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.
49,415 skills from 2,407 repositories · updated 2 hours ago
49,415 skills
- setupmicrosoft/power-platform-skillsUse when Process Intelligence needs building, explicit cloud/account/environment configuration, sign-in, connection diagnostics, or recovery from an authentication error.OtherNo warnings★ 1.1K↓ —
- design-system-compliancereticlehq/reticleCheck that the UI you actually rendered uses the design system, by reading computed styles in the running app against the project's design tokens. Catches hardcoded hex colors, off-palette backgrounds, invisible or unusable controls, and animations that never ran. Use after building or restyling a component, when a design review is wanted, when a UI looks slightly off but nobody can say why, or when a design system exists and nothing checks whether the code follows it.DesignNo warnings★ 1.2K↓ —
- product-skillsalirezarezvani/claude-skillsUse when a product request needs routing across the product-team skills (prioritization, OKRs, UX research, experiments, discovery, roadmaps), or to run the continuous discovery loop. Routes with product_goal_router.py and gates with discovery_cadence_tracker.py and ost_linter.py.DesignNo warnings★ 29.3K↓ —
- goose-product-photosgooseworks-ai/goose-skillsMake product photos (studio, lifestyle or on a model) of a brand's real products with GooseWorks in this chat. Start brand work with brand_knowledge_browse and follow the next_step in every answer.MediaNo warnings★ 1.3K↓ —
- aeofcakyon/claude-codex-settingsThis skill should be used when the user asks to "build an AEO strategy", "improve AI search visibility", "track buyer prompts", "analyze AI citations", or "plan content for answer engines". Apply an evidence-led answer engine optimization (AEO/GEO) feedback loop to any product or service, prioritizing discovery by buyers who have not heard of it.PlanningNo warnings★ 1.2K↓ —
- verify-language-switchreticlehq/reticleProve a language switch translates what the user sees, keeps what they had already typed, and is still in force after a reload. Use when i18n, a locale picker, a language menu or translation files were added or changed, when a string is suspected of staying in the old language or showing a raw translation key, or when a user reports losing their form or their language choice after switching or refreshing.OtherNo warnings★ 1.2K↓ —
- desktop-zeromohitagw15856/pm-claude-skillsClear the desktop that's become a hundred-icon guilt mosaic — the fast triage that empties it today, the honest read of what the desktop was being used for (it's a to-do list wearing icons), and the replacement systems that keep it clear. Use when asked clean up my desktop, my desktop has 200 files on it, why does my desktop keep filling up, or set up a clean-desktop habit. Produces the today-pass, the function-replacement mapping, and the two-minute weekly habit.OtherNo warnings★ 1.5K↓ —
- 00-arena-routeragentscope-ai/OpenJudgeUse when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.PlanningNo warnings★ 1.1K↓ —
- fix-what-i-pointed-atreticlehq/reticlePick up the bugs a human flagged by pointing at them in the running app, each arriving with the element, the note they typed, and the source file and line. Use when the user says they marked or flagged something, when starting a session on an app someone has been clicking through, when a designer or PM has left feedback in the UI, or when the user describes a problem as "that button there" without saying which file.DesignNo warnings★ 1.2K↓ —
- onboarding-croalirezarezvani/claude-skillsUse when activation, time-to-value or a first-run experience after signup needs work, before redesigning it. Finds the activation drop-off with activation_funnel_analyzer.py.MarketingNo warnings★ 29.3K↓ —
- commit-craftNewalirezarezvani/claude-skillsTurn a mix of changes into clean, reviewable commits with good messages, blocking staged secrets and .env files. Use whenever the user says commit this, wants to split work into commits, write a commit message, or is about to push.EngineeringNo warnings★ 29.3K↓ —
- orchestrating-agent-relayAgentWorkforce/relayThe canonical way to run agent-relay - self-bootstrap the local broker and autonomously spawn, monitor, and coordinate a team of worker agents without human intervention. Covers infrastructure startup, agent spawning, lifecycle monitoring, message-based reading via the relay MCP, and team coordination.DevOpsNo warnings★ 1.1K↓ —
- cloud-securityalirezarezvani/claude-skillsUse when checking AWS, Azure or GCP for security misconfigurations: IAM privilege escalation, public buckets, open security groups, IaC gaps. Runs cloud_posture_check.py and maps findings to MITRE ATT&CK.SecurityNo warnings★ 29.3K↓ —
- review-fix-signoff-loopAgentWorkforce/relayUse when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts, iteration-count reporting, PR signoff comments, and blocked-state handling.EngineeringNo warnings★ 1.1K↓ —
- meltdown-mapmohitagw15856/pm-claude-skillsBuild your personal early-warning system for meltdowns or shutdowns — your specific rising signs, the triggers that stack, what actually helps at each stage, and a plain plan you can hand to the people around you. Use when someone says 'my meltdowns come out of nowhere', 'help me not shut down', 'I need a plan for when I'm overwhelmed', or supports someone who melts down or shuts down. Produces a staged warning map, a per-stage response plan, and a shareable one-pager. A self-management tool — not a clinical or crisis service.ScienceNo warnings★ 1.5K↓ —
- stock-analysisalirezarezvani/claude-skillsAnalyze, research or value a listed stock or company (US, global, NSE or BSE) with verified data, ratios, scores and valuation. Use whenever asked if a stock is a buy, what it is worth, or how a company looks.FinanceNo warnings★ 29.3K↓ —
- scrapecreators-apigooseworks-ai/goose-skillsProvider reference for collecting public profiles, posts, comments, transcripts, trends, and ad-library data from major social platforms through ScrapeCreators. Use as a dependency of research workflows, not as the final user-facing deliverable.BrowserNo warnings★ 1.3K↓ —
- orchestrating-agent-relayAgentWorkforce/relayThe canonical way to run agent-relay - self-bootstrap the local broker and autonomously spawn, monitor, and coordinate a team of worker agents without human intervention. Covers infrastructure startup, agent spawning, lifecycle monitoring, message-based reading via the relay MCP, and team coordination.DevOpsNo warnings★ 1.1K↓ —
- improve-search-visibility-page-and-foundation-checkgooseworks-ai/goose-skillsStep of the improve-search-visibility playbook: audits site indexing, crawling, technical and page issues at the requested scope, or checks pages behind lost visibility questions. Run improve-search-visibility instead; not for direct use.BrowserNo warnings★ 1.3K↓ —
- improve-search-visibility-entity-footprintgooseworks-ai/goose-skillsStep of the improve-search-visibility playbook: checks the profiles answer engines read, plus local listings and reviews, against the brand's facts and writes corrections. Run improve-search-visibility instead; not for direct use.WritingNo warnings★ 1.3K↓ —
- replay-user-flowsreticlehq/reticleTurn a user journey you just clicked through into a saved regression check that re-runs deterministically, with no model in the loop and no test code to write. Use when you have driven the same flow twice, when the user wants regression coverage without a Playwright suite, when a refactor needs proving against every existing journey, or when re-verifying by hand is costing a full drive every time.TestingNo warnings★ 1.2K↓ —
- skill-fusionmohitagw15856/pm-claude-skillsFuse two skills from this library into one hybrid brief for a task that sits between them — the meta-skill. Use when a task straddles two skills (a PRD that's also a pitch; a postmortem that must double as a board update) and running them separately would produce two documents where one is needed. Produces the fused operating brief: combined structure, merged quality bar, precedence rules for where the parents disagree, and the fused output itself if input was provided.PlanningNo warnings★ 1.5K↓ —
- verify-unattendedreticlehq/reticleInstall, instrument and verify a web app end to end without pausing for a human. Use in an autonomous or goal-mode agent, in CI, or in any client that asks for approval on every command: it never says "restart your client" or "open a browser", because it takes a route that needs neither. Prefer the normal reticle skill when a human is present and can answer.BrowserNo warnings★ 1.2K↓ —
- creating-agent-skillsAgentWorkforce/relayUse when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the agentskills.io specification with frontmatter constraints, directory structure, and validation rulesPlanningNo warnings★ 1.1K↓ —
01-auto-arena
agentscope-ai/OpenJudge
TestingUpdated 12 hours ago
From the author
Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style evaluation.
Install
npx skills add agentscope-ai/OpenJudge --skill 01-auto-arena -a claude-code
Installs to .claude/skills/01-auto-arena/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyUses the networkLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance76
Maintenance100
Licence100
Adoption49
Files (1)
- SKILL.md