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.
49,534 skills from 2,407 repositories · updated 3 minutes ago
48,435 skills
- add-mnemonnanocoai/nanoclawAdd persistent graph-based memory via mnemon. Agents recall past context before responding and remember insights after each turn.ProductivityNo warnings★ 31.1K↓ —
- kubernetes-operatoralirezarezvani/claude-skillsUse when building a Kubernetes operator or CRD (controller-runtime, kubebuilder, operator-sdk, KOPF), before writing the controller. Validates CRDs with crd_validator.py, lints reconcile loops with reconcile_lint.py and scores OperatorHub capability level.DevOpsNo warnings★ 29.3K↓ —
- imc-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning an ACM IMC campaign end to end, covering the choice between the two annual deadlines, backward planning from the target cutoff, the registration step, the One-Shot-Revision path across deadlines, availability shepherding, the camera-ready and dataset release, and the Replicability Track calendar.ProductivityNo warnings★ 1.4K↓ —
- cell-summarybrycewang-stanford/Awesome-Journal-SkillsUse to write Cell's Summary — a single unstructured paragraph of ≤ ~150 words that conveys the complete story, the mechanism, and the broad significance, quantified and readable by a general life-scientist. Late-stage polish.ProductivityNo warnings★ 1.4K↓ —
- multi-domain-brand-seokostja94/marketing-skillsWhen the user wants to optimize brand search for a company with multiple domains (e.g. parent company.com vs product.ai). Ensure the parent/company domain ranks first for brand queries. Also use when the user mentions "brand search," "multi-domain SEO," "company domain first," "parent vs product domain," "hub-spoke domain," "brand SERP control," or "differentiate company and product domains." For domain structure, use domain-architecture.MarketingNo warnings★ 1.1K↓ —
- hri-workflowbrycewang-stanford/Awesome-Journal-SkillsUse to plan an ACM/IEEE HRI campaign backward from the full-paper deadline through the abstract-then-paper two-step, the rebuttal, the program-committee meeting, camera-ready, and the March conference, coordinating the parallel alt.HRI, Late-Breaking Reports, video, and Student Design deadlines.ProductivityNo warnings★ 1.4K↓ —
- cell-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when deciding which cell-* sub-skill to invoke next, or when sequencing a manuscript from significance test through reviewer rebuttal for Cell (Cell Press). Routes — it does not replace — the specialized skills.ProductivityNo warnings★ 1.4K↓ —
- designhashgraph-online/awesome-codex-pluginsUse for UI, UX, visual hierarchy, frontend-design judgment, references, redesigns, and design critique when the user's Emulo taste should guide the task. Do not use for unrelated execution or marketing/social writing alone.DesignNo warnings★ 1.5K↓ —Also in 2 other repos
- vibe-knowledge-filmHeyChengC/vibe-knowledge-film抖音「Vibe知识大赏」式的无旁白知识短片：2–5 分钟、16:9、没有人声，观众读底部一行字幕，同时看屏上把这句话演出来。 核心是讲解设计：给每个概念找一个外行认得的形象，画得像它本身（不用点、线、圈代替），句子里说到什么屏上就是什么、动词真的发生； 提问、命名、结论不硬配图。全片由代码逐帧画出（Canvas + seek(t) + Playwright + ffmpeg）。 内含四条参考片的逐句拆解、六种画法、找形象的方法、分镜表格式、两套外观、渲染引擎和合成配乐。 用户说"做一条 vibe 知识大赏的视频""像《信息论·惊奇之学》《运气的形状》《超常刺激》《自指》那样的片子""代码直出的知识短片""没有旁白的字幕科普片""把这个概念直观地讲清楚"， 或者给了一个题目、一份文案要做成这种片子时使用。只做 16:9 横屏。有人声口播的讲解片不用这个。TestingNo warnings★ 1.1K↓ —
- icde-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an IEEE ICDE research-track submission for round choice, Microsoft CMT setup, conflict declarations, the IEEE 12-page format, single-blind requirements, supplemental-material availability, the June/November two-round calendar, desk-reject triggers, and final-week sequencing for a data-engineering systems paper.DataNo warnings★ 1.4K↓ —
- threat-detectionalirezarezvani/claude-skillsUse when hunting threats, sweeping IOCs or looking for anomalies in logs and telemetry. Ranks ATT&CK-mapped signals and z-score anomalies with threat_signal_analyzer.py.OtherNo warnings★ 29.3K↓ —
- nejm-ethicsbrycewang-stanford/Awesome-Journal-SkillsUse to confirm clinical ethics and research-integrity requirements for an NEJM submission — IRB/ethics-committee approval and informed consent per the Declaration of Helsinki, ICMJE conflict-of-interest disclosures and authorship criteria, the role-of-the-funding-source statement, and the ICMJE data-sharing statement.ScienceNo warnings★ 1.4K↓ —
- codebase-onboardingalirezarezvani/claude-skillsExplain an unfamiliar repo: architecture brief and onboarding docs. Use whenever someone is new to a codebase, asks how a project is structured or where to start reading.PlanningNo warnings★ 29.3K↓ —
- mobile-friendlykostja94/marketing-skillsWhen the user wants to optimize for mobile-first indexing or fix mobile usability. Also use when the user mentions "mobile-friendly," "mobile-first indexing," "mobile SEO," "responsive design," "mobile adaptation," "mobile viewport," "viewport meta," "touch targets," "font size mobile," "AMP," or "Accelerated Mobile Pages." For viewport meta, use page-metadata.DesignNo warnings★ 1.1K↓ —
- kdd-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning a KDD project calendar across the venue's two submission cycles per year, including cycle choice, abstract-then-paper deadline pairs a week apart, rebuttal capacity planning, the Resubmit-to-next-cycle loop, ADS evidence lead times, and ACM e-rights/TAPS camera-ready scheduling for SIGKDD.ProductivityNo warnings★ 1.4K↓ —
- agent-run-forensicsNewalirezarezvani/claude-skillsUse when asked why an agent did something, what a past session or run changed, whether tests really passed, or to verify a session summary. Answers from the recorded transcript, not memory, with trace_finder.py, trace_timeline.py and claim_checker.py.SecurityNo warnings★ 29.3K↓ —
- 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↓ —
- shotshashgraph-online/awesome-codex-pluginsGenerate, revise, translate, and manage App Store marketing screenshots and app icon candidates through the hosted Shots MCP tools. Use for App Store screenshot creation, app icon generation, ASO screenshot strategy, screenshot revisions, localization, App Store listing scraping, and public App Store screenshot inspiration. Do not use for generic image generation.BrowserNo warnings★ 1.5K↓ —
- ipsn-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an IPSN-lineage submission for HotCRP readiness, covering the IP-vs-SPOTS track choice, the ACM Primary Article Template and ≤12-page inclusive budget, the double-blind sweep for hardware/deployment papers, dataset/artifact links, and desk-reject triage — routed to the current successor (SenSys) call because IPSN no longer runs standalone.DevOpsNo warnings★ 1.4K↓ —
- tddhashgraph-online/awesome-codex-pluginsTest-first cycle and red-step evidence rule for skills that implement behavior a test can assert. Binds when the verification skill resolves a test command; defines what the red run must quote and when the cycle is skipped with a reason.TestingNo warnings★ 1.5K↓ —
- hri-camera-readybrycewang-stanford/Awesome-Journal-SkillsUse when preparing the camera-ready of an accepted ACM/IEEE HRI paper — de-anonymizing systematically, completing ACM+IEEE dual-publication metadata (CCS concepts, ORCID, rights/eRights form), delivering every rebuttal promise within the 8-page budget, finalizing the video and de-anonymized archive, and passing production checks.MediaNo warnings★ 1.4K↓ —
- codiris-agentizerhashgraph-online/awesome-codex-pluginsThis skill should be used when the user asks to "agentize a website", "transform a website", "create an agentfront", "build a WWA app", "make an agent-first website", "turn a website into an agent experience", "agentizer", "wwa transform", or mentions "agentfront" in context of building one from a URL.ProductivityNo warnings★ 1.5K↓ —
- improve-architecturedaveebbelaar/bamaArchitecture check-in for a growing macOS Swift codebase. Finds hot spots, proposes deeper modules, and refactors one step per commit with behavior proven unchanged. Use at the end of a milestone, before a big feature, when a file passes 600 lines, when one feature touches many files, when bugs repeat in one area, or when the user asks to refactor or clean up the code.PlanningNo warnings★ 1.6K↓ —
- jetson-promote-imageNVIDIA/skillsUse to promote overlay files and built artifacts into the staged BSP image. Do NOT use to flash or build. Triggers: promote bsp image.MediaNo warnings★ 3.9K↓ —
bootstrap
agentscope-ai/OpenJudge
PlanningUpdated 8 hours ago
From the author
Use when the user has nothing — no traces, no labels, no eval set — and needs to build a v0 evaluation from scratch. Also use when the user says "I need to start evaluating my app but don't know where to begin," "I want to set up eval for a new product," or has just identified failure modes and needs to turn them into principles. Outputs a v0 grader in 30 minutes using OpenJudge SimpleRubricsGenerator, plus a roadmap to reach calibrated evaluation.
Install
npx skills add agentscope-ai/OpenJudge --skill bootstrap -a claude-code
Installs to .claude/skills/bootstrap/ · 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