skill-tester Claude Code subagentA

skill-tester from luongnv89/skills is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.

Install it, pinned
mdr add luongnv89/skills/.claude/agents/skill-tester.md@git:20260204.88ec09c

Pins git:20260204.88ec09c in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
Claude Code subagent
Repository
luongnv89/skills
Path
.claude/agents/skill-tester.md
Versions recorded
1
Latest version
git:20260204.88ec09c, committed Feb 4, 2026
Size
493 bytes
Repository stars
147
License
MIT

Tests skill functionality by simulating usage scenarios and validating outputs.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

You are a skill tester. For each skill:

1. Read the SKILL.md and understand its purpose
2. Identify the expected triggers from the description
3. Simulate realistic user prompts that should invoke the skill
4. Verify any bundled scripts work correctly
5. Check that referenced files exist

Report issues found and suggest fixes.

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add luongnv89/skills/.claude/agents/skill-tester.md@sha256:cb919ffbbda0f698

The line at the top of this page pins the label git:20260204.88ec09c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_hd25gvgh52bunh7w.svg)](https://markdownregistry.com/a/art_hd25gvgh52bunh7w)

1 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in luongnv89/skills/.claude/agents/skill-tester.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of skill-tester.md from somewhere else? Ask it: where did my skill-tester.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Feb 4, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260204.88ec09c latest2026-02-04 88ec09c 493 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (493 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

luongnv89/skills · 147 stars · license MIT · pushed 2026-11-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hd25gvgh52bunh7w
GET https://markdownregistry.com/api/v1/resolve?ref=luongnv89/skills/.claude/agents/skill-tester.md
GET https://markdownregistry.com/api/v1/blob/cb919ffbbda0f6983b6554d72afd01d2ceac180aaf61995e45a736b10b51ab05

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: which agent file does what.

More from luongnv89/skills

skill-documenter Claude Code subagent
luongnv89/skills · .claude/agents/skill-documenter.md · Generates concise documentation for skills, focusing on usage examples and trigger phrases
git:20260204.88ec09c · audit A · 147 stars
skill-packager Claude Code subagent
luongnv89/skills · .claude/agents/skill-packager.md · Validates and packages skills into distributable .skill files
git:20261106.cb310ef · audit A · 147 stars
skill-reviewer Claude Code subagent
luongnv89/skills · .claude/agents/skill-reviewer.md · Reviews skill files for quality, best practices, and adherence to skill creation guidelines
git:20261106.cb310ef · audit A · 147 stars
AGENTS.md AGENTS.md file
luongnv89/skills · AGENTS.md
git:20261106.cb310ef · audit A · 147 stars
CLAUDE.md CLAUDE.md file
luongnv89/skills · CLAUDE.md
git:20261001.c1c53b9 · audit B · 147 stars
agent-profile SKILL.md skill
luongnv89/skills · extras/agent-profile/SKILL.md · Run a task with a saved agent profile (harness, model, thinking level) built only from what this machine has installed…
v1.1.0 · audit A · 147 stars
ai-job-scout SKILL.md skill
luongnv89/skills · extras/ai-job-scout/SKILL.md · Find open AI engineering jobs that fit a candidate, verify location and apply links, and assess each employer's…
v1.2.2 · audit A · 147 stars
appstore-assets SKILL.md skill
luongnv89/skills · extras/appstore-assets/SKILL.md · Generate App Store screenshots, header/search images and looping videos for iPhone, iPad, Mac from code or a landing…
v1.4.1 · audit A · 147 stars
appstore-review-checker SKILL.md skill
luongnv89/skills · extras/appstore-review-checker/SKILL.md · Audit iOS/macOS apps against App Store Review Guidelines before submission, with evidence-backed verdicts and fixes…
v1.7.1 · audit A · 147 stars
aso-marketing SKILL.md skill
luongnv89/skills · extras/aso-marketing/SKILL.md · Optimize App Store and Google Play listings via a 7-phase, plan-approval-gated ASO workflow: keywords and rank…
v1.6.1 · audit A · 147 stars
brand-name-checker SKILL.md skill
luongnv89/skills · extras/brand-name-checker/SKILL.md · Check product and brand names for conflicts across trademarks, domains, social handles, and package registries. Returns…
v1.7.0 · audit A · 147 stars
codebase-modernizer SKILL.md skill
luongnv89/skills · extras/codebase-modernizer/SKILL.md · Audit a stale, inherited, or messy codebase — deps, bugs, security, tests, CI, docs, UI/UX — then emit a phased…
v1.5.2 · audit A · 147 stars

Every file in luongnv89/skills

Other files named skill-tester

skill-tester SKILL.md skill
borghei/claude-skills · engineering/skill-tester/SKILL.md · Validate and score Claude Code skill packages for quality, completeness, and best-practice compliance. Tests Python…
v1.1.0 · audit A · 1,156 stars
skill-tester SKILL.md skill
ivuorinen/skills · .claude/skills/skill-tester/SKILL.md · Runs TDD pressure scenarios against a skill before and after it is written, proving the skill actually changes agent…
git:20260907.99db6c5 · audit A · 4 stars

Browse by kind, by grade A, or by owner.