AGENT SKILL

skill-tester-ci

Validates all CI skills in this repo. Checks Agent Skills spec compliance, gh-aw workflow compilation, permission correctness, and structural conventions. Use when CI skills have been added or modified and you want to verify they compile and conform before committing.

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
skill-tester-ci
description
Validates all CI skills in this repo. Checks Agent Skills spec compliance, gh-aw workflow compilation, permission correctness, and structural conventions. Use when CI skills have been added or modified and you want to verify they compile and conform before committing.

02 资源文件 1

03 SKILL.md 正文

Skill Tester CI

Validates all CI skills (*-ci) in this repo. Runs spec validation, compiles gh-aw workflows, and checks CI-specific conventions.

When to Use

  • After adding or modifying a CI skill
  • After upgrading gh-aw to a new version (API changes may break workflows)
  • Before committing CI skill changes
  • Before submitting the plugin for Anthropic review

Prerequisites

  • gh-aw CLI installed (gh extension install github/gh-aw)
  • python3 with pyyaml installed
  • quick_validate.py available at .claude/skills/skill-creator/scripts/

Checks

1. Anthropic Spec Validation

Run quick_validate.py on every CI skill:

for d in skills/*-ci/; do
  python3 .claude/skills/skill-creator/scripts/quick_validate.py "$d"
done

2. Workflow Example Compilation

Extract workflow blocks from each CI skill's references/workflow-example.md and compile with gh aw compile:

# Extract markdown code blocks with frontmatter
# Copy to temp .github/workflows/
# Run: gh aw compile

Pass criteria: Zero compilation errors. Warnings are reported but don't fail.

3. Permission Checks

CI workflows in strict mode must NOT use write permissions directly. Verify:

  • No issues: write (use safe-outputs: add-comment instead)
  • No pull-requests: write (use safe-outputs: create-pull-request-review-comment instead)
  • No contents: write unless the workflow creates files (eval-creator create mode)
  • Required read permissions present for declared toolsets

4. Structural Checks

Check Rule Severity
Has references/workflow-example.md Required for all CI skills Error
Workflow example has frontmatter block At least one ```markdown block with --- Error
Name matches folder Frontmatter name == directory name Error
Description mentions gh-aw CI skills should reference gh-aw Warning
Has corresponding interactive skill foo-ci should have a foo counterpart Warning

5. Cross-Workflow Validation

For workflows that use call-workflow:

  • Verify the target workflow exists and has workflow_call in its on: section
  • Verify the target's inputs match what the caller provides

Output Format

## CI Skill Test Results

**Date:** YYYY-MM-DD
**gh-aw version:** vX.Y.Z
**Skills tested:** N
**Passed:** N
**Compile errors:** N
**Spec failures:** N

### Compilation Results
- [skill-name]: ✓ compiled (N KB) | ✗ error: [message]

### Spec Results
- [skill-name]: ✓ valid | ✗ [error]

### Permission Issues
- [skill-name]: [issue]

Running

Invoke manually:

/skill-tester-ci

Or run the script directly:

bash skills/skill-tester-ci/scripts/run-tests.sh

What This Skill Does NOT Do

  • Does not test interactive skills (use skill-tester for those)
  • Does not execute workflows against real repos — only compiles them
  • Does not modify skills — reports findings only
  • Does not test workflow runtime behavior — compilation validates structure and permissions only

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1