* feat: add MiniMax AI as LLM platform adaptor
Original implementation by octo-patch in PR #318.
This commit includes comprehensive improvements and documentation.
Code Improvements:
- Fix API key validation to properly check JWT format (eyJ prefix)
- Add specific exception handling for timeout and connection errors
- Remove unused variable in upload method
Dependencies:
- Add MiniMax to [all-llms] extra group in pyproject.toml
Tests:
- Remove duplicate setUp method in integration test class
- Add 4 new test methods:
* test_package_excludes_backup_files
* test_upload_success_mocked (with OpenAI mocking)
* test_upload_network_error
* test_upload_connection_error
* test_validate_api_key_jwt_format
- Update test_validate_api_key_valid to use JWT format keys
- Fix test assertions for error message matching
Documentation:
- Create comprehensive MINIMAX_INTEGRATION.md guide (380+ lines)
- Update MULTI_LLM_SUPPORT.md with MiniMax platform entry
- Update 01-installation.md extras table
- Update INTEGRATIONS.md AI platforms table
- Update AGENTS.md adaptor import pattern example
- Fix README.md platform count from 4 to 5
All tests pass (33 passed, 3 skipped)
Lint checks pass
Co-authored-by: octo-patch <octo-patch@users.noreply.github.com>
* fix: improve MiniMax adaptor — typed exceptions, key validation, tests, docs
- Remove invalid "minimax" self-reference from all-llms dependency group
- Use typed OpenAI exceptions (APITimeoutError, APIConnectionError)
instead of string-matching on generic Exception
- Replace incorrect JWT assumption in validate_api_key with length check
- Use DEFAULT_API_ENDPOINT constant instead of hardcoded URLs (3 sites)
- Add Path() cast for output_path before .is_dir() call
- Add sys.modules mock to test_enhance_missing_library
- Add mocked test_enhance_success with backup/content verification
- Update test assertions for new exception types and key validation
- Add MiniMax to __init__.py docstrings (module, get_adaptor, list_platforms)
- Add MiniMax sections to MULTI_LLM_SUPPORT.md (install, format, API key,
workflow example, export-to-all)
Follows up on PR #318 by @octo-patch (feat: add MiniMax AI as LLM platform adaptor).
Co-Authored-By: Octopus <octo-patch@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: octo-patch <octo-patch@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Skip OCR on WEBCAM/OTHER frames (eliminates ~64 junk results per video)
- Add _clean_ocr_line() to strip line numbers, IDE decorations, collapse markers
- Add _fix_intra_line_duplication() for multi-engine OCR overlap artifacts
- Add _is_likely_code() filter to prevent UI junk in reference code fences
- Add language detection to get_text_groups() via LanguageDetector
- Apply OCR cleaning in _assemble_structured_text() pipeline
- Add two-pass AI enhancement: Pass 1 cleans reference Code Timeline
using transcript context, Pass 2 generates SKILL.md from cleaned refs
- Update video-tutorial.yaml prompts for pre-cleaned references
- Add 17 new tests (197 total video tests), 2540 tests passing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Auto-detects NVIDIA (CUDA), AMD (ROCm), or CPU-only GPU and installs the
correct PyTorch variant + easyocr + all visual extraction dependencies.
Removes easyocr from video-full pip extras to avoid pulling ~2GB of wrong
CUDA packages on non-NVIDIA systems.
New files:
- video_setup.py (835 lines): GPU detection, PyTorch install, ROCm config,
venv checks, system dep validation, module selection, verification
- test_video_setup.py (60 tests): Full coverage of detection, install, verify
Updated docs: CHANGELOG, AGENTS.md, CLAUDE.md, README.md, CLI_REFERENCE,
FAQ, TROUBLESHOOTING, installation guide, video dependency plan
All 2523 tests passing (15 skipped).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add FALLBACK_MAIN_SELECTORS constant and _find_main_content() helper to
eliminate 3 duplicated fallback loops in doc_scraper.py
- Move link extraction before early return in extract_content() so links
are always discovered from the full page, not just main content
- Fix single-threaded dry-run to extract links from soup (full page)
instead of main element only — fixes reactflow.dev finding only 1 page
- Add link extraction to async dry-run path (was completely missing)
- Remove main_content from get_configuration() defaults so fallback logic
kicks in instead of a broad CSS comma selector matching body
- Smart create --config routing: peek at JSON to determine unified
(sources array → unified_scraper) vs simple (base_url → doc_scraper)
- Update docs/user-guide/02-scraping.md and docs/reference/CONFIG_FORMAT.md
to use unified config format (legacy format rejected since v2.11.0)
- Fix test_auto_fetch_enabled and test_mcp_validate_legacy_config
Closes#300
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
All scrapers (scrape, github, analyze, pdf) now share a common argument
contract via add_all_standard_arguments() in arguments/common.py.
Universal flags (--dry-run, --verbose, --quiet, --name, --description,
workflow args) work consistently across all source types.
Previously, `create <url> --dry-run`, `create owner/repo --dry-run`,
and `create ./path --dry-run` would crash because sub-scrapers didn't
accept those flags. Also fixes main.py _handle_analyze_command() not
forwarding --dry-run, --preset, --quiet, --name, --description to
codebase_scraper.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add CI Troubleshooting section with step-by-step debugging checklist
- Update Local Pre-Commit Validation with auto-fix commands (uvx ruff --fix)
- Add pitfall #9: CI Passes Locally But Fails in GitHub Actions
- Document critical dependency patterns (MCP version, PyYAML, try/except ImportError)
- Update test count references: 1,880+/1,952+ → 2,121 (current reality)
- Add v3.1.0 CI Stability section to Recent Achievements
- Include timing-sensitive test guidance for CI environments
These improvements are based on real troubleshooting experience from recent
CI failures (MCP version mismatch, PyYAML dependency, benchmark thresholds).
- Add YAML-based enhancement workflow presets shipped inside the package
(default, minimal, security-focus, architecture-comprehensive, api-documentation)
- Add `skill-seekers workflows` subcommand: list, show, copy, add, remove, validate
- copy/add/remove all accept multiple names/files in one invocation with partial-failure behaviour
- `add --name` override restricted to single-file operations
- Add 5 MCP tools: list_workflows, get_workflow, create_workflow, update_workflow, delete_workflow
- Fix: create command _add_common_args() now correctly forwards each --enhance-workflow
as a separate flag instead of passing the whole list as a single argument
- Update README: reposition as "data layer for AI systems" with AI Skills front and centre
- Update CHANGELOG, QUICK_REFERENCE, CLAUDE.md with workflow preset details
- 1,880+ tests passing
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Major improvements to developer documentation:
CLAUDE.md:
- Add unified `create` command to quick command reference
- New comprehensive section on unified create command architecture
- Auto-detection of source types (web/GitHub/local/PDF/config)
- Progressive disclosure help system (--help-web, --help-github, etc.)
- Universal flags that work across all sources
- -p shortcut for preset selection
- Document enhancement flag consolidation (Phase 1)
- Old: --enhance, --enhance-local, --api-key (3 flags)
- New: --enhance-level 0-3 (1 granular flag)
- Auto-detection of API vs LOCAL mode
- Add "Modifying the Unified Create Command" section
- Three-tier argument system (universal/source-specific/advanced)
- File locations and architecture
- Examples for contributors
- New troubleshooting: "Confused About Command Options"
- Update test counts: 1,765 current (1,852+ in v3.1.0)
- Add v3.1.0 to recent achievements
- Update best practices to prioritize create command
AGENTS.md:
- Update version to 3.0.0
- Add new directories: arguments/, presets/, create_command.py
These changes ensure future Claude instances understand the CLI
refactor work and can effectively contribute to the project.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add comprehensive developer-focused sections to improve onboarding and
productivity:
- ⚡ Quick Command Reference: Most-used commands for instant access
- 🧪 Test Execution Strategy: Detailed guide on when to use test markers
- 🔄 Expanded CI/CD Pipeline: Complete breakdown of GitHub Actions workflow
- 🚨 Common Pitfalls & Solutions: 7 common issues with fixes
- 🎯 Where to Make Changes: File-by-file guide for common tasks
- 🐛 Debugging Tips: Comprehensive debugging guide with pytest options
Changes:
- Added 478 lines of practical developer guidance
- Enhanced 3 existing sections with more detail
- Maintained all original comprehensive architecture documentation
- File grew from 1,021 to 1,487 lines
Impact: Significantly improves developer experience by providing quick
access to essential commands, clear debugging workflows, and explicit
guidance on where to make changes for common tasks.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Update version from v2.8.0 to v2.9.0
- Add signal_flow_analyzer.py to file structure and key locations
- Add comprehensive C3.10 Signal Flow Analysis documentation
- Remove duplicate C3.9 entry
- Update Recent Achievements with v2.9.0 release and C3.10 features
- Add Godot 4.x support details (GDScript, .tscn, .tres, .gdshader)
- Update C3.x series list to include C3.9 and C3.10
Major feature release with enhanced code analysis and documentation.
Features:
- C3.9: Project documentation extraction
- Granular AI enhancement control (--enhance-level 0-3)
- C# language support for test extraction
- 6-12x faster parallel LOCAL mode AI enhancement
- Auto-enhancement and LOCAL mode fallbacks
- GLM-4.7 and custom Claude-compatible API support
Bug Fixes:
- Fixed C# test extraction language errors
- Fixed config type field mismatch
- Fixed LocalSkillEnhancer import issues
- Fixed critical linter errors
Contributors:
- @xuintl - Chinese README improvements
- @Zhichang Yu - GLM-4.7 support and PDF fixes
- @YusufKaraaslanSpyke - Core features and maintenance
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Complete implementation of C3.9, granular AI enhancement control, performance optimizations, and bug fixes.
Features:
- C3.9 Project Documentation Extraction (markdown files)
- Granular AI enhancement control (--enhance-level 0-3)
- C# test extraction support
- 6-12x faster LOCAL mode with parallel execution
- Auto-enhancement UX improvements
- LOCAL mode fallback for all AI enhancements
Bug Fixes:
- C# language support
- Config type field compatibility
- LocalSkillEnhancer import
Documentation:
- Updated CHANGELOG.md
- Updated CLAUDE.md
- Removed client-specific files
Tests: All 1,257 tests passing
Critical linter errors: Fixed
- Scan ALL .md files in project (README, docs/, etc.)
- Smart categorization by folder/filename (overview, architecture, guides, etc.)
- Processing depth: surface=raw copy, deep=parse+summarize, full=AI-enhanced
- AI enhancement at level 2+ adds topic extraction and cross-references
- New "Project Documentation" section in SKILL.md with summaries
- Output to references/documentation/ organized by category
- Default ON, use --skip-docs to disable
- Add skip_docs parameter to MCP scrape_codebase_tool
- Add 15 new tests for markdown documentation features
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements Phase 1 of the codebase analysis UX improvement plan, making the
command discoverable and adding intuitive preset flags while maintaining 100%
backward compatibility.
New Features:
- Add 'analyze' subcommand to main CLI (skill-seekers analyze)
- Add --quick preset: Fast analysis (1-2 min, basic features only)
- Add --comprehensive preset: Full analysis (20-60 min, all features + AI)
- Add --enhance flag: Simple AI enhancement with auto-detection
- Improve help text with timing estimates and mode descriptions
Files Modified:
- src/skill_seekers/cli/main.py: Add analyze subcommand (lines 15, 273-311, 542-589)
- src/skill_seekers/cli/codebase_scraper.py: Add preset logic and improve help text
- tests/test_analyze_command.py: NEW - 20 comprehensive tests
- tests/test_cli_paths.py: Fix version check (2.7.0 -> 2.7.2)
- tests/test_package_structure.py: Fix 4 version checks (2.7.0 -> 2.7.2)
- README.md: Update examples to use 'analyze' command
- CLAUDE.md: Update examples to use 'analyze' command
Test Results:
- 81 tests related to Phase 1: ALL PASSING ✅
- 20 new tests for analyze command: ALL PASSING ✅
- Zero regressions introduced
- 100% backward compatibility maintained
Backward Compatibility:
- Old 'skill-seekers-codebase' command still works
- All existing flags (--depth, --ai-mode, --skip-*) still functional
- No breaking changes
Usage Examples:
skill-seekers analyze --directory . --quick
skill-seekers analyze --directory . --comprehensive
skill-seekers analyze --directory . --enhance
Fixes#262 (codebase UX issues)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Merging with admin override due to known issues:
✅ **What Works**:
- GLM-4.7 Claude-compatible API support (correctly implemented)
- PDF scraper improvements (content truncation fixed, page traceability added)
- Documentation updates comprehensive
⚠️ **Known Issues (will be fixed in next commit)**:
1. Import bugs in 3 files causing UnboundLocalError (30 tests failing)
2. PDF scraper test expectations need updating for new behavior (5 tests failing)
3. test_godot_config failure (pre-existing, not caused by this PR - 1 test failing)
**Action Plan**:
Fixes for issues #1 and #2 are ready and will be committed immediately after merge.
Issue #3 requires separate investigation as it's a pre-existing problem.
Total: 36 failing tests, 35 will be fixed in next commit.
This patch release fixes the broken Chinese language selector link
on PyPI by using absolute GitHub URLs instead of relative paths.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This PR improves MCP server configuration by updating all documentation
to use the current server_fastmcp module and ensuring setup scripts
automatically use virtual environment Python instead of system Python.
## Changes
### 1. Documentation Updates (server → server_fastmcp)
Updated all references from deprecated `server` module to `server_fastmcp`:
**User-facing documentation:**
- examples/http_transport_examples.sh: All 13 command examples
- README.md: Configuration examples and troubleshooting commands
- docs/guides/MCP_SETUP.md: Enhanced migration guide with stdio/HTTP examples
- docs/guides/TESTING_GUIDE.md: Test import statements
- docs/guides/MULTI_AGENT_SETUP.md: Updated examples
- docs/guides/SETUP_QUICK_REFERENCE.md: Updated paths
- CLAUDE.md: CLI command examples
**MCP module:**
- src/skill_seekers/mcp/README.md: Updated config examples
- src/skill_seekers/mcp/agent_detector.py: Use server_fastmcp module
Note: Historical release notes (CHANGELOG.md) preserved unchanged.
### 2. Venv Python Configuration
**setup_mcp.sh improvements:**
- Added automatic venv detection (checks .venv, venv, and $VIRTUAL_ENV)
- Sets PYTHON_CMD to venv Python path when available
- **CRITICAL FIX**: Now updates PYTHON_CMD after creating/activating venv
- Generates MCP configs with full venv Python path
- Falls back to system python3 if no venv found
- Displays detected Python version and path
**Config examples updated:**
- .claude/mcp_config.example.json: Use venv Python path
- example-mcp-config.json: Use venv Python path
- Added "type": "stdio" for clarity
- Updated to use server_fastmcp module
### 3. Bug Fix: PYTHON_CMD Not Updated After Venv Creation
Previously, when setup_mcp.sh created or activated a venv, it failed to
update PYTHON_CMD, causing generated configs to still use system python3.
**Fixed cases:**
- When $VIRTUAL_ENV is already set → Update PYTHON_CMD to venv Python
- When existing venv is activated → Set PYTHON_CMD="$REPO_PATH/venv/bin/python3"
- When new venv is created → Set PYTHON_CMD="$REPO_PATH/venv/bin/python3"
## Benefits
### For Users:
✅ No deprecation warnings - All docs show current module
✅ Proper Python environment - MCP uses venv with all dependencies
✅ No system Python issues - Avoids "module not found" errors
✅ No global installation needed - No --break-system-packages required
✅ Automatic detection - setup_mcp.sh finds venv automatically
✅ Clean isolation - Projects don't interfere with system Python
### For Maintainers:
✅ Prepared for v3.0.0 - Documentation ready for server.py removal
✅ Reduced support burden - Fewer MCP configuration issues
✅ Consistent examples - All docs use same module/pattern
## Testing
**Verified:**
- ✅ All command examples use server_fastmcp
- ✅ No deprecated module references in user-facing docs (0 results)
- ✅ New module correctly referenced (129 instances)
- ✅ setup_mcp.sh detects venv and generates correct config
- ✅ PYTHON_CMD properly updated after venv creation
- ✅ MCP server starts correctly with venv Python
**Files changed:** 12 files (+262/-107 lines)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Reduced from 1116 to 526 lines (53% reduction)
- Focused on architecture and testing requirements
- Removed redundant user-facing documentation
- Added critical development notes and workflows
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add automatic skill installation to 10+ AI coding agents with a single command.
New Features:
- New install-agent command for installing skills to any AI agent
- Support for 10+ agents: Claude Code, Cursor, VS Code, Amp, Goose, OpenCode, Letta, Aide, Windsurf
- Smart path resolution (global ~/.agent vs project-relative .agent/)
- Fuzzy agent name matching with suggestions
- --agent all flag to install to all agents at once
- --force flag to overwrite existing installations
- --dry-run flag to preview installations
- Comprehensive error handling and user feedback
Implementation:
- Created install_agent.py (379 lines) with core installation logic
- Updated main.py with install-agent subcommand
- Updated pyproject.toml with entry point
- Added 32 comprehensive tests (all passing, 603 total)
- No regressions in existing functionality
Documentation:
- Updated README.md with multi-agent installation guide
- Updated CLAUDE.md with install-agent examples
- Updated CHANGELOG.md with v2.3.0 release notes
- Added agent compatibility table
Technical Details:
- 100% own implementation (no external dependencies)
- Pure Python using stdlib (shutil, pathlib, argparse)
- Compatible with Agent Skills open standard (agentskills.io)
- Works offline
Closes#210🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Major improvements:
- Configurable directory exclusions (Issue #203)
- Unlimited local repository analysis
- Skip llms.txt option (PR #198)
- 10+ bug fixes for GitHub scraper
- Test suite expanded to 427 tests
See CHANGELOG.md for full details.
Updates across all major documentation files to reflect v2.1.0 release
status and recent completions.
Changes:
- CLAUDE.md:
* Updated version from v2.0.0 to v2.1.0
* Updated date to November 29, 2025
* Updated test count from 391 to 427
* Moved completed PRs (#195, #198) and Issue #203 to "Completed" section
* Updated "Next Up" priorities
- README.md:
* Updated version badge from 2.0.0 to 2.1.0
* Updated test badge from 379 to 427 passing
- CHANGELOG.md:
* Added Issue #203 (Configurable EXCLUDED_DIRS) to Unreleased section
* Documented 19 comprehensive tests for exclude_dirs feature
* Listed both extend and replace modes
- FUTURE_RELEASES.md:
* Marked v2.1.0 as "Released" (November 29, 2025)
* Moved "Fix 12 unified tests" to completed
* Updated release schedule table
- FLEXIBLE_ROADMAP.md:
* Updated current status from v1.0.0 to v2.1.0
* Added latest release date
* Expanded "What Works" section with new features
* Updated test count to 427
All documentation now accurately reflects:
- v2.1.0 release status ✅
- 427 tests passing (up from 391) ✅ - Issue #203 completion ✅
- PR #195 and #198 merged status ✅
Related: #203
Merges feat/add-skip-llm-to-config by @sogoiii.
This PR adds a valuable configuration option to explicitly skip llms.txt
detection, useful when a site's llms.txt is incomplete, incorrect, or when
specific HTML scraping is needed.
Key features:
- New 'skip_llms_txt' config option (default: false, backward compatible)
- Boolean type validation with warning for invalid values
- Support in both sync and async scraping modes
- 17 comprehensive tests (15 feature tests + 2 config validation tests)
All tests passing after fixing import paths to use proper package names.
Test results: ✅ 17/17 tests passing
Full test suite: ✅ 391 tests passing
Co-authored-by: sogoiii <sogoiii@users.noreply.github.com>
All unified scraping tests are now passing! Updated documentation to reflect current status.
**Changes:**
1. **CLAUDE.md** - Updated test status throughout
- Changed "⚠️ 12 unified tests need fixes" to "✅ All 22 unified tests passing"
- Updated test count from 379 to 391 tests
- Marked unified configs as ✅ (all 5 working and tested)
- Updated "Next Up" section with completed items
- Updated last verification date to Nov 29, 2025
2. **README.md** - Updated test count
- Changed "379 tests" to "391 tests"
3. **docs/CLAUDE.md** - Updated test documentation
- Updated test counts throughout
- Removed outdated warnings about failing tests
**Test Status:**
- ✅ tests/test_unified.py: 18/18 passing
- ✅ tests/test_unified_mcp_integration.py: 4/4 passing
- ✅ Total: 391 tests passing, 32 skipped
**Unified Scraping:**
- All 5 unified configs verified and working
- Conflict detection fully tested
- Rule-based and AI merge modes tested
- Feature is production-ready
Task 2.2 Complete - No code changes needed, tests were already passing!
Major updates for v2.0.0:
- Added PyPI publication status and installation instructions
- Updated to reflect modern Python packaging (src/ layout, pyproject.toml)
- Updated all commands to use 'skill-seekers' CLI instead of python3 cli/*
- Updated file structure section for src/ layout
- Updated key code locations with new paths
- Added FUTURE_RELEASES.md to documentation list
- Updated test count (379 passing, all CI checks green)
- Updated date to November 11, 2025
- Added development workflow section
- Reorganized Additional Documentation into categories
All sections now reflect the post-PyPI publication state of the project.
Major documentation update explaining the new unified scraping system that combines documentation + GitHub + PDF sources in a single skill with automatic conflict detection.
## Changes:
**README.md:**
- Update version badge to v2.0.0
- Add "Unified Multi-Source Scraping" to Key Features section
- Add comprehensive Option 5 section showing:
- Problem statement (documentation drift)
- Solution with code example
- Conflict detection types and severity levels
- Transparent reporting with side-by-side comparison
- List of advantages (identifies gaps, catches changes, single source of truth)
- Available unified configs
- Link to full guide (docs/UNIFIED_SCRAPING.md)
**CLAUDE.md:**
- Update Current Status to v2.0.0
- Add "Major Release: Unified Multi-Source Scraping" in Recent Updates
- Update configs count from 11/11 to 15/15 (added 4 unified configs)
- Add new "Unified Multi-Source Scraping" section under Core Commands
- Include command examples and feature highlights
- Explain what makes unified scraping special
**QUICKSTART.md:**
- Add Option D: Unified Multi-Source to Step 2
- Add unified configs to Available Presets section
- Show react_unified, django_unified, fastapi_unified, godot_unified examples
## Value:
This documentation update explains how unified scraping helps developers:
- Mix documentation + code in one skill
- Automatically detect conflicts (missing_in_docs, missing_in_code, signature_mismatch)
- Get transparent side-by-side comparisons with ⚠️ warnings
- Identify documentation gaps and outdated docs
- Create a single source of truth combining both sources
Related to: Phase 7-11 unified scraper implementation (commit 5d8c7e3)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Added ansible-core.json config to available presets list in:
- README.md: Added to preset table and usage examples
- CLAUDE.md: Added to production configs list with details
Changes:
- Total configs: 11 → 12
- New category: DevOps & Automation
- Reorganized config list for better categorization
Related: PR #147
The MCP package requires Python 3.10 or higher. Updated:
- GitHub Actions workflow to test Python 3.10, 3.11, 3.12
- README.md badge to Python 3.10+
- CLAUDE.md prerequisites
- CONTRIBUTING.md prerequisites
- docs/MCP_SETUP.md prerequisites
This fixes the MCP installation error in CI:
'ERROR: No matching distribution found for mcp>=1.0.0'
MCP package versions 0.9.1+ all require Python 3.10+.
