mirror of
https://github.com/rohitg00/skillkit.git
synced 2026-11-18 18:04:26 +00:00
* feat(quality): add skill quality evaluation system - Add quality scoring module with structure, clarity, and specificity metrics - Evaluate skills for metadata, triggers, boundaries, code examples - Detect vague terms and penalize overly long skills - Update validate command to include quality reports - Add --verbose, --quality, --issues, --json flags - Quality scores: A (90+), B (80+), C (70+), D (60+), F (<60) * fix: address CodeRabbit and Devin review suggestions - Fix JSON output to return exit code 1 on validation failures - Add --min-score NaN validation with warning message - Add directory guard for --all flag with .mdc file support - Fix CRLF handling in frontmatter extraction - Fix code blocks double-counting in specificity evaluation - Fix warning message inconsistency for code examples - Add try/catch error handling in evaluateSkillFile - Fix isHighQuality threshold to match UI display (80) * feat(quality): extend quality evaluation system with badges, deeper analysis, and fix command - Phase 2: Add quality badges to CLI commands (list, recommend, install) - formatQualityBadge() helper for color-coded grade badges - --quality flag for list command - Low-quality skill warnings during install - Phase 3: Add TUI quality badges - Extended SkillItem with quality, grade, warnings fields - Quality evaluation in loadSkills() - Grade badges in Installed and Recommend screens - Phase 4: Deeper quality analysis - Deprecated pattern detection (CommonJS, class components, var) - Security pattern detection (hardcoded credentials, eval, innerHTML) - Conflicting instruction detection - Completeness assessment (TODOs, empty sections, example coverage) - New weight distribution: Structure 35%, Clarity 25%, Specificity 25%, Advanced 15% - Phase 1: Pre-compute marketplace quality scores - Updated schema.json with quality field (0-100) - Created scripts/compute-quality.ts for batch computation - Phase 5: Benchmark against category leaders - New benchmark.ts module with category detection - Percentile calculation and comparison notes - --benchmark flag for validate command - Phase 6: Fix command for automated quality fixes - skillkit fix command with --dry-run and --interactive modes - Auto-generates frontmatter, "When to Use", "Boundaries" sections - --fix flag alias on validate command * fix: address CodeRabbit and Devin review suggestions - Fix .mdc file name extraction in fix.ts (handles both .md and .mdc) - Add missing advanced field to test fixtures in quality.test.ts - Fix duplicate header detection in assessCompleteness using regex.exec - Fix ESM compatibility in compute-quality.ts using import.meta.url - Add trailing newline to skills.json output * fix: address remaining CodeRabbit review suggestions - Escape regex metacharacters in vague term patterns (fix.ts) - Improve diff algorithm using set-based comparison (fix.ts) - Fix validateSkill receiving file path instead of directory (validate.ts) - Check final section in completeness assessment (index.ts) - Add error handling and empty skills guard (compute-quality.ts) * fix: address additional review feedback - validate.ts: Add error when --fix is passed without targets - index.ts: Skip headers inside fenced code blocks during completeness check - compute-quality.ts: Use nullish coalescing (??) to preserve zero quality scores
SkillKit
Universal skills manager for AI coding agents. Install, manage, and sync skills across 17+ AI agents including Claude Code, Cursor, Codex, Gemini CLI, and more.
Installation
npm install -g skillkit
Quick Start
# Initialize skillkit in your project
skillkit init
# Install skills from GitHub
skillkit install anthropics/skills
# Get recommendations for your stack
skillkit recommend
# Launch interactive TUI
skillkit ui
Core Features
Cross-Agent Translation
# Translate a Claude skill to Cursor format
skillkit translate react-patterns --to cursor
# Translate all skills to multiple agents
skillkit translate --all --to windsurf,codex
# Preview translation
skillkit translate my-skill --to copilot --dry-run
Smart Recommendations
# Get project-aware suggestions
skillkit recommend
# Filter by task
skillkit recommend --search "authentication"
# Quality threshold
skillkit recommend --min-score 85
Team Collaboration
# Initialize team
skillkit team init --name "Engineering Team"
# Create skill bundle
skillkit team bundle-create
# Share with team
skillkit team share onboarding-bundle
# Sync with remote registry
skillkit team sync
Plugin System
# List installed plugins
skillkit plugin list
# Install custom plugin
skillkit plugin install @company/custom-translator
# View plugin info
skillkit plugin info my-plugin
Development Methodologies
# List available methodologies
skillkit methodology list
# Load TDD methodology
skillkit methodology load tdd
# Apply to project
skillkit methodology apply agile
Plan System
# Parse and validate plan
skillkit plan parse ./implementation-plan.md
skillkit plan validate ./plan.md
# Execute plan
skillkit plan execute ./feature-plan.md
# Check status
skillkit plan status
Hooks & Automation
# List hooks
skillkit hook list
# Register pre-commit hook
skillkit hook register pre-commit
# Trigger manually
skillkit hook trigger pre-commit
Workflow Orchestration
# List workflows
skillkit workflow list
# Run workflow
skillkit workflow run feature-development
# Create new workflow
skillkit workflow create deployment-flow
Session Memory
# View learnings
skillkit memory list
# Search past sessions
skillkit memory search "error handling"
# Compress observations
skillkit memory compress
# Export learning as skill
skillkit memory export auth-insight --output auth-skill.md
Supported Agents (17)
Claude Code, Cursor, Codex, Gemini CLI, Windsurf, GitHub Copilot, OpenCode, Antigravity, Amp, Clawdbot, Droid, Goose, Kilo, Kiro, Roo, Trae, Universal
Usage Examples
Install and Sync
# Install to multiple agents
skillkit install anthropics/skills --agent claude-code,cursor
# Sync all skills to detected agents
skillkit sync --all
Context Management
# Initialize project context
skillkit context init
# View detected stack
skillkit context show
# Sync to all agents
skillkit context sync --all
Testing
# Run all skill tests
skillkit test
# Test specific skills
skillkit test ./my-skill --tags unit
# CI/CD integration
skillkit cicd init
Documentation
Full documentation: https://github.com/rohitg00/skillkit
License
Apache-2.0