skill-ao92265-claude-code-playbook-done · by Install
$ agentstack add skill-ao92265-claude-code-playbook-done ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-ao92265-claude-code-playbook-done) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Done — Verification Gate
A "done" claim without a verification command and exit code is a guess. This skill makes the gate mechanical.
Protocol
- Detect entrypoint. From the repo root:
- If
jq -e '.scripts."ci:local"' package.jsonsucceeds → runnpm run ci:local. - Else discover available scripts:
typecheck,lint,test,build. Run
them in that order. Skip silently if a script does not exist.
- For monorepos with
frontend/andbackend/workspaces (Wraith pattern):
also run the frontend variants (typecheck:frontend, lint:frontend, test:frontend).
- Capture exit code per stage. Print one line per stage:
`` [done] typecheck: exit=0 [done] lint: exit=0 [done] test: exit=1 /dev/null.
- Long stages (build, full test) → use
run_in_backgroundandMonitor. Don't
poll with sleep loops.
- If
npm installis needed first, that's a different skill (/check-env). Do
not auto-install dependencies.
When Not To Run
- The user asked a research-only or exploratory question.
- You haven't actually made any changes this turn.
- A specific narrower check was requested (e.g. "just typecheck").
Why This Skill Exists
The /insights report (2026-04-27) flagged "premature completion claims" as the #1 recurring friction across 82 sessions. Existing prose rules in CLAUDE.md ("verify before claiming done") were not enough — Claude declared done with failing tsc/vitest 3–4 times per cycle. This skill replaces the prose with a mechanical gate.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ao92265
- Source: ao92265/claude-code-playbook
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.