Benchmark Checklist
Benchmark Checklist is an agent skill (a SKILL.md file) from backnotprop/pstack. Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. It works with Claude Code, Codex, Cursor and OpenCode and has 4,285 GitHub stars across a repository of 5 listed skills.
github.com/backnotprop/pstack/skills/benchmark-checklist (opens in a new tab)
Data as of from the GitHub API and skills.sh; description from the skill's SKILL.md. Report an error
Add this skill
Claude
Claude Code loads skills from ~/.claude/skills/ (all projects) or .claude/skills/ (one project):
git clone --depth 1 https://github.com/backnotprop/pstack.git
cp -r pstack/skills/benchmark-checklist ~/.claude/skills/benchmark-checklist # personal, or .claude/skills in a projectIn the Claude apps, zip the benchmark-checklist folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).
ChatGPT / Codex
Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:
git clone --depth 1 https://github.com/backnotprop/pstack.git
cp -r pstack/skills/benchmark-checklist .agents/skills/benchmark-checklist # repo; ~/.agents/skills for all projectsStandalone skills also load in the ChatGPT desktop app.
Cursor
Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:
git clone --depth 1 https://github.com/backnotprop/pstack.git
cp -r pstack/skills/benchmark-checklist .cursor/skills/benchmark-checklist # project; ~/.cursor/skills for all projectsSource (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)
What this skill does
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured. Use this when you produce a performance number: a PR's before and after, a regression claim, a hillclimb harness, or a library or config choice. Answer each question with evidence from a run, not a guess about the code.
When it triggers
- Use when you run a benchmark or report a speedup or regression you measured.
More skills in backnotprop/pstack
5 skills are listed from this repository.
Similar skills
More testing & qa skills
Observal Ops
AgenticResourceRegistry/AgenticResourceRegistry
Inspects Observal traces, sessions, rankings, feedback, telemetry health, logs, and Agent insight reports.
Active · last commit Nov 14, 2026
Testing & QAPythonMeta Tags Optimizer
nowork-studio/notfair-plugin
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate.
Maintained · last commit Nov 13, 2026
Testing & QAFix Merge Conflicts
michael-denyer/pstack-claude
Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution.
Active · last commit Nov 13, 2026
Testing & QAJavaScriptMirrord CI
metalbear-co/mirrord
Help users set up mirrord in CI pipelines for testing against real Kubernetes environments.
Active · last commit Nov 15, 2026
OfficialTesting & QARustAPI Fuzzing Bug Bounty
zebbern/claude-code-guide
This skill should be used when the user asks to "test API security", "fuzz APIs", "find IDOR vulnerabilities", "test REST API", "test GraphQL", "API penetration testing", "bug bounty API testing"…
Maintained · last commit Nov 14, 2026
Testing & QAPythonHTML Wireframe
plannotator/effective-html
Direct-invocation specialist for low-fidelity, self-contained HTML wireframes that test information hierarchy, content, navigation, task flow, and responsive structure before visual design.
Maintained · last commit Oct 31, 2026
Testing & QAHTML
How do I install the Benchmark Checklist skill?
Copy the benchmark-checklist folder (the one containing SKILL.md) into ~/.claude/skills/ for Claude Code, .agents/skills/ for Codex or .cursor/skills/ for Cursor. The agent picks it up automatically when a task matches its description.
Is the Benchmark Checklist skill free?
Yes. The repository is open source under the MIT license.
Is Benchmark Checklist maintained?
The repository's most recent commit was on Nov 15, 2026. appsgit only lists skills from repositories with a commit in the last six months.