CleanExpo/.claude/skills/arch-plan
.claude/skills/arch-plan/SKILL.md
# Architecture Plan Skill **Name:** arch-plan **Triggers:** `/arch-plan`, "design implementation for", "architect this feature" **Version:** 1.0.0 --- ## Purpose Lightweight architectural planning that runs in an isolated subagent context. Returns a structured 350-word plan to the main conversation without polluting it with the dozens of file reads the planner walked through. **This is NOT the canonical interactive planning command.** For interactive planning with CEO approval gates, the pr
$ install --global
skillsauthnpx skillsauth add CleanExpo/CCW-CRM .claude/skills/arch-planInstall 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, 12:47 PM4.5s1 file scanned
SKILL.md
Architecture Plan Skill
Name: arch-plan
Triggers: /arch-plan, "design implementation for", "architect this feature"
Version: 1.0.0
Purpose
Lightweight architectural planning that runs in an isolated subagent context. Returns a structured 350-word plan to the main conversation without polluting it with the dozens of file reads the planner walked through.
This is NOT the canonical interactive planning command. For interactive planning with CEO approval gates, the project's standard plan template, and the full TASK EXECUTION PROTOCOL, use /plan (which exists at .claude/commands/plan.md). This skill is the cheaper, faster, isolated-context version meant for use inside other subagent workflows (e.g., the /implement skill calls arch-plan as its first phase).
Commands
/arch-plan <feature description>
Dispatches the planning request to an isolated subagent. The subagent uses grep/glob to understand the relevant codebase area, identifies which files need to change, sequences the steps, and returns a structured plan.
Returns to main context (≤350 words):
- Objective: 1 sentence — what this feature accomplishes
- Files to change:
filepath+ 1-line rationale per file - Steps: numbered, dependency-ordered
- Tests: specific cases needed (Vitest + Pytest)
- Risks: what could break + how to mitigate
The plan is read-only — no code is written, no files are modified. The output goes to the main session for CEO approval before any /implement invocation.
Dispatch Target
Routes to the existing planner.md agent at .claude/agents/planner.md. That agent already produces the project's standard plan template (Objective / Files / Steps / Risks / Breaking Changes). This skill wraps it in a lightweight isolated-context invocation.
Process Rules (enforced inside the subagent)
- Read-only. The subagent must NOT call
WriteorEditunder any circumstances. - grep/glob first. Locate relevant files without reading them in full.
- Cite reference patterns. Plans must reference
apps/backend/src/api/routes/translations.py(backend pattern) andapps/web/components/auth/login-form.tsx(frontend pattern) where relevant. - No locked files. Plans must NOT touch
apps/backend/src/db/demo_models.py,apps/backend/src/api/routes/demo_auth.py, orapps/web/middleware.ts. - Word budget. Output is hard-capped at 350 words.
When NOT to use this skill
- You need interactive multi-round planning with CEO approval — use
/planinstead (canonical interactive command) - The change is a 1-line fix or typo — use
/fixinstead - You don't yet know what you want to build — use
/researchfirst to understand the codebase - The feature requires schema changes — STOP, escalate to CEO via Linear ticket (schema changes are forbidden)
Related
.claude/commands/plan.md— canonical interactive planning command (use this for real planning sessions).claude/agents/planner.md— dispatch target.claude/skills/implement/SKILL.md— callsarch-planas its first phaseMANAGED_AGENTS_v4_FINAL.md— operating protocol that all plans must respect
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