AGENT SKILL

skill-check

Comprehensive testing and validation of Claude skills. Use this skill whenever the user wants to test, validate, audit, or quality-check a skill — whether they say "test my skill", "check this skill works", "validate my skill", "run skill-check", or anything similar. Also trigger when the user asks things like "does this skill handle edge cases?", "what's wrong with my skill?", "find problems in my skill", "is this skill secure?", "does my skill follow best practices?", or "how robust is this skill?". Even if they just say "check this" and point at a skill directory, use skill-check. This skill covers triggering tests, output quality tests, input/output contract validation, script execution checks, security review, best practices auditing, and multi-file skill analysis. Do NOT use for creating or editing skills (that's skill-creator) — skill-check is purely about testing and reporting on existing skills.

License 许可
MIT
所属仓库
bg-szy/TOP-SKILLS
最近更新
2026-11-15
Stars
★ 6
Forks
0

01 前言 Front Matter

name
skill-check
license
MIT
description
Comprehensive testing and validation of Claude skills. Use this skill whenever the user wants to test, validate, audit, or quality-check a skill — whether they say "test my skill", "check this skill works", "validate my skill", "run skill-check", or anything similar. Also trigger when the user asks things like "does this skill handle edge cases?", "what's wrong with my skill?", "find problems in my skill", "is this skill secure?", "does my skill follow best practices?", or "how robust is this skill?". Even if they just say "check this" and point at a skill directory, use skill-check. This skill covers triggering tests, output quality tests, input/output contract validation, script execution checks, security review, best practices auditing, and multi-file skill analysis. Do NOT use for creating or editing skills (that's skill-creator) — skill-check is purely about testing and reporting on existing skills.
allowed-tools
Bash Read Write

02 资源文件 4

03 SKILL.md 正文

SkillCheck — Comprehensive Skill Testing

SkillCheck audits an entire skill directory, understands every moving part, and generates targeted tests to verify the skill works as advertised. It doesn't just check "does it roughly work" — it tests every aspect: triggering, input handling, output quality, script correctness, security, best practices, and resource integrity.


How it works

Three phases: Discover → Test → Report. Discovery is always required. Testing depth depends on what the user wants. Reporting adapts to what was found.

Depth What it covers
Quick Static analysis — structure, syntax, integrity, security, best practices
Standard Static + script execution + happy-path I/O + eval regression
Deep Everything — edge cases, mock files, e2e workflows, stress

If the user doesn't specify, default to Standard — it catches real functional problems without the time investment of Deep. If they seem in a hurry, go Quick. If they mention thoroughness, edge cases, or "test everything", go Deep.

For a worked example of a Standard Check from start to finish, see references/example-run.md.


Gotchas

  • The evals.json format must match the skill-creator schema exactly (see references/eval-schema.md). Don't invent a new format — compatibility with skill-creator's benchmarking tools is the whole point.
  • Mock file generation for binary formats (DOCX, XLSX, PPTX, PDF, images) requires third-party Python packages that may not be installed. Always check availability before generating and fall back to text-based equivalents if installation fails. See references/mock-files.md for the dependency list.
  • Cross-reference mismatches between SKILL.md and scripts are often the root cause of multiple downstream test failures (script execution fails, eval regression fails, I/O tests fail — all for the same reason). Identify and report the root cause rather than listing each symptom as a separate unrelated failure.
  • Best practice scores are advisory and reported separately — do not add them to the main pass/fail verdict percentage. A skill can be functionally perfect but structurally messy, and the report should reflect that distinction.
  • Security review runs before script execution for a reason — if Critical security issues are found in scripts, warn the user before executing them at Standard or Deep depth. Don't silently run code you've just flagged as dangerous.
  • Incomplete skills (TODOs, stubs, placeholder text) need a progress report, not a wall of failures. It's easy to mechanically run the standard flow and produce 15 failures that all say "this doesn't exist yet" — that's not useful. Read references/incomplete-skills.md and reframe.
  • On Claude.ai without subagents, end-to-end tests run sequentially in shared context. This means earlier test results can influence later tests — an agent that just discovered a cross-reference bug might "know" to use the correct arguments on the next test. Keep this in mind when interpreting e2e results.
  • The frontmatter name field must match the parent directory name per the Agent Skills spec. This is easy to miss because many platforms will still load the skill with a mismatch — but others won't, making it a silent portability bug.
  • Report sections should be collapsed when empty — a Quick Check on a minimal skill should produce 5 sections, not a 12-section skeleton full of "N/A". See references/report-format.md for collapsing rules.

Phase 1: Discover

Find the skill, scan it, understand what it contains, and decide how to test it.

Find the skill

If the user gives a specific path, use it. If not, read references/finding-the-skill.md to locate the skill from conversation context or common locations.

Scan the directory

Read the entire skill directory, not just SKILL.md. Categorize every file:

Category What to look for
Core SKILL.md — the main instructions file
Scripts scripts/ — executable code (Python, Bash, JS, etc.)
References references/ — documentation loaded into context as needed
Assets assets/ — templates, icons, fonts, images used in output
Examples Any example input/output files, sample data
Config Package files, requirements, dependency lists
Evals evals/ — existing test cases (if any)

Record a manifest — you'll reference this throughout testing.

Parse the SKILL.md

Extract from the frontmatter and body:

  • Name and description — what it does and when it should trigger
  • Declared inputs — file types, formats, schemas (pay close attention to explicitly named extensions, column names, data structures)
  • Declared outputs — file types, formats, target paths, expected structures
  • Step-by-step workflows — numbered or ordered procedures
  • Tool/dependency requirements — libraries, CLIs, external tools
  • Conditional logic — branching paths
  • Constraints and rules — ALWAYS, NEVER, MUST directives
  • References to bundled files — when to read other files in the skill
  • Script invocations — exact commands including arguments and flags

Analyze supporting files

For each non-SKILL.md file:

  • Scripts: Read the code. Identify arguments, outputs, hardcoded paths, error handling, and dependencies. Pay special attention to argument parsing — you'll compare this against how SKILL.md invokes the script.
  • References: Skim for structure and purpose. Note if SKILL.md actually references them.
  • Assets: Note file types and whether they're referenced. Assets will be validated for integrity during testing — see references/quick-check.md.
  • Examples: Identify as input examples, output examples, or both — gold for test generation.
  • Evals: Read evals.json if present. See references/eval-schema.md for the format.

Present findings

Show the user: the file manifest, what the skill claims to do, declared inputs/outputs, immediate red flags, and whether evals were found.

If the skill appears incomplete (TODOs, placeholder text, missing referenced files, stub scripts), read references/incomplete-skills.md and adjust your approach — reframe as a progress report rather than a failure report.

Then ask which depth level they'd like (if they haven't already said).


Phase 2: Test

Read the reference file for the chosen depth level. It defines exactly which tests to run, in what order, and how to evaluate results:

  • Quick: references/quick-check.md — static integrity, asset validation, SKILL.md quality, cross-reference consistency, multi-skill dependencies, security review, and 22 best practice checks (references/best-practices.md)
  • Standard: references/standard-check.md — everything in Quick, plus eval regression (references/eval-schema.md), script execution with mock inputs (references/mock-files.md), happy-path I/O contract validation, and workflow tests
  • Deep: references/deep-check.md — everything in Standard, plus edge case inputs, end-to-end workflow simulation, triggering analysis, error recovery, and script robustness

Test plan (Standard and Deep only)

For Standard and Deep checks, present the test plan to the user before executing — they may know about domain-specific edge cases worth adding, or tests that aren't relevant. For Quick checks on simple skills, skip straight to running the tests.

Execution order

  1. Static tests first — fast, free, and may reveal issues that make later tests pointless or unsafe (security problems, broken cross-references)
  2. Eval regression next — the author's own tests are the most authoritative baseline
  3. Script tests — run with mock inputs, verify outputs
  4. I/O contract tests — generate mock files, run the skill, check results
  5. End-to-end tests last — slowest and most context-heavy; earlier tests may have already uncovered the issues they'd find

For each test, record: test ID, what was tested, pass/fail, evidence, and notes. Evidence is critical — it lets the user verify your judgment and makes the report actionable.

On Claude.ai (no subagents): Run tests sequentially. Save outputs to a workspace directory so the user can inspect them after the report.

With subagents: Static tests first, then dynamic tests in parallel. Use independent subagents for end-to-end tests — shared context lets earlier tests influence later ones, masking issues that would appear in a fresh invocation.


Phase 3: Report

Read references/report-format.md for the full template and collapsing rules. Key elements:

  • Summary card with pass/fail counts and verdict (HEALTHY / MOSTLY HEALTHY / NEEDS ATTENTION / CRITICAL)
  • Failed test details — what was tested, what happened, why it matters, suggested fix
  • Security findings — dedicated section if anything flagged, prominent banner for Critical findings
  • Best practices score — separate from the main verdict
  • Improvement suggestions — prioritized: Critical → Important → Nice to have

Only include report sections that have content. See the collapsing rules in references/report-format.md for which sections to skip at each depth level.

04 同仓库更多 Skills

bg-szy
bg-szy/TOP-SKILLS

serpmaven

Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.

★ 6
bg-szy
bg-szy/TOP-SKILLS

revnu-landing-page-audit

Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: "audit my landing page", "why isn't this page converting", "review my homepage", "my ads get clicks but no signups", "people bounce from the pricing page", "CRO review", "improve conversion rate", "is my hero section clear", "roast my landing page", "rewrite my headline", "what's wrong with this page", "landing page feedback", "make the signup page convert better". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.

★ 6
bg-szy
bg-szy/TOP-SKILLS

revnu-growth-context

Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents/revnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says "set up our marketing context", "who is our ideal customer", "write our ICP", "describe the product for marketing", "positioning doc", "what's our brand voice", "remember this about our customers", "log what we tried", "what have we learned from marketing", "we changed pricing, update the context", "update our growth notes", "summarize the business for the agent", "import my product-marketing.md", "start a growth doc", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.

★ 6
bg-szy
bg-szy/TOP-SKILLS

revnu-get-listed

Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: "best X" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says "get us listed", "which directories should we submit to", "how do we get into best-of lists", "why does ChatGPT recommend competitors and not us", "get mentioned in AI answers", "submit to awesome lists", "get on G2", "where are our competitors listed", "pitch listicle authors", "find backlink opportunities", "launch directories", "get into roundups", "Product Hunt alternatives", "where should we be listed", "get cited by Perplexity". Never submits, pays or posts without a yes. Works without a Revnu account.

★ 6
bg-szy
bg-szy/TOP-SKILLS

revnu-ai-readiness-audit

Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks "is my site ready for AI search", "audit my site for AI answers", "AEO audit", "GEO audit", "why doesn't ChatGPT quote our pricing", "make our pages citable by AI", "do I need llms.txt", "does schema help with ChatGPT", "check our structured data", "is our content visible without JavaScript", "AI SEO audit", "optimize our homepage for AI answers", "LLM SEO check", "why does AI get our product wrong", "fix our site for AI Overviews". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.

★ 6
bg-szy
bg-szy/TOP-SKILLS

proxy-troubleshooting

Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.

★ 6