Other Sources (17 Supported)
|
||||
|
||||
```bash
|
||||
@@ -224,6 +231,7 @@ Instead of spending days on manual preprocessing, Skill Seekers:
|
||||
## Key Features
|
||||
|
||||
### 🌐 Documentation Scraping
|
||||
- ✅ **Smart SPA Discovery** - Three-layer discovery for JavaScript SPA sites (sitemap.xml → llms.txt → headless browser rendering)
|
||||
- ✅ **llms.txt Support** - Automatically detects and uses LLM-ready documentation files (10x faster)
|
||||
- ✅ **Universal Scraper** - Works with ANY documentation website
|
||||
- ✅ **Smart Categorization** - Automatically organizes content by topic
|
||||
@@ -519,7 +527,7 @@ skill-seekers resume github_react_20260117_143022
|
||||
|
||||
### 🎯 Bootstrap Skill - Self-Hosting
|
||||
|
||||
Generate skill-seekers as a Claude Code skill to use within Claude:
|
||||
Generate skill-seekers as a skill to use within your AI agent (Claude Code, Kimi, Codex, etc.):
|
||||
|
||||
```bash
|
||||
# Generate the skill
|
||||
@@ -636,6 +644,15 @@ stages:
|
||||
- ✅ **Checkpoint/Resume** - Never lose progress on long scrapes
|
||||
- ✅ **Caching System** - Scrape once, rebuild instantly
|
||||
|
||||
### 🤖 Agent-Agnostic Skill Generation
|
||||
- ✅ **Multi-Agent Support** - Generate skills for Claude, Kimi, Codex, Copilot, OpenCode, or any custom agent via `--agent` flag
|
||||
- ✅ **Custom Agent Commands** - Use `--agent-cmd` to specify a custom agent CLI command for enhancement
|
||||
- ✅ **Universal Flags** - `--agent` and `--agent-cmd` available on all commands (create, scrape, github, pdf, etc.)
|
||||
|
||||
### 📦 Marketplace Pipeline
|
||||
- ✅ **Publish to Marketplace** - Publish skills to Claude Code plugin marketplace repos
|
||||
- ✅ **End-to-End Pipeline** - From documentation source to published marketplace entry
|
||||
|
||||
### ✅ Quality Assurance
|
||||
- ✅ **Fully Tested** - 2,540+ tests with comprehensive coverage
|
||||
|
||||
@@ -719,7 +736,7 @@ skill-seekers install --config react --dry-run
|
||||
|
||||
**Requirements:**
|
||||
- ANTHROPIC_API_KEY environment variable (for auto-upload)
|
||||
- Claude Code Max plan (for local AI enhancement)
|
||||
- Claude Code Max plan (for local AI enhancement), or use `--agent` to select a different AI agent
|
||||
|
||||
---
|
||||
|
||||
@@ -756,6 +773,9 @@ skill-seekers scrape --url https://react.dev --name react
|
||||
|
||||
# With async mode (3x faster)
|
||||
skill-seekers scrape --config configs/godot.json --async --workers 8
|
||||
|
||||
# Use a specific AI agent for enhancement
|
||||
skill-seekers scrape --config configs/react.json --agent kimi
|
||||
```
|
||||
|
||||
### PDF Extraction
|
||||
@@ -902,15 +922,15 @@ graph LR
|
||||
C --> F[Organized References]
|
||||
D --> F
|
||||
F --> E
|
||||
E --> G[Claude Skill .zip]
|
||||
G --> H[Upload to Claude AI]
|
||||
E --> G[AI Skill .zip]
|
||||
G --> H[Upload to AI Platform]
|
||||
```
|
||||
|
||||
0. **Detect llms.txt** - Checks for llms-full.txt, llms.txt, llms-small.txt first
|
||||
0. **Detect llms.txt** - Checks for llms-full.txt, llms.txt, llms-small.txt first (part of Smart SPA Discovery)
|
||||
1. **Scrape**: Extracts all pages from documentation
|
||||
2. **Categorize**: Organizes content into topics (API, guides, tutorials, etc.)
|
||||
3. **Enhance**: AI analyzes docs and creates comprehensive SKILL.md with examples
|
||||
4. **Package**: Bundles everything into a Claude-ready `.zip` file
|
||||
3. **Enhance**: AI analyzes docs and creates comprehensive SKILL.md with examples (supports multiple agents via `--agent`)
|
||||
4. **Package**: Bundles everything into a platform-ready `.zip` file
|
||||
|
||||
## Architecture
|
||||
|
||||
@@ -924,9 +944,9 @@ The system is organized into **8 core modules** and **5 utility modules** (~200
|
||||
| **Scrapers** | 17 source-type extractors | `DocToSkillConverter`, `GitHubScraper`, `UnifiedScraper` |
|
||||
| **Adaptors** | 20+ output platform formats | `SkillAdaptor` (ABC), `ClaudeAdaptor`, `LangChainAdaptor` |
|
||||
| **Analysis** | C3.x codebase analysis pipeline | `UnifiedCodebaseAnalyzer`, `PatternRecognizer`, 10 GoF detectors |
|
||||
| **Enhancement** | AI-powered skill improvement | `AIEnhancer`, `UnifiedEnhancer`, `WorkflowEngine` |
|
||||
| **Enhancement** | AI-powered skill improvement via `AgentClient` | `AgentClient`, `AIEnhancer`, `UnifiedEnhancer`, `WorkflowEngine` |
|
||||
| **Packaging** | Package, upload, install skills | `PackageSkill`, `InstallAgent` |
|
||||
| **MCP** | FastMCP server (34 tools) | `SkillSeekerMCPServer`, 8 tool modules |
|
||||
| **MCP** | FastMCP server (40 tools) | `SkillSeekerMCPServer`, 10 tool modules |
|
||||
| **Sync** | Doc change detection | `ChangeDetector`, `SyncMonitor`, `Notifier` |
|
||||
|
||||
Utility modules: **Parsers** (28 CLI parsers), **Storage** (S3/GCS/Azure), **Embedding** (multi-provider vectors), **Benchmark** (performance), **Utilities** (16 shared helpers).
|
||||
|
||||
@@ -11,7 +11,7 @@ Transform Skill Seekers into the easiest way to create Claude AI skills from **a
|
||||
**What Works:**
|
||||
- ✅ **17 source types** — documentation, GitHub, PDF, video, Word, EPUB, Jupyter, local HTML, OpenAPI, AsciiDoc, PowerPoint, RSS/Atom, man pages, Confluence, Notion, Slack/Discord, local codebase
|
||||
- ✅ Unified multi-source scraping with generic merge for any source combination
|
||||
- ✅ 26+ MCP tools fully functional
|
||||
- ✅ 40 MCP tools fully functional
|
||||
- ✅ Multi-platform support (16 platforms: Claude, Gemini, OpenAI, LangChain, LlamaIndex, Haystack, ChromaDB, FAISS, Weaviate, Qdrant, Cursor, Windsurf, Cline, Continue.dev, Pinecone, Markdown)
|
||||
- ✅ Auto-upload to all platforms
|
||||
- ✅ 24 preset configs (including 7 unified configs)
|
||||
@@ -364,7 +364,7 @@ Small standalone tools that add value
|
||||
- ✅ 17 source types supported
|
||||
- ✅ 24 preset configs (14 official + 10 test/examples)
|
||||
- ✅ 1,880+ tests (excellent coverage)
|
||||
- ✅ 26+ MCP tools
|
||||
- ✅ 40 MCP tools
|
||||
- ✅ 4 platform adaptors (Claude, Gemini, OpenAI, Markdown)
|
||||
- ✅ C3.x codebase analysis suite complete
|
||||
- ✅ Multi-source synthesis with generic merge for any combination
|
||||
|
||||
@@ -103,7 +103,7 @@ docs/
|
||||
|
||||
**Files:**
|
||||
- `CLI_REFERENCE.md` - All CLI commands (including 17 source-type subcommands)
|
||||
- `MCP_REFERENCE.md` - 26+ MCP tools
|
||||
- `MCP_REFERENCE.md` - 40 MCP tools
|
||||
- `CONFIG_FORMAT.md` - JSON schema (covers all 17 source types)
|
||||
- `ENVIRONMENT_VARIABLES.md` - All env vars (including Confluence, Notion, Slack tokens)
|
||||
|
||||
|
||||
@@ -460,9 +460,9 @@ skill-seekers upload output/react-claude.zip --target claude
|
||||
|
||||
AI enhancement transforms basic skills (2-3/10 quality) into production-ready skills (8-9/10 quality) using LLMs.
|
||||
|
||||
**Two Modes:**
|
||||
1. **API Mode:** Direct Claude API calls (fast, costs ~$0.15-0.30)
|
||||
2. **LOCAL Mode:** Uses Claude Code CLI (free with your Max plan)
|
||||
**Two Modes (via AgentClient):**
|
||||
1. **API Mode:** Multi-provider AI API calls -- Anthropic, Moonshot/Kimi, Gemini, OpenAI (fast, costs ~$0.15-0.30)
|
||||
2. **LOCAL Mode:** Any supported coding agent -- Claude Code, Kimi, Codex, Copilot, OpenCode, or custom (free with agent subscription)
|
||||
|
||||
**What it improves:**
|
||||
- Better organization and structure
|
||||
|
||||
@@ -15,9 +15,9 @@ Skill Seekers converts documentation from 17 source types into production-ready
|
||||
- **Scrapers** -- 17 source-type extractors (web, GitHub, PDF, Word, EPUB, video, etc.)
|
||||
- **Adaptors** -- Strategy+Factory pattern for 20+ output platforms (Claude, Gemini, OpenAI, RAG frameworks)
|
||||
- **Analysis** -- C3.x codebase analysis pipeline (AST parsing, 10 GoF pattern detectors, guide builders)
|
||||
- **Enhancement** -- AI-powered skill improvement (API mode + LOCAL mode, --enhance-level 0-3)
|
||||
- **Enhancement** -- AI-powered skill improvement via `AgentClient` (API mode: Anthropic/Kimi/Gemini/OpenAI + LOCAL mode: Claude Code/Kimi/Codex/Copilot/OpenCode/custom, --enhance-level 0-3)
|
||||
- **Packaging** -- Package, upload, and install skills to AI agent directories
|
||||
- **MCP** -- FastMCP server exposing 34 tools via stdio/HTTP transport
|
||||
- **MCP** -- FastMCP server exposing 40 tools via stdio/HTTP transport (includes marketplace and config publishing)
|
||||
- **Sync** -- Documentation change detection and re-scraping triggers
|
||||
|
||||
**Utility Modules** (lower area):
|
||||
@@ -52,7 +52,7 @@ Entry point: `skill-seekers` CLI. `CLIDispatcher` maps subcommands to modules vi
|
||||
### Enhancement
|
||||
|
||||
|
||||
Two enhancement hierarchies: `AIEnhancer` (API mode, Claude API calls) and `UnifiedEnhancer` (C3.x pipeline enhancers). Each has specialized subclasses for patterns, test examples, guides, and configs. `WorkflowEngine` orchestrates multi-stage `EnhancementWorkflow`.
|
||||
Two enhancement hierarchies: `AIEnhancer` (API mode, multi-provider via `AgentClient`) and `UnifiedEnhancer` (C3.x pipeline enhancers). Each has specialized subclasses for patterns, test examples, guides, and configs. `WorkflowEngine` orchestrates multi-stage `EnhancementWorkflow`. The `AgentClient` (`cli/agent_client.py`) centralizes all AI invocations, supporting API mode (Anthropic, Moonshot/Kimi, Gemini, OpenAI) and LOCAL mode (Claude Code, Kimi Code, Codex, Copilot, OpenCode, custom agents).
|
||||
|
||||
### Packaging
|
||||
|
||||
@@ -62,7 +62,7 @@ Two enhancement hierarchies: `AIEnhancer` (API mode, Claude API calls) and `Unif
|
||||
### MCP Server
|
||||
|
||||
|
||||
`SkillSeekerMCPServer` (FastMCP) with 34 tools in 8 categories. Supporting classes: `SourceManager` (config CRUD), `AgentDetector` (environment detection), `GitConfigRepo` (community configs).
|
||||
`SkillSeekerMCPServer` (FastMCP) with 40 tools in 10 categories. Supporting classes: `SourceManager` (config CRUD), `AgentDetector` (environment detection), `GitConfigRepo` (community configs), `MarketplacePublisher` (publish skills to marketplace repos), `MarketplaceManager` (marketplace registry CRUD), `ConfigPublisher` (push configs to registered source repos).
|
||||
|
||||
### Sync
|
||||
|
||||
@@ -132,7 +132,7 @@ MCP Client (Claude Code/Cursor) → FastMCPServer (stdio/HTTP) with two invocati
|
||||
### Enhancement Pipeline
|
||||
|
||||
|
||||
`--enhance-level` decision flow with precise internal variable mapping: Level 0 sets `ai_mode=none`, skips all AI. Level ≥ 1 selects `ai_mode=api` (if `ANTHROPIC_API_KEY` set) or `ai_mode=local` (Claude Code CLI), then SKILL.md enhancement happens post-build via `enhance_command`. Level ≥ 2 enables `enhance_config=True`, `enhance_architecture=True` inside `analyze_codebase()`. Level 3 adds `enhance_patterns=True`, `enhance_tests=True`.
|
||||
`--enhance-level` decision flow with precise internal variable mapping: Level 0 sets `ai_mode=none`, skips all AI. Level >= 1 selects `ai_mode=api` (if any supported API key set: Anthropic, Moonshot/Kimi, Gemini, OpenAI) or `ai_mode=local` (via `AgentClient` with configurable agent: Claude Code, Kimi, Codex, Copilot, OpenCode, or custom), then SKILL.md enhancement happens post-build via `enhance_command`. Level >= 2 enables `enhance_config=True`, `enhance_architecture=True` inside `analyze_codebase()`. Level 3 adds `enhance_patterns=True`, `enhance_tests=True`.
|
||||
|
||||
### Runtime Components
|
||||
|
||||
|
||||
@@ -20,6 +20,7 @@ All enhancement modes now support **multiple local coding agents**:
|
||||
| Agent | Display Name | Default | Notes |
|
||||
|-------|--------------|---------|-------|
|
||||
| **claude** | Claude Code | ✅ Yes | Your Claude Code Max plan (no API costs) |
|
||||
| **kimi** | Kimi Code CLI | No | Uses `kimi --print` with stdin |
|
||||
| **codex** | OpenAI Codex CLI | No | Uses `codex exec --full-auto` |
|
||||
| **copilot** | GitHub Copilot CLI | No | Uses `gh copilot chat` |
|
||||
| **opencode** | OpenCode CLI | No | Uses `opencode` command |
|
||||
@@ -101,6 +102,10 @@ Agent names are normalized with smart alias support:
|
||||
# All resolve to "copilot"
|
||||
--agent copilot
|
||||
--agent copilot-cli
|
||||
|
||||
# All resolve to "kimi"
|
||||
--agent kimi
|
||||
--agent kimi-code
|
||||
```
|
||||
|
||||
## Mode Comparison
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
# MCP Reference - Skill Seekers
|
||||
|
||||
> **Version:** 3.2.0
|
||||
> **Last Updated:** 2026-03-15
|
||||
> **Complete reference for 27 MCP tools**
|
||||
> **Version:** 3.4.0
|
||||
> **Last Updated:** 2026-04-01
|
||||
> **Complete reference for 40 MCP tools**
|
||||
|
||||
---
|
||||
|
||||
@@ -14,9 +14,11 @@
|
||||
- [Starting the Server](#starting-the-server)
|
||||
- [Tool Categories](#tool-categories)
|
||||
- [Core Tools (9)](#core-tools)
|
||||
- [Extended Tools (9)](#extended-tools)
|
||||
- [Extended Tools (10)](#extended-tools)
|
||||
- [Config Source Tools (5)](#config-source-tools)
|
||||
- [Config Splitting Tools (2)](#config-splitting-tools)
|
||||
- [Config Publishing Tools (1)](#config-publishing-tools)
|
||||
- [Marketplace Tools (4)](#marketplace-tools)
|
||||
- [Vector Database Tools (4)](#vector-database-tools)
|
||||
- [Workflow Tools (5)](#workflow-tools)
|
||||
- [Tool Reference](#tool-reference)
|
||||
@@ -87,14 +89,14 @@ Advanced scraping and analysis tools:
|
||||
|------|---------|
|
||||
| `scrape_github` | GitHub repository analysis |
|
||||
| `scrape_pdf` | PDF extraction |
|
||||
| `scrape_video` | Video transcript extraction |
|
||||
| `scrape_codebase` | Local codebase analysis |
|
||||
| `scrape_generic` | Generic scraper for 10 new source types |
|
||||
| `unified_scrape` | Multi-source scraping |
|
||||
| `sync_config` | Sync config from remote source |
|
||||
| `detect_patterns` | Pattern detection |
|
||||
| `extract_test_examples` | Extract usage examples from tests |
|
||||
| `build_how_to_guides` | Generate how-to guides |
|
||||
| `extract_config_patterns` | Extract configuration patterns |
|
||||
| `detect_conflicts` | Find doc/code discrepancies |
|
||||
|
||||
### Config Source Tools (5)
|
||||
|
||||
@@ -117,6 +119,25 @@ Handle large documentation:
|
||||
| `split_config` | Split large config |
|
||||
| `generate_router` | Generate router skill |
|
||||
|
||||
### Config Publishing Tools (1)
|
||||
|
||||
Push configs to registered source repositories:
|
||||
|
||||
| Tool | Purpose |
|
||||
|------|---------|
|
||||
| `push_config` | Push validated config to a registered config source repo |
|
||||
|
||||
### Marketplace Tools (4)
|
||||
|
||||
Manage plugin marketplace repositories:
|
||||
|
||||
| Tool | Purpose |
|
||||
|------|---------|
|
||||
| `add_marketplace` | Register a marketplace repository |
|
||||
| `list_marketplaces` | List registered marketplaces |
|
||||
| `remove_marketplace` | Remove a marketplace |
|
||||
| `publish_to_marketplace` | Publish skill to a marketplace repo |
|
||||
|
||||
### Vector Database Tools (4)
|
||||
|
||||
Export to vector databases:
|
||||
|
||||
@@ -39,11 +39,15 @@ Choose how much enhancement to apply:
|
||||
|
||||
### API Mode (Default if key available)
|
||||
|
||||
Uses Claude API for fast enhancement.
|
||||
Uses any supported AI provider API via `AgentClient`. Providers: Anthropic (Claude), Moonshot/Kimi, Google Gemini, OpenAI.
|
||||
|
||||
**Requirements:**
|
||||
```bash
|
||||
export ANTHROPIC_API_KEY=sk-ant-...
|
||||
# Any one of these activates API mode:
|
||||
export ANTHROPIC_API_KEY=sk-ant-... # Claude
|
||||
export MOONSHOT_API_KEY=... # Kimi
|
||||
export GOOGLE_API_KEY=... # Gemini
|
||||
export OPENAI_API_KEY=... # OpenAI
|
||||
```
|
||||
|
||||
**Usage:**
|
||||
@@ -67,27 +71,33 @@ skill-seekers enhance output/my-skill/ --agent api
|
||||
|
||||
### LOCAL Mode (Default if no key)
|
||||
|
||||
Uses Claude Code (free with Max plan).
|
||||
Uses a local AI coding agent via `AgentClient`. Supports Claude Code, Kimi Code, Codex, Copilot, OpenCode, or custom agents.
|
||||
|
||||
**Requirements:**
|
||||
- Claude Code installed
|
||||
- Claude Code Max subscription
|
||||
- One of the supported agents installed (Claude Code, Codex, Copilot, OpenCode, Kimi)
|
||||
|
||||
**Usage:**
|
||||
```bash
|
||||
# Auto-detects LOCAL mode (no API key)
|
||||
# Auto-detects LOCAL mode (no API key), defaults to Claude Code
|
||||
skill-seekers create <source>
|
||||
|
||||
# Explicit
|
||||
skill-seekers enhance output/my-skill/ --agent local
|
||||
# Use a different local agent
|
||||
skill-seekers enhance output/my-skill/ --agent codex
|
||||
skill-seekers enhance output/my-skill/ --agent copilot
|
||||
skill-seekers enhance output/my-skill/ --agent kimi
|
||||
skill-seekers enhance output/my-skill/ --agent opencode
|
||||
|
||||
# Custom agent
|
||||
skill-seekers enhance output/my-skill/ --agent custom --agent-cmd "my-agent {prompt_file}"
|
||||
```
|
||||
|
||||
**Pros:**
|
||||
- Free (with Claude Code Max)
|
||||
- Free (with agent subscription)
|
||||
- Better quality (full context)
|
||||
- Agent-agnostic -- works with any supported coding agent
|
||||
|
||||
**Cons:**
|
||||
- Requires Claude Code
|
||||
- Requires a local coding agent
|
||||
- Slightly slower (~60-120 sec)
|
||||
|
||||
---
|
||||
|
||||
@@ -82,7 +82,7 @@ You should see a list of preset configurations (Godot, React, Vue, etc.).
|
||||
|
||||
## Available Tools
|
||||
|
||||
The MCP server exposes 18 tools:
|
||||
The MCP server exposes 40 tools (see `docs/reference/MCP_REFERENCE.md` for the full list). Key tools include:
|
||||
|
||||
### 1. `generate_config`
|
||||
Create a new configuration file for any documentation website.
|
||||
@@ -419,9 +419,27 @@ Agent: ✅ 6 skills packaged:
|
||||
|
||||
```
|
||||
mcp/
|
||||
├── server.py # Main MCP server
|
||||
├── requirements.txt # MCP dependencies
|
||||
└── README.md # This file
|
||||
├── server_fastmcp.py # Main MCP server (FastMCP, 40 tools)
|
||||
├── server.py # Server entry point
|
||||
├── server_legacy.py # Legacy server
|
||||
├── source_manager.py # Config source CRUD
|
||||
├── agent_detector.py # Environment/agent detection
|
||||
├── git_repo.py # Community config git repos
|
||||
├── marketplace_publisher.py # Publish skills to marketplace repos
|
||||
├── marketplace_manager.py # Marketplace registry management
|
||||
├── config_publisher.py # Push configs to source repos
|
||||
├── tools/ # Tool implementations by category
|
||||
│ ├── config_tools.py
|
||||
│ ├── marketplace_tools.py
|
||||
│ ├── packaging_tools.py
|
||||
│ ├── scraping_tools.py
|
||||
│ ├── source_tools.py
|
||||
│ ├── splitting_tools.py
|
||||
│ ├── sync_config_tools.py
|
||||
│ ├── vector_db_tools.py
|
||||
│ └── workflow_tools.py
|
||||
├── requirements.txt # MCP dependencies
|
||||
└── README.md # This file
|
||||
```
|
||||
|
||||
### How It Works
|
||||
@@ -500,13 +518,13 @@ python3 -m pytest tests/test_mcp_server.py -v
|
||||
|
||||
2. Verify server can start:
|
||||
```bash
|
||||
python3 mcp/server.py
|
||||
python3 -m skill_seekers.mcp.server_fastmcp
|
||||
# Should start without errors (Ctrl+C to exit)
|
||||
```
|
||||
|
||||
3. Check dependencies:
|
||||
```bash
|
||||
pip3 install -r mcp/requirements.txt
|
||||
pip3 install -e ".[mcp]"
|
||||
```
|
||||
|
||||
4. Completely restart your AI coding agent (quit and reopen)
|
||||
|
||||
Reference in New Issue
Block a user