菜单
Install executable quality gates for a repo and normalize validation behind stable scripts. Use when a project needs linting, formatting, type checking, tests, builds, doc checks, boundary checks, CI, or a single scripts/validate command for Codex.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Diagnose failed or unreliable agent workflows by classifying bad assumptions, missing observations, tool misuse, wrapper failures, hidden repair loops, incomplete validation, handoff gaps, and repeated failure patterns. Use after a failed harness run, flaky agent output, or confusing validation loop.
Review agent-generated changes against project rules. Use when asked for a review, before opening a PR, after large Codex edits, or when checking diffs for correctness, security, architecture, tests, docs drift, dependencies, migrations, and release risk.
Generate or maintain a minimal high-signal AGENTS.md for coding agents. Use whenever a repo needs agent instructions, an existing AGENTS.md is too long or vague, or project docs/scripts need a concise routing map for Codex.
Define and mechanically enforce architecture boundaries for a repo. Use when a project needs allowed dependency rules, forbidden imports, layer documentation, dependency maps, circular dependency checks, or protection against agent-created architectural drift.
Scaffold a new TypeScript web, mobile, API, or full-stack project with Better-T-Stack, then harden it with the Pax Fullstack Harness. Use whenever the user wants a new TypeScript app scaffold, mentions Better-T-Stack, asks for a modern type-safe stack, or wants Codex to start a repo that is agent-ready from day one.
Use guided Chrome DevTools MCP setup and workflows for browser runtime debugging. Use when a web app needs console, network, DOM, accessibility, Lighthouse, performance, responsive, or live-browser investigation beyond normal tests.
| name | quality-gates-installer |
| description | Install executable quality gates for a repo and normalize validation behind stable scripts. Use when a project needs linting, formatting, type checking, tests, builds, doc checks, boundary checks, CI, or a single scripts/validate command for Codex. |
Turn repeated agent mistakes into executable checks. Prefer project-native tooling and normalize it behind stable wrappers.
scripts/ directoryDetect existing checks.
Create stable wrappers.
scripts/lintscripts/typecheckscripts/testscripts/buildscripts/check-boundariesscripts/check-docsscripts/audit-entropyscripts/validatescripts/check-feature-state, scripts/check-session-handoff, scripts/init-check, scripts/termination-check, scripts/check-sprint-contract, and scripts/check-instructions.scripts/test-e2e, scripts/click-path-audit, scripts/check-research-evidence, and scripts/ci-local.Make scripts/validate canonical.
Add CI.
.github/workflows/ci.yml that runs the same validation interface.scripts/ci-local when helpful.ci-cd-harness when deployment gates, artifacts, coverage, or CI failure triage are needed.Update docs.
docs/development/commands.md.docs/quality/code-style.md.AGENTS.md command list if needed.security-baseline, dependency-governance, and documentation-sync-enforcer for specialized security, dependency, and docs checks.termination-gatekeeper when validation must prove task completion instead of baseline health.#!/usr/bin/env bash and set -euo pipefail for shell wrappers.rg for text checks.scripts/test scoped to unit/integration tests and run Playwright only through scripts/test-e2e.AGENTS.md, unless the check is explicitly a docs check../scripts/validate.AGENTS.md list the same commands.