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.
49,409 skills from 2,375 repositories · updated 8 hours ago
48,362 skills
- beta-program-managementrampstackco/claude-skillsRunning closed and open betas that produce real signal. Beta participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional feedback loops, clear graduation criteria). Triggers on beta program, alpha test, beta cohort, beta participant, beta feedback, beta to GA decision, design partner, early access program, closed beta, open beta, RC release. Also triggers when a feature is approaching launch and the team needs structured pre-GA validation, when prior betas produced noise rather than signal, or when the team has soft-launched before but wants more structured feedback this time.TestingNo warnings★ 1K↓ —
- ceo-advisorUpdatedalirezarezvani/claude-skillsCEO and founder advice: company strategy, board and investor management, fundraising, org design, culture. Use whenever a CEO asks how to run the company, handle investors or board, or make a big bet.DesignNo warnings★ 29.2K↓ —
- agentlas-uploadagentlas-ai/Agentlas-OSUse when the user types /agentlas-upload, /agentlas upload, $hephaestus-upload, or /hep-upload to scan, gate, and publish an agent/team package to Agentlas Cloud (private) or Agentlas Hub (public).OtherNo warnings★ 1.6K↓ —
- hep-searchagentlas-ai/Agentlas-OSSearch Agentlas Cloud and Hub agent candidates without invoking.OtherNo warnings★ 1.6K↓ —
- monitoring-and-alertingrampstackco/claude-skillsDesign and run a monitoring system for a website or web app. Use this skill when setting up uptime checks, defining SLOs, configuring error tracking, choosing what to alert on, designing on-call rotations, or fixing alert fatigue. Triggers on monitoring, alerts, uptime, SLO, SLA, error rate, on-call, pager, alert fatigue, observability, dashboards, what should we monitor. Also triggers when an incident reveals a gap in monitoring.DevOpsNo warnings★ 1K↓ —
- agent-team-designagentlas-ai/Agentlas-OSUse when designing a new multi-agent team, visible agents folder, role boundaries, handoff flow, PM Soul, Memory Curator, Policy Gate, or evaluation role. Use for agent-team repo creation even when the user only says they want a meta-agent or agent operating system.DesignNo warnings★ 1.6K↓ —Also in 1 other repo
- cloudbaseNewTencentCloudBase/CloudBase-AI-ToolkitUse when the user builds, deploys, debugs, or troubleshoots anything on 腾讯云开发 CloudBase / 云开发 / TCB / 微信云开发 — Web, 微信小程序, uni-app, 原生 App. Triggers on: 建站, 页面, 表单, 后台, 原型, 登录, 注册, 鉴权, 数据库, 集合, 建表, 云函数, 云托管, 云存储, 静态托管, 上传, 部署, 上线, 域名, 日志, 报错, 巡检, 大模型, AI 对话, 流式输出, 智能体, 小程序. This is an entry skill: it routes the task to the right CloudBase MCP tool and then pulls the detailed recipe from the CloudBase MCP knowledge base. Do NOT use for non-CloudBase stacks or self-hosted backends.DevOpsNo warnings★ 1.2K↓ —
- runtime-adaptersagentlas-ai/Agentlas-OSUse when creating Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical agent core. Use whenever a generated repo needs multiple AI runtimes without duplicating instructions.EngineeringNo warnings★ 1.6K↓ —
- refactoring-guruciembor/agent-rules-booksApply Refactoring.Guru-inspired rules when diagnosing code smells, choosing refactoring techniques, and stopping cleanup before uncontrolled redesign.EngineeringNo warnings★ 3.2K↓ —
- agentlas-networkagentlas-ai/Agentlas-OSUse when the user types /agentlas-network, /agentlas network, $hephaestus-network, or /hep-network to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams.OtherNo warnings★ 1.6K↓ —
- frontend-component-buildrampstackco/claude-skillsBuild production-ready frontend components with accessible markup, sensible props, defined states, and tested behavior. Use this skill whenever the user wants to build a component from scratch, refactor an existing one, design a component API, or implement a UI element with proper states and accessibility. Triggers on build a component, create a button, create a modal, create a form input, component API, props design, component states, refactor component, accessible component. Also triggers when implementing UI from a design that needs to be reusable.DesignNo warnings★ 1K↓ —
- gentle-ai-tui-designNewGentleman-Programming/gentle-shellTrigger: terminal UI design, TUI redesign, Gentle Shell look, IDE in a terminal, sidebar/status bar polish, critique TUI. Design, critique and refine terminal UIs with visual proof.DesignNo warnings★ 1.5K↓ —
- onboarding-wizard-designrampstackco/claude-skillsDesigning first-run product onboarding wizards that get users to the ah-ha moment without overwhelming them. Step architecture, progressive disclosure, escape hatches, completion incentives, drop-off measurement. Honest about tutorial-overload (dump everything upfront), skip-friendly-empty (skipped onboarding leads to abandoned product), and earned-progressive-disclosure (right things at the right moments) patterns. Triggers on onboarding wizard, product onboarding, first-run experience, signup flow, activation flow, FRX, time-to-value, ah-ha moment design. Also triggers when activation rates are low, when users skip onboarding and never return, when onboarding flows are being scoped for the first time, or when audience research shows users not finding key features.DesignNo warnings★ 1K↓ —
- agentlas-packagingagentlas-ai/Agentlas-OSUse when converting, repairing, or packaging an existing local or external agent/team into Agentlas architecture for local install, Agentlas import, Codex plugin use, Claude adapter use, or open-source release.PlanningNo warnings★ 1.6K↓ —
- cn-prd-reviewmohitagw15856/pm-claude-skillsPrepare for and run a product requirements review (需求评审 / PRD 评审会) the way Chinese internet teams do it: a pre-read the engineers, testers and designers can challenge, the questions each role will ask, the meeting run sheet and a written conclusion (通过 / 有条件通过 / 不通过). Use when asked 帮我准备需求评审, PRD 评审会怎么开, 评审前检查一下我的 PRD, 研发会问什么问题, or prepare my requirements review in Chinese. Produces a readiness check of the PRD, a role-by-role question bank with answer points, a 60-minute run sheet, and the review minutes template with the conclusion and follow-ups.PlanningNo warnings★ 1.5K↓ —
- asc-ad-hoc-distributionrorkai/app-store-connect-cli-skillsPrepare, publish, resume, and verify private iOS release-testing installs with asc distribute. Use when distributing an IPA to registered devices outside TestFlight, reconciling ad hoc profiles, publishing through caller-owned S3-compatible storage, or diagnosing a resumable private distribution run.MarketingNo warnings★ 1.1K↓ —
- competitor-ad-intelligencegooseworks-ai/goose-skillsScrape competitor ads from Meta, TikTok, Google, and LinkedIn ad libraries, analyze creative patterns (hooks, formats, CTAs), reverse-engineer landing page funnels, and produce a strategic teardown with vulnerability analysis and counter-play recommendations. Use when you need to understand the competitive ad landscape, find new creative directions, or identify weaknesses in a competitor's paid strategy.MarketingNo warnings★ 1.3K↓ —
- os-ask-simplekharmanskyi/open-stepsALWAYS invoke this skill before asking the user any technical question or offering options, and whenever they ask to be asked in plain words - "ask simple", "ask me simply", "ask me in plain words" - in any language. ALWAYS invoke it too when the user asks for your view on a technical choice: whether it is worth doing, more than the problem needs, or replaceable by something simpler, and which option you would take. Invoke it even when the code makes the answer look obvious: the checks are what make the answer more than a guess. Rewrites the question in plain words and always ends with one marked recommendation. A structural choice first passes six checks, shown as a table: effort now, simpler substitute, extra work later, lock-in, over-engineering, easy to undo. Doing nothing is always weighed.EngineeringNo warnings★ 1.3K↓ —
- csrdSushegaad/Claude-Skills-Governance-Risk-and-ComplianceExpert CSRD (Corporate Sustainability Reporting Directive, EU 2022/2464) compliance advisor. Use this skill whenever a user asks about CSRD, European Sustainability Reporting Standards (ESRS), double materiality assessment, sustainability reporting obligations, ESG disclosure, CSRD scope and thresholds, value chain reporting, XBRL digital tagging, third-party assurance, CSRD gap assessments, CSRD implementation timelines, ESRS E1–E5 environmental standards, ESRS S1–S4 social standards, ESRS G1 governance, the 2026 Omnibus scope change (Directive (EU) 2026/470, 1,000+ employees) and revised/simplified ESRS (July 2026), CSRD vs GRI/TCFD/SASB alignment, or any EU corporate sustainability reporting question. Trigger even if the user only mentions "ESG reporting Europe", "sustainability disclosure EU", or "non-financial reporting".FinanceNo warnings★ 1K↓ —
- generate-release-noteshuytieu/COG-second-brainGenerate categorized release notes from any source (GitHub, Linear, Jira, or manual input) with optional publishingProductivityNo warnings★ 1.3K↓ —Also in 1 other repo
- tisaxSushegaad/Claude-Skills-Governance-Risk-and-ComplianceExpert TISAX (Trusted Information Security Assessment Exchange) advisor for the automotive supply chain — the ENX/VDA assessment regime that OEMs like VW, BMW, and Mercedes-Benz require from suppliers and service providers. Covers the VDA ISA 6 catalogue (current through 2026) and the ISA2027 transition (published July 1, 2026; mandatory for assessments ordered from January 1, 2027), assessment levels AL1/AL2/AL3, all 12 assessment objectives/labels (Confidential, Strictly Confidential, High/Very High Availability, Proto Parts/Vehicles, Test Vehicles, Proto Events, Data, Special Data), maturity scoring (0–5, target 3, cutback rules), the ENX portal process, scoping, audit-provider selection, corrective action plans and the 9-month window, 3-year label validity, and ISO 27001 mapping. Use for any TISAX, VDA ISA, ENX, automotive information-security assessment, prototype protection, or OEM supplier-security requirement question — gap assessments, label selection, readiness, and audit prep.SecurityNo warnings★ 1K↓ —
- the-pragmatic-programmerciembor/agent-rules-booksApply Hunt and Thomas-inspired pragmatic programming rules when improving engineering judgment, feedback loops, DRY knowledge, orthogonality, automation, or adaptability.OtherNo warnings★ 3.2K↓ —
- itarSushegaad/Claude-Skills-Governance-Risk-and-ComplianceExpert ITAR compliance advisor for US defense contractors, exporters, and manufacturers. Use this skill for any question about 22 CFR Parts 120-130, the United States Munitions List (USML), DDTC registration, export license applications (DSP-5/73/94), Technical Assistance Agreements (TAA), Manufacturing License Agreements (MLA), brokering regulations (Part 129), deemed export rules for foreign nationals, technology control plans, voluntary disclosures, violation mitigation, jurisdiction determination (ITAR vs EAR), or US Munitions List category scoping. Trigger even if the user doesn't say "skill" — any ITAR or US defense export control question should use this skill.LegalNo warnings★ 1K↓ —
- 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↓ —
03-ref-hallucination-arena
agentscope-ai/OpenJudge
ScienceUpdated 22 hours ago
From the author
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
Install
npx skills add agentscope-ai/OpenJudge --skill 03-ref-hallucination-arena -a claude-code
Installs to .claude/skills/03-ref-hallucination-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