Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
17,218 skills from 571 repositories · updated 20 minutes ago
3,257 skills
- share-of-voiceindranilbanerjee/digital-marketing-proCalculate share of voice by script vs competitors in search, social and AI. "what's our share of voice"OtherNo warnings★ 906↓ —
- verify-claimsindranilbanerjee/digital-marketing-proVerify copy claims by script against evidence you give; without it, lists what needs proof. "can we back up these numbers"OtherNo warnings★ 906↓ —
- fix-github-issueAgnosticUI/agnosticuiFix a GitHub issue by number. Use when asked to fix GitHub issues.OtherNo warnings★ 831↓ —
- civitaiartokun/comfyui-mcpDiscover Civitai models with the BUILT-IN download_model action:"search_civitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).OtherNo warnings★ 860↓ —
- flux-txt2imgartokun/comfyui-mcpBuild Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patternsOtherNo warnings★ 860↓ —
- matter-intake-scoping-scott-margettslawve-ai/awesome-legal-skillsMatter scoping across the full pre-execution arc — organise client data into a structured brief, capture the agreed baseline, or reconstruct scope mid-flight. Use when making sense of client information before a proposal, scoping a new matter, running a kickoff, defining scope, mapping stakeholders, or inheriting a matter mid-flight. Trigger on: 'make sense of this', 'structure this for the proposal', 'scope this matter', 'new matter', 'kickoff', 'what are we doing', 'who are the stakeholders', 'what does success look like', 'matter setup', 'intake', 'I've inherited this matter', 'organise this client data'.OtherNo warnings★ 891↓ —
- serp-trackerindranilbanerjee/digital-marketing-proDeprecated; use rank-monitor --features for SERP features. "track SERP features"OtherNo warnings★ 906↓ —
- eval-suiteindranilbanerjee/digital-marketing-proEvaluate a batch of content in one run: ranked quality report, systemic issues. "score our whole content library"OtherNo warnings★ 906↓ —
- churn-riskindranilbanerjee/digital-marketing-proScore churn risk per segment by script, with tiered retention playbooks. "which customers are about to churn"OtherNo warnings★ 906↓ —
- what-ifindranilbanerjee/digital-marketing-proRun a quick what-if on 2-4 budget scenarios with revenue and ROI estimates. "compare two budget splits"OtherNo warnings★ 906↓ —
- crm-syncindranilbanerjee/digital-marketing-proSync contacts and deals with a connected CRM, deduped, approval-gated. "sync deals to Salesforce"OtherNo warnings★ 906↓ —
- aeo-auditindranilbanerjee/digital-marketing-proRun a one-time AEO audit of six AI answer engines, scored per surface. "check our AI search visibility"OtherNo warnings★ 906↓ —
- eval-contentindranilbanerjee/digital-marketing-proScore one piece via eval-runner on six dimensions with a fix list. Many pieces → eval-suite. "score this draft before it ships"OtherNo warnings★ 906↓ —
- helpindranilbanerjee/digital-marketing-proShow help with live plugin counts: getting started, which skill fits a goal, fixes. "what can this plugin do"OtherNo warnings★ 906↓ —
- recallindranilbanerjee/digital-marketing-proRecall past learnings for a channel or audience as a confidence-ranked playbook. "what worked last time"OtherNo warnings★ 906↓ —
- statusindranilbanerjee/digital-marketing-proShow DMP status for the active brand: profile, engagement progress, recent insights. "what brand am I on"OtherNo warnings★ 906↓ —
- verification-before-completioncoco-research/cocoUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysOtherNo warnings★ 961↓ —
- hreflang-checkindranilbanerjee/digital-marketing-proValidate hreflang, alternate-language link tags and x-default from pasted HTML or sitemaps, with fixes. "check our hreflang tags"OtherNo warnings★ 906↓ —
- cowork-setupindranilbanerjee/digital-marketing-proSet up DMP for team use in Cowork: sandbox check, Drive folders, saved routing. "set up DMP for my team in Cowork"OtherNo warnings★ 906↓ —
- anomaly-scanindranilbanerjee/digital-marketing-proScan connected platforms for anomalies against stored baselines, with likely causes. "why did our CPA spike"OtherNo warnings★ 906↓ —
- schedule-socialindranilbanerjee/digital-marketing-proSchedule social posts to connected platforms at best times, approval-gated. "schedule this post for Monday"OtherNo warnings★ 906↓ —
- amapnano-muse/nanoMusePlaces, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server. Use when the user asks how far, how long, how to get somewhere (car, transit, bike, foot), what is near a place, or about the weather in a Chinese city.OtherNo warnings★ 2.4K↓ —
- audience-profileindranilbanerjee/digital-marketing-proProfile 2-4 buyer personas as narrative documents: drivers, objections, journey. "create a buyer persona"OtherNo warnings★ 906↓ —
- ln-53-documentation-auditorlevnikolaevich/claude-code-skillsAudits documentation and comments for trust, coverage, consistency and freshness; read-only.OtherNo warnings★ 583↓ —
crack-setup
ethanplusai/codex-on-crack
From the author
Configure or change the approved worker models for codex-on-crack, inspect available models and compatibility, preview role files, or undo a setup. The user selects the lead in Codex. Setup preserves root settings, credentials, unrelated agents, and config.toml.
Install
npx skills add ethanplusai/codex-on-crack --skill crack-setup -a claude-code
Installs to .claude/skills/crack-setup/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Safety checks on SKILL.md
No warnings.
Why 87
Files (2)
- SKILL.md
- agents/openai.yaml