danwahlin/ai-agent-board/gate-enforcement
Claude Code and agent skill by danwahlin/ai-agent-board
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Run risk-based ai-agent-board quality gates after code-producing work.
Install
npx vskill@latest install danwahlin/ai-agent-board/gate-enforcementSKILL.md
Context
Use this skill after any task that writes code or changes runtime behavior. Documentation-only Squad state changes only need consistency validation unless they add scripts or app-facing behavior.
Patterns
- Identify the affected surface in
.squad/coverage-matrix.md. - For code-producing work, run the deterministic required gate:
npm run gate:required. - The required gate runs
npm run build:client,npm run build:server, andnpm run test:e2e:required; do not replace it with ad hoc build or E2E commands. - Install the local pre-push hook with
npm run hooks:installso Git uses.githooks/pre-push. - Prefer focused existing tests before broad suites, but required gate evidence must still include
npm run gate:required. - E2E portability/setup problems, including hard-coded Unix paths such as
/tmp/test-repo, are blockers to fix in the test setup before approval; they are not acceptable reasons to defer affected E2E coverage. - Fix-loop ceiling: 3 attempts or 5 minutes on the same failing class, then escalate to Morpheus/Switch.
Examples
- Agent runtime change: Neo owns implementation; Switch requests focused runtime tests plus
npm run gate:required. - Board UI change: Trinity owns implementation; Switch requests focused e2e/component evidence plus
npm run gate:required.
Anti-Patterns
- Do not weaken or skip tests to make a gate pass.
- Do not treat unrelated baseline failures as proof the current change is safe.
- Do not skip affected e2e for convenience, portability, unavailable dev servers, or setup friction; start/fix the required processes or fail the gate.
- Do not replace required e2e evidence with a build-only claim for browser workflow or client-server behavior changes.
- Do not run softer ad hoc E2E commands when
npm run gate:requiredis available.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryChecking.squad/skills/gate-enforcement/SKILL.md
Popularity
- Repository stars
- 69
- Repository forks
- 18
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/danwahlin/ai-agent-board/gate-enforcement)