CleanExpo/.claude/skills/implement
.claude/skills/implement/SKILL.md
# Implement Skill **Name:** implement **Triggers:** `/implement` (manual invocation only — not natural language) **Version:** 1.0.0 --- ## Purpose Three-phase structured build pipeline: PLAN → BUILD → VERIFY. Each phase runs in an isolated subagent context so the main session sees only the verdict, not the file-by-file walkthrough. Designed to drive a complete feature from approved plan to commit-ready code without polluting the main conversation. This skill is **manual invocation only** (n
$ install --global
skillsauthnpx skillsauth add CleanExpo/CCW-CRM .claude/skills/implementInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 1:19 PM63.9s1 file scanned
SKILL.md
Implement Skill
Name: implement
Triggers: /implement (manual invocation only — not natural language)
Version: 1.0.0
Purpose
Three-phase structured build pipeline: PLAN → BUILD → VERIFY. Each phase runs in an isolated subagent context so the main session sees only the verdict, not the file-by-file walkthrough. Designed to drive a complete feature from approved plan to commit-ready code without polluting the main conversation.
This skill is manual invocation only (no natural-language triggers). It runs the heaviest workflow in the system and should never fire unintentionally.
Commands
/implement <feature description>
Runs the full three-phase pipeline. Stops between phases to surface the result to the CEO for approval.
Phase 1 — PLAN
Dispatches to the existing planner.md agent at .claude/agents/planner.md. The planner produces the project's standard plan template (Objective / Files / Steps / Tests / Risks / Breaking Changes) and surfaces it to the CEO. STOP — wait for explicit approval before Phase 2.
If the user has already approved a plan in the current session, skip to Phase 2 with the existing plan.
Phase 2 — BUILD
Dispatches to the existing coder.md agent at .claude/agents/coder.md. The coder follows the approved plan exactly:
- One file at a time
- Tests written alongside implementation (Vitest for frontend, Pytest for backend)
- Reference patterns:
apps/web/components/auth/login-form.tsx(frontend forms),apps/backend/src/api/routes/translations.py(backend routes) - No locked files touched (
demo_models.py,demo_auth.py,middleware.ts) - Commits after each logical unit, NOT at the end
Phase 3 — VERIFY
Runs the project's quality gate inside the subagent and reports pass/fail to main context:
# Frontend
pnpm turbo run lint
pnpm turbo run type-check
pnpm turbo run test
# Backend
cd apps/backend && uv run ruff check
cd apps/backend && uv run mypy src/
cd apps/backend && uv run pytest tests/api/test_<module>.py
All green = ready for review chain. Single red line = STOP, surface to CEO with the exact failure.
After verification passes, the skill recommends invoking the heavyweight review chain (@code-reviewer → @security-auditor → @database-specialist → @deploy-guardian → @orchestrator) before any PR.
Process Rules
- Never skip a phase. PLAN before BUILD before VERIFY — no shortcuts.
- Never auto-commit final results. The skill stages and prepares but the human CEO approves the actual commit.
- Phase boundaries are hard. A failure in Phase 2 does not roll back to Phase 1; it surfaces and stops.
- Reference patterns mandatory. New code must match
login-form.tsxandtranslations.pyshape — no inventing new structure.
When NOT to use this skill
- 1-line fix or typo — use
/fixinstead (much cheaper) - Architecture exploration — use
/arch-planfirst (read-only) - The work crosses module boundaries unpredictably — invoke
@erp-build-specialistfor autonomous selection - The work requires schema changes — STOP, escalate via Linear ticket
Related
.claude/agents/planner.md— Phase 1 dispatch target.claude/agents/coder.md— Phase 2 dispatch target.claude/skills/arch-plan/SKILL.md— lightweight planning alternative.claude/skills/autonomous-build/SKILL.md— autonomous version that selects work AND implementsMANAGED_AGENTS_v4_FINAL.md§ Autonomous Deploy Gate — review chain that runs after this skill
Related Skills
CleanExpo/youtube-uploader
content-media
VerifiedTrustedCommunity
Autonomously uploads CCW HeyGen demo videos to YouTube as Unlisted, collects video IDs, and patches DemoVideoBanner.tsx + video-registry.json. One-time OAuth setup required. Handles resume, retries, and ID propagation.
1SKILL.mdUpdated Apr 16, 2026
CleanExpo/unfreeze
data-ai
VerifiedTrustedCommunity
Clear the freeze boundary set by /freeze, allowing edits to all directories again. Use when you want to widen edit scope without ending the session. Use when asked to "unfreeze", "unlock edits", "remove freeze", or "allow all edits". (gstack)
1SKILL.mdUpdated Apr 16, 2026
CleanExpo/.claude/skills/spec-interview
tools
VerifiedTrustedCommunity
# Spec Interview Skill **Name:** spec-interview **Triggers:** `/spec-interview`, when requirements unclear **Version:** 1.0.0 --- ## Purpose Interviews user to gather complete requirements before planning. --- ## Interview Questions When requirements are unclear, ask: ### 1. Feature Clarity **Question:** "What is this feature supposed to do?" **Why:** Need clear objective ### 2. User Impact **Question:** "Who will use this and why?" **Why:** Understand user needs ### 3. Success Criteri
1SKILL.mdUpdated Apr 16, 2026
CleanExpo/ship
development
VerifiedTrustedCommunity
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is ready, asks about deploying, wants to push code up, or asks to create a PR. (gstack)
1SKILL.mdUpdated Apr 16, 2026