suyoumo/ClawProBench

ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

823Stars on the repository
39Mods indexed here, across every type
14d agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

qa-review

25

suyoumo/ClawProBench

Skill Claude CodeCodex

QA review for code changes — test coverage analysis, edge case identification, test plan generation, regression detection, test health tracking over time.

not rated 823 14d ago A SkillSpector: pass 30 tokens original Apache-2.0

review-checklist

26

suyoumo/ClawProBench

Skill Claude CodeCodex

Pre-merge review checklist based on recurring AI reviewer feedback patterns.

not rated 823 14d ago A SkillSpector: warn 16 tokens original Apache-2.0

review-readiness

27

suyoumo/ClawProBench

Skill Claude CodeCodex

PR readiness dashboard — tracks which reviews have been completed per branch and gates merge decisions. Shows code review, tests, security, QA, and linting status.

not rated 823 14d ago A SkillSpector: pass 36 tokens original Apache-2.0

routine-advisor

28

suyoumo/ClawProBench

Skill Claude CodeCodex

Suggests relevant cron routines based on user context, goals, and observed patterns.

not rated 823 14d ago A SkillSpector: pass 19 tokens original Apache-2.0

security-review

29

suyoumo/ClawProBench

Skill Claude CodeCodex

Security audit for code changes and PRs — OWASP top 10, auth flows, data handling, secrets exposure, supply chain risks. Writes findings as actionable items.

not rated 823 14d ago A SkillSpector: pass 37 tokens original Apache-2.0

tech-debt-tracker

30

suyoumo/ClawProBench

Skill Claude CodeCodex

Detect and track technical debt from conversation and PR review comments. Resurface in weekly retros, promote to commitments when ready to fix.

not rated 823 14d ago A SkillSpector: pass 32 tokens original Apache-2.0

trader-setup

31

suyoumo/ClawProBench

Skill Claude CodeCodex

One-time onboarding for the financial trader workflow — real-time alerts, position-aware relevance, decision journaling with outcome tracking. After successful setup this skill is excluded from selection until the marker file is deleted.

not rated 823 14d ago A SkillSpector: pass 45 tokens original Apache-2.0

web-ui-test

32

suyoumo/ClawProBench

Skill Claude CodeCodex

Test the IronClaw web UI using the Claude for Chrome browser extension.

not rated 823 14d ago C SkillSpector: warn 19 tokens original Apache-2.0

agent-browser

33

suyoumo/ClawProBench

Skill Claude Code

Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.

not rated 823 14d ago A 51 tokens copy · 100% Apache-2.0

frontend-engineer

34

suyoumo/ClawProBench

Skill Claude CodeCodex

Pro frontend engineering discipline. Enforces build-test-verify workflow for every web project. Never declare done until the site is built, tested, responsive, accessible, and visually verified in a real browser. Use alongside vercel-cli for production-quality deployments.

not rated 823 14d ago A 54 tokens copy · 91% Apache-2.0

onecli-gateway

35

suyoumo/ClawProBench

Skill Claude CodeCodex

OneCLI Gateway: transparent HTTPS proxy that injects stored credentials into outbound calls. You MUST use this skill when the user asks you to read emails, check calendar, access GitHub repos, create issues, check Stripe payments, or interact with ANY external service or API. Do NOT use browser extensions or OAuth CLI…

not rated 823 14d ago A 81 tokens copy · 100% Apache-2.0

self-customize

36

suyoumo/ClawProBench

Skill Claude CodeCodex

Customize your own agent — add capabilities, install packages, add MCP servers, edit code or CLAUDE.md. Use when the user asks you to add a feature, install a tool, or modify how you work. For non-trivial code changes, delegate to a builder agent via createagent.

not rated 823 14d ago A 64 tokens copy · 94% Apache-2.0

vercel-cli

37

suyoumo/ClawProBench

Skill Claude CodeCodex

Deploy apps to Vercel. Use when asked to deploy, ship, or publish a web application, or manage Vercel projects, domains, and environment variables.

not rated 823 14d ago A SkillSpector: warn 38 tokens original Apache-2.0

welcome

38

suyoumo/ClawProBench

Skill Claude CodeCodex

Introduce yourself to a newly connected channel. Triggered automatically when a channel is first wired. Send a friendly greeting and brief overview of what you can do.

not rated 823 14d ago A 33 tokens copy · 91% Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: