Files
skillkit/packages/cli/README.md
T
Rohit Ghumare 1344d65b3d feat: implement phases 12-18 - complete agentic development platform (#6)
* feat: implement phases 12-18 - complete agentic development platform

This comprehensive update implements 7 major phases (12-18) transforming
SkillKit into a universal agentic development platform with methodology
packs, hooks, orchestration, planning, and AI capabilities.

Phase 12: Methodology Framework
- MethodologyManager for pack-based methodology distribution
- 5 methodology packs (testing, debugging, planning, collaboration, meta)
- 13 curated methodology skills
- Pack loader with validation and installation
- 56 comprehensive tests

Phase 13: Hooks & Automatic Triggering System
- HookManager with event-driven skill activation
- 10+ event types (session:start, file:open, task:start, etc.)
- Pattern-based triggers with glob support
- Agent-specific hook generation
- 29 comprehensive tests

Phase 14: Subagent Orchestration
- TeamOrchestrator for multi-agent coordination
- TaskManager with cross-agent assignment
- Plan approval workflow (submit → approve/reject)
- TeamMessageBus for agent communication
- Two-stage review system (spec compliance + code quality)
- 36 comprehensive tests

Phase 15: Structured Plan System
- PlanParser for markdown → structured plan conversion
- PlanValidator for completeness checking
- PlanExecutor with dry-run support
- Bite-sized task format (2-5 min atomic tasks)
- 36 comprehensive tests

Phase 16: Slash Commands & Agent Integration
- CommandRegistry for slash command management
- Agent-specific command generation (Claude, Cursor, OpenCode)
- Command aliases and arguments support
- 42 comprehensive tests

Phase 17: Enhanced Agent Features
- Permission system (allow/deny/ask patterns)
- Glob pattern matching for file-scoped skills
- Bootstrap files (AGENTS.md, SOUL.md, TOOLS.md)
- Multi-mode support (Code/Architect/Debug/Ask)
- Agent feature tests

Phase 18: Advanced Features (AI & Audit)
- AIManager with natural language skill search
- Automatic skill generation from examples/code
- MockAIProvider for testing without API keys
- AuditLogger with complete operation trail
- Query, export (JSON/CSV/text), and statistics
- 37 comprehensive tests (15 AI + 22 audit)

CLI Commands Added:
- skillkit methodology list|install|sync
- skillkit hook add|remove|list|generate
- skillkit plan parse|validate|execute|create
- skillkit commands generate|list
- skillkit ai search|generate|similar
- skillkit audit log|export|stats|clear

TUI Enhancements:
- Methodology screen (o key) for pack browsing
- Plan screen (n key) for plan viewing/execution
- Updated navigation and sidebar

Test Coverage:
- Total: 619 tests passing (582 core + 49 agents + 1 cli + 3 app)
- New: 245+ tests for phases 12-18
- Coverage maintained at 80%+

Breaking Changes: None
Dependencies: No new external dependencies added

* fix: apply CodeRabbit security and quality improvements

Security Fixes:
- Replace custom glob-to-regex with minimatch to prevent ReDoS vulnerabilities
- Fix regex pattern generation in globs.ts using battle-tested library
- Eliminate unsafe regex patterns in modes.ts and permissions.ts

Code Quality Improvements:
- Use shared GlobMatcher utility to eliminate code duplication in modes.ts
- Preserve command metadata on updates to prevent data loss
- Fix single-file vs directory output path handling in command.ts
- Pass --strict flag through to plan validator

Race Condition & Concurrency Fixes:
- Add Promise-based mutex to prevent race condition in audit logger flush()
- Handle both sync and async event listeners to prevent unhandled rejections
- Maintain synchronous event emission while safely handling async listeners

Data Integrity Fixes:
- Fix dependency checking to detect missing dependencies
- Rehydrate Date fields when importing tasks from JSON
- Fix executePlan to properly detect incomplete tasks

State Management:
- Add validation for missing step executor (fail fast)
- Handle cancellation and reset executor state in finally block
- Add 'cancelled' status and event to PlanStatus/PlanEvent types

Dependencies:
- Add minimatch@^10.0.1 to @skillkit/agents package

All 639 tests passing.

* docs: update READMEs with Phase 10-18 features

- Root README: add minimal "What's New in v1.5.0" section with 5 bullet points
- packages/core: add usage examples for Team, Plugin, Methodology, Orchestration, Plan, Hooks
- packages/cli: add command sections for team, plugin, methodology, plan, hook, command
- packages/tui: add screen descriptions for Marketplace, Workflow, Execute, Team, Plugins, Methodology, Plan, Memory
- apps/skillkit: expand with practical usage examples for all new features

All updates are clean, user-focused, and avoid AI marketing fluff.

* fix: resolve multiple code quality and robustness issues

- Fix minimatch dependency: downgrade to ^9.0.0 for Node 18 compatibility
- Fix command.ts export: handle directory paths and ensure parent directories exist
- Fix command.ts merge: preserve curated examples when merging commands
- Fix plan.ts: filter empty entries from comma-separated inputs
- Fix audit logger pagination: respect explicit 0 for limit and offset
- Fix audit logger: gracefully handle malformed JSON lines without data loss
- Fix team orchestrator: prevent task assignment to non-idle agents
- Fix plan executor: unblock waitIfPaused() when cancel() is called

All 639 tests passing.

* fix: additional robustness improvements for plan and executor

- Fix plan.ts createPlan: filter empty strings from techStack after split/trim
- Fix executor.ts: re-check abort signal after waitIfPaused() in both execute() and executeTask()
  to prevent running additional tasks/steps after cancellation during pause

All 639 tests passing.
2026-01-24 11:54:47 +00:00

255 lines
7.0 KiB
Markdown

# @skillkit/cli
[![npm version](https://img.shields.io/npm/v/@skillkit/cli.svg)](https://www.npmjs.com/package/@skillkit/cli)
[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
**Command-line interface for SkillKit** - install, manage, translate, and sync skills across 17 AI coding agents.
## Installation
```bash
npm install -g @skillkit/cli
# or
npm install -g skillkit # includes CLI
```
## Quick Start
```bash
# Get skill recommendations for your project
skillkit recommend
# Install skills from GitHub
skillkit install anthropics/skills
# Translate skills between agents
skillkit translate my-skill --to cursor
# Launch interactive TUI
skillkit ui
```
## All Commands
### Skill Management
```bash
skillkit install <source> # Install from GitHub/GitLab/Bitbucket/local
skillkit remove <skills> # Remove installed skills
skillkit update [skills] # Update skills from source
skillkit list # List installed skills
skillkit enable <skills> # Enable specific skills
skillkit disable <skills> # Disable specific skills
skillkit sync # Sync to agent config
skillkit read <skills> # Read skill content
```
### Discovery & Recommendations
```bash
skillkit recommend # Project-based recommendations
skillkit recommend --search "auth" # Task-based search
skillkit recommend --category security # Filter by category
skillkit recommend --min-score 80 # Quality threshold
skillkit marketplace # Browse skills
skillkit marketplace search "react" # Search marketplace
skillkit marketplace --tags typescript # Filter by tags
skillkit marketplace refresh # Refresh index
```
### Translation
```bash
skillkit translate <skill> --to <agent> # Translate single skill
skillkit translate --all --to cursor # Translate all skills
skillkit translate skill --dry-run # Preview without writing
```
### Context Management
```bash
skillkit context init # Analyze project, create context
skillkit context show # Display current context
skillkit context sync --all # Sync to all detected agents
skillkit context export # Export context file
```
### Session Memory
```bash
skillkit memory status # View memory status
skillkit memory search "auth" # Search learnings
skillkit memory list # List all learnings
skillkit memory compress # Compress observations
skillkit memory export <id> # Export as skill
skillkit memory add # Add manual learning
skillkit memory --global # Use global scope
```
### Testing & Workflows
```bash
skillkit test # Run all skill tests
skillkit test ./my-skill # Test specific skill
skillkit test --tags unit # Run tagged tests
skillkit workflow list # List workflows
skillkit workflow run <name> # Execute workflow
skillkit workflow create # Create new workflow
skillkit cicd github-action # Generate GitHub Actions
skillkit cicd gitlab-ci # Generate GitLab CI
skillkit cicd pre-commit # Generate pre-commit hook
skillkit cicd init # Initialize CI/CD templates
```
### Team Collaboration
```bash
skillkit team init --name "Team" # Initialize team
skillkit team share <bundle> # Share skill bundle
skillkit team import <path> # Import bundle
skillkit team list # List team bundles
skillkit team sync # Sync with remote
skillkit team remove <bundle> # Remove bundle
skillkit team bundle-create # Create new bundle
skillkit team bundle-export <id> # Export bundle
skillkit team bundle-list # List all bundles
```
### Plugin System
```bash
skillkit plugin list # List installed plugins
skillkit plugin install <name> # Install plugin
skillkit plugin uninstall <name> # Uninstall plugin
skillkit plugin enable <name> # Enable plugin
skillkit plugin disable <name> # Disable plugin
skillkit plugin info <name> # Plugin details
```
### Methodologies & Plans
```bash
skillkit methodology list # List methodologies
skillkit methodology load <name> # Load methodology
skillkit methodology apply <name> # Apply to project
skillkit plan parse <file> # Parse plan file
skillkit plan validate <file> # Validate plan
skillkit plan execute <file> # Execute plan
skillkit plan status # Plan execution status
```
### Hooks & Automation
```bash
skillkit hook list # List registered hooks
skillkit hook register <event> # Register new hook
skillkit hook trigger <event> # Trigger hook manually
skillkit hook enable <id> # Enable hook
skillkit hook disable <id> # Disable hook
```
### Agent Commands
```bash
skillkit command generate <agent> # Generate agent-native commands
skillkit command list <agent> # List available commands
```
### Utilities
```bash
skillkit init # Initialize in project
skillkit init --agent cursor # Initialize for specific agent
skillkit validate ./skill # Validate skill format
skillkit create my-skill # Create new skill
skillkit settings # View all settings
skillkit settings --set key=value # Update setting
```
## Install Options
```bash
skillkit install owner/repo # GitHub repository
skillkit install gitlab:owner/repo # GitLab repository
skillkit install ./local/path # Local directory
# Options
--list # List available skills without installing
--skills=pdf,xlsx # Install specific skills
--all # Install all discovered skills
--yes # Skip confirmation prompts
--global # Install globally
--force # Overwrite existing
--agent=cursor,windsurf # Install to specific agents
```
## Programmatic Usage
```typescript
import {
installCommand,
listCommand,
syncCommand,
translateCommand,
recommendCommand,
} from '@skillkit/cli';
// Install skills programmatically
await installCommand('anthropics/skills', {
agent: ['claude-code', 'cursor'],
yes: true,
});
// List installed skills
const skills = await listCommand({ json: true });
// Sync to agent
await syncCommand({ all: true });
// Translate skill
await translateCommand('my-skill', {
to: 'cursor',
dryRun: false,
});
// Get recommendations
const recs = await recommendCommand({
path: './my-project',
minScore: 70,
});
```
## CI/CD Usage
```yaml
# GitHub Actions example
- name: Setup skills
run: |
npx skillkit install owner/skills --skills=lint,test --yes
npx skillkit sync --yes
```
## Supported Agents
| Agent | Format |
|-------|--------|
| Claude Code | SKILL.md |
| Cursor | MDC (.mdc) |
| Codex | SKILL.md |
| Gemini CLI | SKILL.md |
| Windsurf | Markdown |
| GitHub Copilot | Markdown |
| + 11 more | SKILL.md |
## Documentation
Full documentation: https://github.com/rohitg00/skillkit
## License
Apache-2.0