AGENT SKILL

agent-skill-kit-ci-integrator

Wire the agent-skills toolkit into CI — install the GitHub Actions workflow that runs validate/lint/audit/deps on every PR, and install the pre-commit hooks for local-loop parity. Use when the user asks to set up CI for skills, install pre-commit hooks, configure GitHub Actions for SKILL.md validation, or wire the toolkit into a new repo.

License 许可
Apache-2.0
最近更新
2026-08-25
Stars
★ 0
Forks
0

01 前言 Front Matter

name
agent-skill-kit-ci-integrator
tier
org
license
Apache-2.0
description
Wire the agent-skills toolkit into CI — install the GitHub Actions workflow that runs validate/lint/audit/deps on every PR, and install the pre-commit hooks for local-loop parity. Use when the user asks to set up CI for skills, install pre-commit hooks, configure GitHub Actions for SKILL.md validation, or wire the toolkit into a new repo.
compatibility
requires `pre-commit` (Python pkg) for local hooks; GitHub Actions for CI; node>=20 + python>=3.11 for the underlying skills-ref CLI

03 SKILL.md 正文

Agent Skill CI Integrator

Documents the two CI integration points the toolkit ships and explains how to install, inspect, and extend them.

When to use

  • "Set up CI for our skills"
  • "Install pre-commit for SKILL.md"
  • "How do I wire skills-ref into GitHub Actions?"
  • "Add a PR gate for skills changes"
  • "Audit the agent-skills CI configuration"

GitHub Actions workflow

The canonical workflow lives at .github/workflows/agent-skills-ci.yml. It declares three jobs in a strict dependency order:

  1. mjs-ci — runs make ci in .agents/skills/agent-skill-kit-commons/packages/mjs/. Emits artifacts/validate.json from the Node runtime as a stage artifact.
  2. py-ci — runs make ci in .agents/skills/agent-skill-kit-commons/packages/py/. Verifies polyglot parity by re-running the same gates from the Python runtime.
  3. gate (depends on both) — runs lint, audit, deps from the Node runtime, downloads mjs-ci's validate artifact, and posts a single rolled-up comment on the PR. The comment is keyed by an HTML marker (<!-- agent-skills-ci-marker -->) so subsequent pushes update the existing comment in place rather than stacking new ones.

Triggers: pull_request filtered on paths: [".agents/skills/**", ".github/workflows/agent-skills-ci.yml"] (the .agents/skills/** glob covers the moved agent-skill-kit-commons/packages/** subtree, so no separate filter entry is needed). Permissions: contents: read, pull-requests: write — the minimum needed to comment.

Action pins are all majors (@v4, @v5, @v7); never @main. The security auditor flags @main refs as A030_HOST_PATH_LEAK-adjacent, so the convention is enforced by the toolkit itself.

Pre-commit hooks

The manifest at .pre-commit-hooks.yaml exposes four hooks, one per CLI verb (validate, lint, audit, deps). All hooks use language: system and shell out to the mjs CLI — staying single-runtime in the inner loop avoids paying the parity overhead on every commit.

The local config at .pre-commit-config.yaml consumes the manifest so the suite runs its own hooks against itself. Local install:

pip install pre-commit
pre-commit install

After install, any git commit touching .agents/skills/** runs validate, lint, audit, deps against the entire skill set. pass_filenames: false is critical — the CLI walks the tree itself; without it, pre-commit would replace the args with the changed file paths and break the recursive scan.

Inspect / extend

To add a new gate (e.g., a custom organisation-specific rule):

  1. Copy a hook entry in .pre-commit-hooks.yaml, point entry: at your new tool, keep pass_filenames: false.
  2. Add the matching step to the gate job in the workflow YAML.
  3. Run bash .agents/skills/agent-skill-kit-commons/scripts/test-workflow.sh locally — it parses the YAML, audits for security findings, and confirms all action refs stay pinned to majors.

Self-test driver

.agents/skills/agent-skill-kit-commons/scripts/test-workflow.sh runs offline sanity checks (YAML parse, audit clean, action-ref pinning) and optionally invokes act to run the workflow locally inside a Docker runner. If act is not installed, the script prints a manual verification checklist.

Reference

Full specification: see the canonical spec at ../../../docs/agentskills.io.md.

04 同仓库更多 Skills

carlosmarte
carlosmarte/ai-agent-artifacts

validation_handoff

Forces the agent to conclude its response by generating a strict validation checklist and outlining pending actions, focusing heavily on defensive execution and edge-case testing.

★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

project-ployglot-project-scafford

Scaffold a polyglot library project as TypeScript + Python twin packages under `packages/ts/` + `packages/py/`, with a shared `SPEC.md`, cross-language `tests/parity/fixtures.json`, side-by-side `examples/sdk/` + `examples/api/` documentation, per-package `Makefile`, and a root orchestrator that exposes `make ci`. Open-source friendly — no organization-specific paths or scopes baked in. Use when starting a new polyglot library, porting a single-language library to a twin, or auditing/regularizing an existing two-language repo against the canonical layout.

★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

playwright-ui-locator

Auto-heal Playwright tests after a frontend developer changes a div's class, id, or other selector. Catches a failing Playwright test, captures the old vs new DOM tree, finds the element that drifted, derives the most stable replacement locator, and proposes the fix as a GitHub pull request (confident heals) or files a GitHub issue (ambiguous / element-removed cases) — never editing the working tree directly. Trigger when Playwright tests fail with "locator resolved to 0 elements", "Timeout waiting for selector", or after a UI refactor / class rename / Tailwind cleanup broke previously-passing tests.

设计师代码审查测试与质量
★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

org-learn-context-window

Distill the current conversation into a reusable command or skill artifact. Use when the user wants to capture a workflow they just executed (create a reusable slash command) or formalize a resolution/mistake/correction into a reusable skill so the same class of issue never recurs.

Skill与智能体开发
★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

org-agent-skill-creator

Scaffold and validate scope-aware agent skills (company, enterprise, org, team, project, application). Use when the user asks to create a new agent skill, generate a SKILL.md file, scaffold a skill directory, or validate that existing skill directories meet SKILL_SPEC.md (frontmatter, naming rules, structure, scope/tier).

Skill与智能体开发
★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

app-workshop-session-pdf-recap-next

Extract content from a workshop session PDF and produce a structured recap focused on (1) what was learned, (2) next steps, and (3) possible enhancements. Ingests a single PDF file path, parses session material (slides, transcripts, exercises, Q&A), and emits a Markdown report with Learning Recap, Next Steps, and Enhancement Opportunities sections with page-level traceability. Use when the user asks to "summarize a workshop", "recap a training PDF", "pull next steps from a session deck", or provides a workshop/seminar/tutorial PDF and wants a learn-and-act summary.

文档处理
★ 0