firefrost-gaming/skill-seekers-reference
3
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
586 Commits 1 Branch 0 Tags
ab13fcee788bc117fe2f8e38fc63d27962b9f52f
Commit Graph

586 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
yusyus
2d64a2be48 docs: Mark C3.10 as NEW feature in CHANGELOG 2026-02-02 23:16:40 +03:00
yusyus
809f00cb2c Merge feature/fix-csharp-and-config-type-bugs: C3.10 Signal Flow + Complete Godot Support 
Features:
- C3.10: Signal Flow Analysis for Godot projects (208 signals, 634 connections)
- Complete Godot game engine support (.gd, .tscn, .tres, .gdshader)
- GDScript dependency extraction with preload/load/extends patterns
- GDScript test extraction (GUT, gdUnit4, WAT frameworks)
- Signal-based how-to guides generation

Fixes:
- GDScript dependency extraction (265+ syntax errors eliminated)
- Framework detection false positive (Unity → Godot)
- Circular dependency detection (self-loops filtered)
- GDScript test discovery (32 test files found)
- Config extractor array handling (JSON/YAML root arrays)
- Progress indicators for small batches

Tests:
- Added comprehensive GDScript test extraction test case
- 396 test cases extracted from 20 GUT test files
 2026-02-02 23:10:51 +03:00
yusyus
174ce0a8fd docs: Update CHANGELOG with C3.10 Signal Flow Analysis and Godot features 2026-02-02 23:10:00 +03:00
yusyus
c09fc3de41 test: Add GDScript test extraction test case 2026-02-02 23:08:25 +03:00
yusyus
c82669004f fix: Add GDScript regex patterns for test example extraction 
PROBLEM:
- Test files discovered but extraction failed
- WARNING: Language GDScript not supported for regex extraction
- PATTERNS dictionary missing GDScript entry

SOLUTION:
Added GDScript patterns to PATTERNS dictionary:

1. test_function pattern:
   - Matches GUT: func test_something()
   - Matches gdUnit4: @test\nfunc test_something()
   - Pattern: r"(?:@test\s+)?func\s+(test_\w+)\s*\("

2. instantiation pattern:
   - var obj = Class.new()
   - var obj = preload("res://path").new()
   - var obj = load("res://path").new()
   - Pattern: r"(?:var|const)\s+(\w+)\s*=\s*(?:(\w+)\.new\(|(?:preload|load)\([\"']([^\"']+)[\"']\)\.new\()"

3. assertion pattern:
   - GUT assertions: assert_eq, assert_true, assert_false, etc.
   - gdUnit4 assertions: assert_that, assert_str, etc.
   - Pattern: r"assert_(?:eq|ne|true|false|null|not_null|gt|lt|between|has|contains|typeof)\(([^)]+)\)"

4. signal pattern (bonus):
   - Signal connections: signal_name.connect()
   - Signal emissions: emit_signal("signal_name")
   - Pattern: r"(?:(\w+)\.connect\(|emit_signal\([\"'](\w+)[\"'])"

IMPACT:
- ✅ GDScript test files now extract examples
- ✅ Supports GUT, gdUnit4, and WAT test frameworks
- ✅ Extracts instantiation, assertion, and signal patterns

FILE: test_example_extractor.py line 680-690

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 22:28:06 +03:00
yusyus
50b28fe561 fix: Framework detection, circular deps, and GDScript test discovery 
FIXES:

1. Framework Detection (Unity → Godot)
   PROBLEM: Detected Unity instead of Godot due to generic "Assets" marker
   - "Assets" appears in comments: "// TODO: Replace with actual music assets"
   - Triggered false positive for Unity framework

   SOLUTION: Made Unity markers more specific
   - Before: "Assets", "ProjectSettings" (too generic)
   - After: "Assembly-CSharp.csproj", "UnityEngine.dll", "Library/" (specific)
   - Godot markers: "project.godot", ".godot", ".tscn", ".tres", ".gd"

   FILE: architectural_pattern_detector.py line 92-94

2. Circular Dependencies (Self-References)
   PROBLEM: Files showing circular dependency to themselves
   - WARNING: Cycle: analysis-config.gd -> analysis-config.gd
   - 3 self-referential cycles detected

   ROOT CAUSE: No self-loop filtering in build_graph()
   - File resolves class_name to itself
   - Edge created from file to same file

   SOLUTION: Skip self-dependencies in build_graph()
   - Added check: `target != file_path`
   - Prevents file from depending on itself

   FILE: dependency_analyzer.py line 728

3. GDScript Test File Detection
   PROBLEM: Found 0 test files (expected 20 GUT tests with 396 tests)
   - TEST_PATTERNS missing GDScript patterns
   - Only had: test_*.py, *_test.go, Test*.java, etc.

   SOLUTION: Added GDScript test patterns
   - Added: "test_*.gd", "*_test.gd" (GUT, gdUnit4, WAT)
   - Added ".gd": "GDScript" to LANGUAGE_MAP

   FILES:
   - test_example_extractor.py line 886-887
   - test_example_extractor.py line 901

IMPACT:
- ✅ Godot projects correctly detected as "Godot" (not Unity)
- ✅ No more false circular dependency warnings
- ✅ GUT/gdUnit4/WAT test files now discovered and analyzed
- ✅ Better test example extraction for Godot projects

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 22:11:38 +03:00
yusyus
fca0951e52 fix: Handle JSON/YAML arrays at root level in config extraction 
PROBLEM:
- Config extractor crashed on JSON files with arrays at root
- Error: "'list' object has no attribute 'items'"
- Example: save.json with [{"name": "item1"}, {"name": "item2"}]
- Only handled dict roots, not list roots

SOLUTION:
- Added type checking in _parse_json() and _parse_yaml()
- Handle three cases:
  1. Dict at root: extract normally (existing behavior)
  2. List at root: iterate and extract from each dict item
  3. Primitive at root: skip with debug log
- List items are prefixed with [index] in nested path

CHANGES:
- config_extractor.py _parse_json(): Added isinstance checks
- config_extractor.py _parse_yaml(): Added list handling

EXAMPLE:
Before: WARNING: Error parsing save.json: 'list' object has no attribute 'items'
After: Extracts settings with paths like "[0].name", "[1].value"

IMPACT:
- No more crashes on valid JSON/YAML arrays
- Better coverage of config file variations
- Handles game save files, API responses, data arrays

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 22:04:56 +03:00
yusyus
eec37f543a fix: Show AI enhancement progress for small batches (<10) 
PROBLEM:
- Progress indicator only showed every 5 batches or at completion
- When enhancing 1-4 patterns, no progress was visible
- User saw "Enhancing 1 patterns..." → "Enhanced 1 patterns" with no progress

SOLUTION:
- Modified progress condition to always show for small jobs (total < 10)
- Original: `if completed % 5 == 0 or completed == total`
- Updated: `if total < 10 or completed % 5 == 0 or completed == total`

IMPACT:
- Now shows "Progress: 1/3 batches completed" for small jobs
- Large jobs (10+) still show every 5th batch to avoid spam
- Applied to both _enhance_patterns_parallel and _enhance_examples_parallel

FILES:
- ai_enhancer.py line 301-302 (patterns)
- ai_enhancer.py line 439-440 (test examples)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 22:02:18 +03:00
yusyus
3e6c448aca fix: Add GDScript-specific dependency extraction to eliminate syntax errors 
PROBLEM:
- 265+ "Syntax error in *.gd" warnings during analysis
- GDScript files were routed to Python AST parser (_extract_python_imports)
- Python AST failed because GDScript syntax differs (extends, signal, @export)

SOLUTION:
- Created dedicated _extract_gdscript_imports() method using regex
- Parses GDScript-specific patterns:
  * const/var = preload("res://path")
  * const/var = load("res://path")
  * extends "res://path/to/base.gd"
  * extends MyBaseClass (with built-in Godot class filtering)
- Converts res:// paths to relative paths
- Routes GDScript files to new extractor instead of Python AST

CHANGES:
- dependency_analyzer.py (line 114-116): Route GDScript to new extractor
- dependency_analyzer.py (line 201-318): Add _extract_gdscript_imports()
- Updated module docstring: 9 → 10 languages + Godot ecosystem
- Updated analyze_file() docstring with GDScript support

IMPACT:
- Eliminates all 265+ syntax error warnings
- Correctly extracts GDScript dependencies (preload/load/extends)
- Completes C3.10 Signal Flow Analysis integration

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 21:56:42 +03:00
yusyus
1831c1bb47 feat: Add Signal-Based How-To Guides (C3.10.1) - Complete C3.10 
Final piece of Signal Flow Analysis - AI-generated tutorial guides:

## Signal-Based How-To Guides (C3.10.1)
Completes the 5th and final proposed feature for C3.10.

### Implementation
Added to SignalFlowAnalyzer class:
- extract_signal_usage_patterns(): Identifies top 10 most-used signals
- generate_how_to_guides(): Creates tutorial-style guides
- _generate_signal_guide(): Builds structured guide for each signal

### Guide Structure (3-Step Pattern)
Each guide includes:
1. **Step 1: Connect to the signal**
   - Code example with actual handler names from codebase
   - File context (which file to add connection in)

2. **Step 2: Emit the signal**
   - Code example with actual parameters from codebase
   - File context (where emission happens)

3. **Step 3: Handle the signal**
   - Function implementation template
   - Proper parameter handling

4. **Common Usage Locations**
   - Connected in: file.gd → handler()
   - Emitted from: file.gd

### Output
Generates signal_how_to_guides.md with:
- Table of Contents (10 signals)
- Tutorial guide for each signal
- Real code examples extracted from codebase
- Actual file locations and handler names

### Test Results (Cosmic Ideler)
Generated guides for 10 most-used signals:
- camera_3d_resource_property_changed (most used)
- changed
- wait_started
- dead_zone_changed
- display_refresh_needed
- pressed
- pcam_priority_override
- dead_zone_reached
- noise_emitted
- viewfinder_update

File: signal_how_to_guides.md (6.1KB)

## C3.10 Status: 5/5 Features Complete ✅

1. ✅ Signal Connection Mapping (634 connections tracked)
2. ✅ Event-Driven Architecture Detection (3 patterns)
3. ✅ Signal Flow Visualization (Mermaid diagrams)
4. ✅ Signal Documentation Extraction (docs in reference)
5. ✅ Signal-Based How-To Guides (10 tutorials) - NEW

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 21:48:55 +03:00
yusyus
281f6f7916 feat: Add Signal Flow Analysis (C3.10) and Test Framework Detection 
Comprehensive Godot signal analysis and test framework support:

## Signal Flow Analysis (C3.10)
Enhanced GDScript analyzer to extract:
- Signal declarations with documentation comments
- Signal connections (.connect() calls)
- Signal emissions (.emit() calls)
- Signal flow chains (source → signal → handler)

Created SignalFlowAnalyzer class:
- Analyzes 208 signals, 634 connections, 298 emissions (Cosmic Ideler)
- Detects event patterns:
  - EventBus Pattern (centralized event system)
  - Observer Pattern (multi-connected signals)
  - Event Chains (cascading signal emissions)
- Generates:
  - signal_flow.json (full analysis data)
  - signal_flow.mmd (Mermaid diagram)
  - signal_reference.md (human-readable docs)

Statistics:
- Signal density calculation (signals per file)
- Most connected signals ranking
- Most emitted signals ranking

## Test Framework Detection
Added support for 3 Godot test frameworks:
- **GUT** (Godot Unit Test) - extends GutTest, test_* functions
- **gdUnit4** - @suite and @test annotations
- **WAT** (WizAds Test) - extends WAT.Test

Detection results (Cosmic Ideler):
- 20 GUT test files
- 396 test cases detected

## Integration
Updated codebase_scraper.py:
- Signal flow analysis runs automatically for Godot projects
- Test framework detection integrated into code analysis
- SKILL.md shows signal statistics and test framework info
- New section: 📡 Signal Flow Analysis (C3.10)

## Results (Tested on Cosmic Ideler)
- 443/452 files analyzed (98%)
- 208 signals documented
- 634 signal connections mapped
- 298 signal emissions tracked
- 3 event patterns detected (EventBus, Observer, Event Chains)
- 20 GUT test files found with 396 test cases

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 21:44:26 +03:00
yusyus
b252f43d0e feat: Add comprehensive Godot file type support 
Complete support for all Godot file types:
- GDScript (.gd) - Regex-based parser for Godot-specific syntax
- Godot Scenes (.tscn) - Node hierarchy and script attachments
- Godot Resources (.tres) - Properties and dependencies
- Godot Shaders (.gdshader) - Uniforms and shader functions

Implementation details:
- Added 4 new analyzer methods to CodeAnalyzer class
  - _analyze_gdscript(): Functions, signals, @export vars, class_name
  - _analyze_godot_scene(): Node hierarchy, scripts, resources
  - _analyze_godot_resource(): Resource type, properties, script refs
  - _analyze_godot_shader(): Shader type, uniforms, varyings, functions

- Updated dependency_analyzer.py
  - Added _extract_godot_resources() for ext_resource and preload()
  - Fixed DependencyInfo calls (removed invalid 'alias' parameter)

- Updated codebase_scraper.py
  - Added Godot file extensions to LANGUAGE_EXTENSIONS
  - Extended content filter to accept Godot-specific keys
    (nodes, properties, uniforms, signals, exports)

Tested on Cosmic Ideler Godot project:
- 443/452 files successfully analyzed (98%)
- 265 GDScript, 118 .tscn, 38 .tres, 9 .gdshader, 13 .cs

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 21:36:56 +03:00
yusyus
583a774b00 feat: Add GDScript (.gd) language support for Godot projects 
**Problem:**
Godot projects with 267 GDScript files were only analyzing 13 C# files,
missing 95%+ of the codebase.

**Changes:**
1. Added `.gd` → "GDScript" to LANGUAGE_EXTENSIONS mapping
2. Added GDScript support to code_analyzer.py (uses Python AST parser)
3. Added GDScript support to dependency_analyzer.py (uses Python import extraction)

**Known Limitation:**
GDScript has syntax differences from Python (extends, @export, signals, etc.)
so Python AST parser may fail on some files. Future enhancement needed:
- Create GDScript-specific regex-based parser
- Handle Godot-specific keywords (extends, signal, @export, preload, etc.)

**Test Results:**
Before: 13 files analyzed (C# only)
After:  280 files detected (13 C# + 267 GDScript)
Status: GDScript files detected but analysis may fail due to syntax differences

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 21:22:51 +03:00
yusyus
6fe3e48b8a fix: Framework detection now checks directory structure for game engines 
**Problem:**
Framework detection only checked analyzed source files, missing game
engine marker files like project.godot, .unity, .uproject (config files).

**Root Cause:**
_detect_frameworks() only scanned files_analysis list which contains
source code (.cs, .py, .js) but not config files.

**Solution:**
- Now scans actual directory structure using directory.iterdir()
- Checks BOTH analyzed files AND directory contents
- Game engines checked FIRST with priority (prevents false positives)
- Returns early if game engine found (avoids Unity→ASP.NET confusion)

**Test Results:**
Before: frameworks_detected: []
After:  frameworks_detected: ["Godot"] ✅

Tested with: Cosmic Ideler (Godot 4.6 RC2 project)
- Correctly detects project.godot file
- No longer requires source code to have "godot" in paths

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 21:20:17 +03:00
yusyus
32e080da1f feat: Complete Unity/game engine support and local source type validation 
Completes the implementation for Unity/Unreal/Godot game engine support
and adds missing "local" source type validation.

Changes:
- Add "local" to VALID_SOURCE_TYPES in config_validator.py
- Add _validate_local_source() method with full validation
- Add Unity/Unreal/Godot to FRAMEWORK_MARKERS for priority detection
- Add game engine directory exclusions to all 3 scrapers:
  * Unity: Library/, Temp/, Logs/, UserSettings/, etc.
  * Unreal: Intermediate/, Saved/, DerivedDataCache/
  * Godot: .godot/, .import/
- Prevents scanning massive build cache directories (saves GBs + hours)

This completes all features mentioned in PR #278:
✅ Unity/Unreal/Godot framework detection with priority
✅ Pattern enhancement performance fix (grouped approach)
✅ Game engine directory exclusions
✅ Phase 5 SKILL.md AI enhancement
✅ Local source references copying
✅ "local" source type validation
✅ Config field name compatibility
✅ C# test example extraction

Tested:
- All unified config tests pass (18/18)
- All config validation tests pass (28/28)
- Ready for Unity project testing

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 21:06:01 +03:00
pawu
3204c73c01 fix: Resolves CI test failures and linting errors 2026-02-02 01:08:59 +05:30
yusyus
5c4b176117 fix: Add __version__ to __all__ in mcp.tools 
Fix ruff linting error F401 (imported but unused)
 2026-02-01 19:41:14 +03:00
yusyus
f4c326c150 refactor: Use centralized version from _version.py in mcp.tools 
- Remove hardcoded version string
- Import from skill_seekers._version instead
- Ensures single source of truth for version management
- Future version bumps only need pyproject.toml update
 2026-02-01 17:39:40 +03:00
yusyus
4a61449239 fix: Update mcp.tools version to 2.8.0 
Fix failing test in test_package_structure.py
 2026-02-01 17:38:38 +03:00
yusyus
2d038e25c0 ci: Add PyPI publishing to release workflow 
- Build package with uv
- Publish to PyPI using UV_PUBLISH_TOKEN secret
- Automates PyPI release alongside GitHub release
 2026-02-01 17:31:18 +03:00
yusyus
ec9ee9dae8 test: Update version assertions to 2.8.0 
Fix failing tests that were still checking for version 2.7.4
 2026-02-01 17:30:27 +03:00
yusyus
5292a79ad1 chore: Release v2.8.0 
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>
 2026-02-01 17:03:33 +03:00
yusyus
80a40b4fc9 docs: Add AGENTS.md guide for AI coding agents 
- Comprehensive guide for AI assistants working with the codebase
- Covers project structure, development commands, architecture patterns
- Includes testing guidelines, CI/CD info, and troubleshooting
- Documents all entry points, dependencies, and best practices
 2026-02-01 16:31:20 +03:00
pawu
427ea176c6 feat: Add Dart, Scala, SCSS, SASS, Elixir, Lua, Perl language detection resolves #165 2026-02-01 15:15:30 +05:30
yusyus
3a79ceba93 fix: Handle None ai_analysis in how-to guide builder (PR #247) (#274) 
* Fix how-to guide builder edge case

* Resolve merge conflict

* fix: Handle None ai_analysis in how-to guide builder

Fixes NoneType AttributeError when ai_analysis is explicitly None.

The issue occurred when workflow.get('ai_analysis') returned None and
code attempted to call .get() without checking if it was None first.

Using 'workflow.get("ai_analysis", {})' only provides default {} when
the key is missing, not when the value is None. Changed to use
'workflow.get("ai_analysis") or {}' pattern which handles both cases.

Also added isinstance() type safety check in _extract_workflow_examples
to gracefully handle malformed data.

Changes:
- _group_by_ai_tutorial_group: ai_analysis = workflow.get() or {}
- _extract_workflow_examples: isinstance(ex, dict) check added
- _create_guide: ai_analysis = primary_workflow.get() or {} (2 locations)
- _generate_overview: ai_analysis = primary_workflow.get() or {}

All 34 how-to guide builder tests passing.

Closes #242

Co-authored-by: yashrastogi019-cell <yashrastogi019@gmail.com>

---------

Co-authored-by: yashrastogi019-cell <yashrastogi019@gmail.com>
 2026-01-31 22:17:19 +03:00
yusyus
91bd2184e5 fix: Resolve PDF processing (#267), How-To Guide (#242), Chinese README (#260) + code quality (#273) 
Thanks @franklegolasyoung for the excellent work on the core fixes for issues #267, #242, and #260! 🙏

Your comprehensive approach to fixing PDF processing, expanding workflow detection, and improving the Chinese README documentation is much appreciated. I've added code quality fixes and comprehensive tests to ensure everything passes CI.

All 1266+ tests are now passing, and the issues are resolved! 🎉
 2026-01-31 21:30:00 +03:00
yusyus
f726a9abc5 refactor: Centralize version management in single source of truth 
- Create src/skill_seekers/_version.py as single source of truth
- Read version dynamically from pyproject.toml at runtime
- Update all __init__.py files to import from _version module
- Add tomli dependency for Python <3.11 (built-in tomllib for 3.11+)
- Remove hardcoded version duplicates (2.7.2 in 3 files)
- Fixes version mismatch: pyproject.toml (2.7.4) vs __init__.py (2.7.2)

Benefits:
- Single place to update version (pyproject.toml)
- No more version mismatches across files
- Automatic version consistency
- Works across Python 3.10-3.13

Before:
- pyproject.toml: 2.7.4
- src/skill_seekers/__init__.py: 2.7.2
- src/skill_seekers/cli/__init__.py: 2.7.2
- src/skill_seekers/mcp/__init__.py: 2.7.2

After:
- pyproject.toml: 2.7.4 (single source of truth)
- All other files: import from _version.py
 2026-01-31 17:03:40 +03:00
yusyus
86e77e2a30 chore: Post-merge cleanup - remove client docs and fix linter errors 
- Remove SPYKE-related client documentation files
- Fix critical ruff linter errors:
  - Remove unused 'os' import in test_analyze_e2e.py
  - Remove unused 'setups' variable in test_test_example_extractor.py
  - Prefix unused output_dir parameter in codebase_scraper.py
  - Fix import sorting in test_integration.py
- Update CHANGELOG.md with comprehensive PR #272 feature documentation

These changes were part of PR #272 cleanup but didn't make it into the squash merge.
 2026-01-31 14:58:09 +03:00
YusufKaraaslanSpyke
aa57164d34 feat: C3.9 documentation extraction, AI enhancement optimization, and C# support 
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
 2026-01-31 14:56:00 +03:00
yusyus
03ac78173b chore: Remove client-specific docs, fix linter errors, update documentation 
- Remove SPYKE-related client documentation files
- Fix critical ruff linter errors:
  - Remove unused 'os' import in test_analyze_e2e.py
  - Remove unused 'setups' variable in test_test_example_extractor.py
  - Prefix unused output_dir parameter with underscore in codebase_scraper.py
  - Fix import sorting in test_integration.py
- Update CHANGELOG.md with comprehensive C3.9 and enhancement features
- Update CLAUDE.md with --enhance-level documentation

All critical code quality issues resolved.
 2026-01-31 14:38:15 +03:00
YusufKaraaslanSpyke
170dd0fd75 feat(C3.9): Add project documentation extraction from markdown files 
- 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>
 2026-01-31 13:54:56 +03:00
YusufKaraaslanSpyke
4cfb94e14f feat: Add default_enhance_level to config system 
- Add default_enhance_level setting (default: 1 = SKILL.md only)
- --enhance flag now uses config default instead of hardcoded 1
- Show enhance level in config --show output

Users can change default via config file:
~/.config/skill-seekers/config.json
  "ai_enhancement": {
    "default_enhance_level": 2,
    ...
  }

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-30 14:45:46 +03:00
YusufKaraaslanSpyke
3abdf2d1f0 feat: Update MCP scrape_codebase_tool with enhance-level support 
- Add enhance_level parameter (0-3) for granular AI control
- Add skip_* parameters for feature control (skip_patterns, skip_test_examples, etc.)
- Remove deprecated --build-* flags (features are now ON by default)
- Adjust timeout based on enhance_level (10min base, up to 60min for level 3)
- Update documentation with examples

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-30 14:43:46 +03:00
YusufKaraaslanSpyke
e953fc6276 fix: Correct LocalSkillEnhancer import and method call 
- Fix import: SkillEnhancer → LocalSkillEnhancer
- Fix method: enhance() → run(headless=True, timeout=600)
- Fix constructor: pass force=True separately

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-30 14:39:11 +03:00
YusufKaraaslanSpyke
d7aa34a3af feat: Add --enhance-level for granular AI enhancement control 
Levels:
- 0 (off): No AI enhancement (default)
- 1 (minimal): SKILL.md enhancement only (fast, high value)
- 2 (standard): SKILL.md + Architecture + Config enhancement
- 3 (full): Everything including patterns and test examples

--comprehensive and --enhance-level are INDEPENDENT:
- --comprehensive: Controls depth and features (full depth + all features)
- --enhance-level: Controls AI enhancement level

Usage examples:
  skill-seekers analyze --directory . --enhance-level 1  # SKILL.md AI only
  skill-seekers analyze --directory . --enhance          # Same as level 1
  skill-seekers analyze --directory . --comprehensive    # All features, no AI
  skill-seekers analyze --directory . --comprehensive --enhance-level 2  # All features + standard AI

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-30 14:32:07 +03:00
YusufKaraaslanSpyke
b8b5e9d6ef perf: Optimize LOCAL mode AI enhancement with parallel execution 
- Increase default batch size from 5 to 20 patterns per CLI call
- Add parallel execution with 3 concurrent workers (configurable)
- Add ai_enhancement settings to config_manager:
  - local_batch_size: patterns per Claude CLI call (default: 20)
  - local_parallel_workers: concurrent CLI calls (default: 3)
- Expected speedup: 6-12x faster for large codebases

Config settings can be changed via:
  skill-seekers config (coming soon) or editing ~/.config/skill-seekers/config.json

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-30 14:07:20 +03:00
YusufKaraaslanSpyke
8a0c1f5fc6 feat: Add LOCAL mode fallback for all AI enhancements 
When no ANTHROPIC_API_KEY is set, ai_enhancer.py now falls back to LOCAL
mode (Claude Code CLI) instead of disabling AI enhancement entirely.

Changes to AIEnhancer base class:
- AUTO mode now falls back to LOCAL instead of disabling
- Added _check_claude_cli() to verify Claude CLI is available
- Added _call_claude_local() method using Claude Code CLI
- Refactored _call_claude() to dispatch to API or LOCAL mode
- 2 minute timeout per LOCAL call (reasonable for batch processing)

This affects all AI enhancements:
- Design pattern enhancement (C3.1) → LOCAL fallback ✅
- Test example enhancement (C3.2) → LOCAL fallback ✅
- Architectural analysis (C3.7) → LOCAL fallback ✅

Before (bad UX):
  ℹ️  AI enhancement disabled (no API key found)

After (good UX):
  ℹ️  No API key found, using LOCAL mode (Claude Code CLI)
  ✅ AI enhancement enabled (using LOCAL mode - Claude Code CLI)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-30 11:15:54 +03:00
YusufKaraaslanSpyke
a8372b8f9d feat: Auto-enhance SKILL.md when --enhance or --comprehensive flag is used 
UX improvement: When running `skill-seekers analyze --enhance` or
`skill-seekers analyze --comprehensive`, the SKILL.md is now automatically
enhanced as the final step. No need for a separate `skill-seekers enhance`
command.

Changes:
- After analyze_main() completes successfully, check if --enhance or
  --comprehensive was used
- If SKILL.md exists, automatically run SkillEnhancer in headless mode
- Use force=True to skip all prompts (consistent with --comprehensive UX)
- 10 minute timeout for large codebases
- Graceful fallback with retry instructions if enhancement fails

Before (bad UX):
  skill-seekers analyze --directory /path --enhance
  # Then separately:
  skill-seekers enhance output/codebase/

After (good UX):
  skill-seekers analyze --directory /path --enhance
  # Everything done in one command!

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-30 11:07:33 +03:00
YusufKaraaslanSpyke
22e2edbc7f fix: Rewrite config_enhancer LOCAL mode to use Claude CLI properly 
The previous implementation had a design flaw - it ran `claude prompt_file`
and expected Claude to magically create a JSON file in a temp directory.
This never worked because Claude CLI is interactive and doesn't auto-save.

Changes:
- Use `--dangerously-skip-permissions` flag to bypass permission prompts
- Create a dedicated temp directory for each enhancement session
- Embed absolute output file path in the prompt so Claude knows where to write
- Run Claude from the temp directory as working_dir
- Improved prompt with explicit Write tool instruction
- Better error handling and logging (file not found, JSON parse errors)
- Show settings preview in prompt for better AI context

The LOCAL mode now follows the same pattern as enhance_skill_local.py
which works correctly.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-30 10:48:49 +03:00
YusufKaraaslanSpyke
be2353cf2f fix: Add C# test example extraction and fix config_type field mismatch 
Bug fixes:
- Fix KeyError in config_enhancer.py where "config_type" was expected but
  config_extractor saves as "type". Now supports both field names for
  backward compatibility.
- Fix settings "value_type" vs "type" mismatch in the same file.

New features:
- Add C# support for regex-based test example extraction
- Add language alias mapping (C# -> csharp, C++ -> cpp)
- Enhanced C# patterns for NUnit, xUnit, MSTest test frameworks
- Support for mock patterns (NSubstitute, Moq)
- Support for Zenject dependency injection patterns
- Support for setup/teardown method extraction

Tests:
- Add 2 new C# test extraction tests (NUnit tests, mock patterns)
- All 1257 tests pass (165 skipped)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-30 10:12:45 +03:00
yusyus
5a78522dbc docs: Update all documentation to use new 'analyze' command 
- Update Chinese README (README.zh-CN.md) with new preset flags
- Update docs/features/*.md (PATTERN_DETECTION, HOW_TO_GUIDES, BOOTSTRAP_SKILL_TECHNICAL)
- Update scripts/bootstrap_skill.sh to use 'skill-seekers analyze'
- Update scripts/skill_header.md command examples
- Update tests/test_bootstrap_skill.py assertions
- Fix CHANGELOG.md historical entry with correct command name

All references to 'skill-seekers-codebase' updated to 'skill-seekers analyze'
except where needed for backward compatibility (pyproject.toml, E2E tests).

Related to Phase 1 implementation from previous commits.
 2026-01-29 22:56:33 +03:00
yusyus
41fdafa13d test: Add comprehensive E2E tests for analyze command 
Adds 13 end-to-end tests that verify real-world usage of the new
'skill-seekers analyze' command with actual subprocess execution.

Test Coverage:
- Command discoverability (appears in help)
- Subcommand help text
- Quick preset execution
- Custom output directory
- Skip flags functionality
- Invalid directory handling
- Missing required arguments
- Backward compatibility (old --depth flag)
- Output structure validation
- References generation
- Old command still works (skill-seekers-codebase)
- Integration with verbose flag
- Multi-step analysis workflow

Key Features Tested:
✅ Real command execution via subprocess
✅ Actual file system operations
✅ Output validation (SKILL.md generation)
✅ Error handling for invalid inputs
✅ Backward compatibility with old flags
✅ Help text and documentation

All 13 E2E tests: PASSING ✅

Test Results:
- test_analyze_help_shows_command: PASSED
- test_analyze_subcommand_help: PASSED
- test_analyze_quick_preset: PASSED
- test_analyze_with_custom_output: PASSED
- test_analyze_skip_flags_work: PASSED
- test_analyze_invalid_directory: PASSED
- test_analyze_missing_directory_arg: PASSED
- test_backward_compatibility_depth_flag: PASSED
- test_analyze_generates_references: PASSED
- test_analyze_output_structure: PASSED
- test_old_command_still_exists: PASSED
- test_analyze_then_check_output: PASSED
- test_analyze_verbose_flag: PASSED

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-29 22:38:58 +03:00
yusyus
61c07c796d fix: Update integration tests for unified config format 
Fixes 2 failing integration tests to match current validation behavior:

1. test_load_config_with_validation_errors:
   - Legacy validator is intentionally lenient for backward compatibility
   - Only validates presence of fields, not format
   - Updated test to use config that's truly invalid (missing all type fields)

2. test_godot_config:
   - godot.json uses unified format (sources array), not legacy format
   - Old validate_config() expects legacy format with top-level base_url
   - Updated to use ConfigValidator which supports both formats

Changes:
- Import ConfigValidator for unified format validation
- Fix test_load_config_with_validation_errors to trigger actual validation error
- Fix test_godot_config to use ConfigValidator instead of old validate_config

Test Results:
- Both previously failing tests now PASS ✅
- All 71 related tests PASS ✅
- No regressions introduced

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-29 22:24:17 +03:00
yusyus
380a71c714 feat: Add discoverable 'analyze' subcommand with preset flags (Phase 1 UX improvement) 
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>
 2026-01-29 21:52:46 +03:00
yusyus
b72073a482 docs: Add user config directory documentation (ref #262) 
Updated documentation to clarify the three config file locations:

1. README.md:
   - Added "Where to Place Custom Configs" section
   - Explains all three options: user dir, current dir, absolute path
   - Shows config resolution order

2. BULLETPROOF_QUICKSTART.md:
   - Added "Where to Save Custom Configs" section
   - Practical examples for beginners
   - Clarifies when to use each option

3. TROUBLESHOOTING.md:
   - Enhanced "Config File Not Found" section
   - Shows all search locations
   - Provides 5 clear solutions

These docs address the confusion reported in #262 about where to
place custom config files. Users now have clear guidance on using
the new ~/.config/skill-seekers/configs/ directory.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-27 22:03:37 +03:00
yusyus
cf3da6dff3 fix: Improve config path resolution and error messages (fixes #262) 
Three critical UX improvements for custom config handling:

1. User config directory support:
   - Added ~/.config/skill-seekers/configs/ to search path
   - Users can now place custom configs in their home directory
   - Path resolution order: exact path → ./configs/ → user config dir → API

2. Better error messages:
   - Show all searched absolute paths when config not found
   - Added get_last_searched_paths() function to track locations
   - Clear guidance on where to place custom configs

3. Auto-create config.json:
   - ConfigManager now creates config.json on first initialization
   - Creates configs/ subdirectory for user custom configs
   - Display shows custom configs directory path

Fixes reported by @melamers in issue #262 where:
- Config path shown by `skill-seekers config` didn't exist
- Unclear where to save custom configs
- Error messages didn't show exact paths searched

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-27 22:01:04 +03:00
yusyus
746e335fae fix: Auto-fetch preset configs from API when not found locally 
Fixes #264

Users reported that preset configs (react.json, godot.json, etc.) were not
found after installing via pip/uv, causing immediate failure on first use.

Solution: Instead of bundling configs in the package, the CLI now automatically
fetches missing configs from the SkillSeekersWeb.com API.

Changes:
- Created config_fetcher.py with smart config resolution:
  1. Check local path (backward compatible)
  2. Check with configs/ prefix
  3. Auto-fetch from SkillSeekersWeb.com API (new!)
- Updated doc_scraper.py to use ConfigValidator (supports unified configs)
- Added 15 comprehensive tests for auto-fetch functionality

User Experience:
- Zero configuration needed - presets work immediately after install
- Better error messages showing available configs from API
- Downloaded configs are cached locally for future use
- Fully backward compatible with existing local configs

Testing:
- 15 new unit tests (all passing)
- 2 integration tests with real API
- Full test suite: 1387 tests passing
- No breaking changes

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-27 21:41:20 +03:00
xuintl
6aec0e3688 Refine wording and formatting in README.zh-CN.md 
Updated formatting and wording for clarity in the README.
 2026-01-27 21:16:38 +03:00
yusyus
8f720670f2 style: Format code with ruff 
- Format 5 files affected by PDF scraper changes
- Ensures CI/CD code quality checks pass

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-27 21:11:21 +03:00
yusyus
3fc4b54164 fix: Remove duplicate import os statements causing UnboundLocalError 
## Critical Bugs Fixed

### 1. UnboundLocalError in AI Enhancement Modules (BLOCKING)
**Issue**: Duplicate `import os` statements inside conditional blocks caused
UnboundLocalError when accessing os.environ before the import was reached.

**Files Fixed**:
- src/skill_seekers/cli/guide_enhancer.py (lines 92, 112)
- src/skill_seekers/cli/ai_enhancer.py (line 77)
- src/skill_seekers/cli/config_enhancer.py (line 82)

**Root Cause**: `os` was already imported at file top, but re-imported inside
conditional blocks, creating a local variable scope issue.

**Solution**: Removed duplicate import statements - os is already available
from the top-level import.

**Impact**: Fixed 30 failing guide_enhancer tests

### 2. PDF Scraper Test Expectations (BREAKING CHANGE)
**Issue**: Tests expected old keyword-based categorization behavior, but PR
introduced new single-file strategy for single PDF sources.

**Files Fixed**:
- tests/test_pdf_scraper.py (5 tests updated)

**Tests Updated**:
1. test_categorize_by_keywords
2. test_build_skill_creates_reference_files
3. test_code_blocks_included_in_references
4. test_high_quality_code_preferred
5. test_image_references_in_markdown

**Solution**: Updated test expectations to match new single-file strategy
behavior (single PDF → single category named after PDF basename).

**Impact**: Fixed 5 failing PDF scraper tests

## Test Results

**Before Fixes**: 35 tests failing
**After Fixes**: 130 tests passing, 5 skipped ✅

### Tested Modules:
- ✅ PDF scraper (18 tests)
- ✅ Guide enhancer (30 tests)
- ✅ All adaptors (82 tests)

## Verification

```bash
pytest tests/test_pdf_scraper.py tests/test_guide_enhancer.py tests/test_adaptors/ -v
# Result: 130 passed, 5 skipped in 1.11s
```

## Notes

The original PR features (GLM-4.7 support + PDF scraper improvements) are
excellent and working correctly. These fixes only address the import scoping
bug introduced during implementation and update tests for the new behavior.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-27 21:11:04 +03:00