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.
48,743 skills from 2,355 repositories · updated 28 minutes ago
47,668 skills
- tanstack-startjezweb/claude-skillsBuild a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per project.DevOpsNo warnings★ 1.1K↓ —
- where-to-start-situation-savegooseworks-ai/goose-skillsStep of the where-to-start playbook: saves the founder's answers and the agreed first move with the brand, so later visits and other playbooks don't ask again. Run where-to-start instead; not for direct use.OtherNo warnings★ 1.3K↓ —
- fedrampSushegaad/Claude-Skills-Governance-Risk-and-ComplianceExpert guidance for FedRAMP certification and compliance under CR26 (FedRAMP Consolidated Rules for 2026). Use this skill whenever a user asks about FedRAMP authorization, ATO (Authority to Operate), cloud security for federal government, NIST SP 800-53 controls, CSP compliance, or any of the core FedRAMP document types: SSP, SAP, SAR, POA&M, CIS/CRM workbooks. Also trigger for questions about FedRAMP Certification Classes (A, B, C, D — new baseline labels: A = pilot/transitional, B = LI-SaaS/Low, C = Moderate, D = High, per NTC-0004), FedRAMP 20x (now the primary authorization pathway), OSCAL mandate (September 2026), 3PAO assessments, continuous monitoring (ConMon), gap assessments, system boundary definition, or architecture reviews for federal cloud. FedRAMP Ready retired July 28, 2026 (Legacy FedRAMP Ready). When in doubt, use this skill — it covers the full FedRAMP lifecycle from readiness through continuous monitoring.SecurityNo warnings★ 1K↓ —
- add-oneclinanocoai/nanoclawInstall or refresh OneCLI as NanoClaw's gateway provider. Use when setup selects OneCLI, an existing OneCLI-backed install is migrated to the gateway seam, or its runtime, approval bridge, setup, and agent guidance must be restored from the in-tree package.OtherNo warnings★ 31.1K↓ —
- agentlas-cloudagentlas-ai/Agentlas-OSUse when the user types /agentlas-cloud, /agentlas cloud, or /hep-cloud to staff only from the signed-in owner's private Cloud packages.OtherNo warnings★ 1.6K↓ —Also in 1 other repo
- clarify-question-loopagentlas-ai/Agentlas-OSUse when a meta-agent request is too ambiguous to safely generate, package, publish, or adapt without one to five targeted questions.OtherNo warnings★ 1.6K↓ —Also in 1 other repo
- browser-automationalirezarezvani/claude-skillsUse for browser automation, scraping, form filling or structured extraction from web pages. Builds scrapers with scraping_toolkit.py and form flows with form_automation_builder.py. Browser testing: playwright-pro.BrowserNo warnings★ 29.2K↓ —
- add-codexnanocoai/nanoclawUse Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongside or instead of Claude. ChatGPT subscription or OpenAI API key, vault-only via the selected gateway. Per-group via `ncl groups config update --provider codex`. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).PlanningNo warnings★ 31.1K↓ —
- api-docs-writermohitagw15856/pm-claude-skillsWrite clear, developer-facing API documentation. Use when asked to document an API endpoint, write API reference docs, create a developer guide, or turn a raw spec/Postman collection into documentation. Produces endpoint documentation with descriptions, parameters, request/response examples, and error codes.WritingNo warnings★ 1.5K↓ —
- senior-secopsalirezarezvani/claude-skillsUse for application security operations: security reviews, CVE remediation, hardening, secrets and auth, or SOC 2, PCI-DSS, HIPAA and GDPR checks. Scans with security_scanner.py, assesses CVEs with vulnerability_assessor.py and checks controls with compliance_checker.py.SecurityNo warnings★ 29.2K↓ —
- 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★ 29.2K↓ —
- 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★ 29.2K↓ —
- email-lifecyclegooseworks-ai/goose-skillsLifecycle email, SMS and push: audits the list and deliverability, then writes the flows this kind of business needs first, loadable as-is in your own tool, plus segments, cadence and this week's broadcasts. Never sends anything. Use when: set up my welcome and abandoned-cart emails; trial onboarding or waitlist launch emails; win back lapsed customers; plan this week's emails and texts; push notifications for my app; why are my emails going to spam; plan our Black Friday email and SMS sends; a send went wrong. Not for cold outreach to prospects — use write-outreach; not the editorial newsletter issue — use make-content; not the whole cross-channel Black Friday plan — use plan-campaign.ProductivityNo warnings★ 1.3K↓ —
- decision-loggeralirezarezvani/claude-skillsUse when logging a decision after a board meeting, reviewing past decisions or checking overdue actions. Keeps raw transcripts and approved decisions separately with decision_tracker.py.OtherNo warnings★ 29.2K↓ —
- 01-auto-arenaagentscope-ai/OpenJudgeAutomatically 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.TestingNo warnings★ 1K↓ —
- api-design-revieweralirezarezvani/claude-skillsUse for any PR or spec that adds or changes REST endpoints, before approving it. Lints conventions with api_linter.py, detects breaking changes with breaking_change_detector.py and scores the design with api_scorecard.py.DesignNo warnings★ 29.2K↓ —
- claude-authenticityagentscope-ai/OpenJudgeDetect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra packages beyond httpx. Use when the user wants to verify a Claude API key or endpoint, check if a third-party Claude service is authentic, audit API providers for Claude authenticity, test multiple models in parallel, or discover what system prompt a provider has injected.TestingNo warnings★ 1K↓ —
- changelog-generatoralirezarezvani/claude-skillsUse when cutting a release, writing CHANGELOG.md or deciding the next version from commits, before writing notes by hand. Lints commits with commit_linter.py, picks the semver bump with version_bumper.py and renders notes with generate_changelog.py.MediaNo warnings★ 29.2K↓ —
- dac-workflowbrycewang-stanford/Awesome-Journal-SkillsUse to plan a full ACM/IEEE Design Automation Conference (DAC) Research-Manuscript campaign backward from the mid-to-late-November manuscript deadline through the two-stage abstract-then-manuscript submission on Softconf, the winter review, the March notification, the April camera-ready and copyright for the ACM Digital Library, and the July conference in Long Beach — with the Engineering-Track and Late-Breaking-Results side calendars.ProductivityNo warnings★ 1.4K↓ —
- cell-fitbrycewang-stanford/Awesome-Journal-SkillsUse when triaging a study before any writing — stress-tests whether it clears Cell's bar (a complete, mechanistic, hypothesis-driven story with multiple converging lines of evidence) or belongs at a sibling. Use this first to decide Cell vs Molecular Cell vs Cell Reports vs Cell Reports Medicine before investing in framing or figures.TestingNo warnings★ 1.4K↓ —
- thesis-outlinemohitagw15856/pm-claude-skillsBuild a defensible thesis or dissertation outline — argument-first structure, chapter by chapter, with the through-line visible. Use when asked to outline my thesis, structure my dissertation, plan my capstone, or organize my research into chapters. Produces a full outline: the one-sentence thesis, chapter map with each chapter's job and claim, evidence allocation, and the risk register of weak links an examiner would probe.ScienceNo warnings★ 1.5K↓ —
- itcs-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when deciding what counts as evidence for an ITCS theory claim — proofs as the primary evidence, worked examples and separations that make a model concrete, and the rare, well-scoped illustrative computation or simulation — and how to keep any computational content checkable and subordinate to the mathematics.MediaNo warnings★ 1.4K↓ —
- nsdi-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the evaluation of an NSDI submission — choosing traces, testbeds, and deployment evidence, sizing scale and failure-injection experiments, picking baselines that fight back, and reporting tail behavior so networked-systems reviewers can see where the design wins, loses, and breaks.DevOpsNo warnings★ 1.4K↓ —
- codebase-onboardingalirezarezvani/claude-skillsUse when someone is new to a repo or a tech lead needs an architecture brief, before writing docs by hand. Maps the codebase with codebase_analyzer.py and produces onboarding docs.WritingNo warnings★ 29.2K↓ —
metric-design
agentscope-ai/OpenJudge
DesignUpdated 3 hours ago
From the author
Use when the user has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline. Also use when the user mentions grader selection, metric design, judge prompt engineering, rubric design, evaluation pipeline code, or "how to evaluate [X] automatically." Outputs executable OpenJudge pipeline code.
Install
npx skills add agentscope-ai/OpenJudge --skill metric-design -a claude-code
Installs to .claude/skills/metric-design/ · 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