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 10 hours ago
48,362 skills
- ap-roadmap-authorSpielewoy/autoprompt-skillWrite one dependency-ordered roadmap with owners, integration points, success items, and real checks.PlanningNo warnings★ 1.2K↓ —
- onboardinghuytieu/COG-second-brainPersonalize COG for your workflow - creates profile, interests, and watchlist files with guided setup (run this first!)ProductivityNo warnings★ 1.3K↓ —Also in 1 other repo
- url-dumphuytieu/COG-second-brainQuick capture URLs with automatic content extraction, insights, and categorization into knowledge bookletsOtherNo warnings★ 1.3K↓ —Also in 1 other repo
- ab-test-setupalirezarezvani/claude-skillsUse before planning or launching any A/B, split or multivariate test, or when asked if a result is significant. Sizes the test with sample_size_calculator.py and writes the hypothesis, metric and stop rule first, so it is not called early on noise.TestingNo warnings★ 29.2K↓ —
- cto-advisorUpdatedalirezarezvani/claude-skillsCTO decisions: tech debt, architecture direction, scaling the engineering team, technology evaluation, DORA metrics. Use whenever the user asks whether to rewrite, how to grow the eng team or which tech to bet on.PlanningNo warnings★ 29.2K↓ —
- scouthuytieu/COG-second-brainEvaluate URLs and tools — check vault coverage, assess relevance, recommend save or skipOtherNo warnings★ 1.3K↓ —Also in 1 other repo
- growth-funnelkostja94/marketing-skillsWhen the user wants to plan growth using the AARRR framework, diagnose growth bottlenecks, or map actions across the customer lifecycle. Also use when the user mentions "growth funnel," "AARRR," "pirate metrics," "acquisition activation retention," "customer lifecycle metrics," or "growth framework." For retention tactics, use retention-strategy.MarketingNo warnings★ 1.1K↓ —
- jetson-flash-imageNVIDIA/skillsUse to flash a promoted BSP image to a Jetson DUT in RCM mode via flash.sh or l4t_initrd_flash.sh. Do NOT use for BSP customization, image promotion, or carrier derivation.MediaNo warnings★ 3.8K↓ —
- minutes-listsilverstein/minutesList recent meetings and voice memos. Use when the user asks "what meetings did I have", "show my recent recordings", "any meetings today", "list my voice memos", or wants an overview of their meeting history. Also use when they need to find a specific meeting by browsing rather than searching.PlanningNo warnings★ 1.6K↓ —Also in 1 other repo
- oma-dbNewfirst-fluke/oh-my-agentDesign schemas and migrations, tune queries, or plan vector retrieval and database operations. Application API implementation uses oma-backend.DataNo warnings★ 1.4K↓ —
- runbook-generatoralirezarezvani/claude-skillsUse when a service needs runbooks for deploy, incident response, maintenance or rollback, before launch. Generates them per environment with runbook_generator.py.DevOpsNo warnings★ 29.2K↓ —
- ap-work-group-managerSpielewoy/autoprompt-skillDivide one accepted work group only when at least two useful workers can have non-overlapping ownership.OtherNo warnings★ 1.2K↓ —
- redis-connectionsredis/agent-skillsRedis client and connection guidance covering connection pooling, multiplexing, pipelining, client-side caching with RESP3, avoiding slow commands (KEYS, SMEMBERS, HGETALL), and tuning socket timeouts. Use when configuring a Redis client (redis-py, Jedis, Lettuce, NRedisStack), batching commands for throughput, eliminating per-request connection creation, iterating large keyspaces with SCAN, enabling client-side caching for read-heavy workloads, or setting connect and read timeouts.OfficialOtherNo warnings★ 172↓ —Also in 1 other repo
- render-editorial-motion-podcastgooseworks-ai/goose-skillsAssemble an editorial-motion podcast-clip ad from a config — a real clipped podcast MP3 carries the narrative while N flat limited-palette editorial-illustration keyframes (one look pack) are animated NOT by generative i2v but by DETERMINISTIC ffmpeg ken-burns (zoompan) + hard cuts (no crossfades, which expose geometric drift), each beat snapped to its spoken line, the real audio muxed, Whisper-driven captions burned only mid-sentence, and closed on a PIL brand end card — never AI-rendered text. This is the FREE deterministic assembly stage (ffmpeg ken-burns + hard concat + audio mux + captions + end card); the real audio is clipped from source and the keyframes come from create-image-fal. Use for the editorial-motion-podcast format.MediaNo warnings★ 1.3K↓ —
- 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★ 977↓ —
- verify-form-validationreticlehq/reticleCheck that a form actually rejects bad input: the error message renders, the submit button stays disabled, and no request goes out. Use when validation logic was written but never driven, when a "required" or pattern check looks right on screen but was never proven, or when a bug report says the form submitted invalid data anyway.MediaNo warnings★ 1.3K↓ —
- 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★ 1K↓ —
- expense-policymohitagw15856/pm-claude-skillsWrite a clear company expense & reimbursement policy. Use when asked to write an expense policy, a reimbursement policy, a travel & expense (T&E) policy, or spending guidelines. Produces a practical policy — what's covered, limits by category, the approval and submission process, timelines, and what's not reimbursable — that's fair, easy to follow, and reduces finance back-and-forth. Not tax/legal advice.FinanceNo warnings★ 1.5K↓ —
- colt-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning a COLT (Conference on Learning Theory) submission calendar backward from the single AoE paper deadline — proof-completion and verification milestones, writing and appendix-assembly passes, CMT logistics, the rebuttal window, decision aftermath, and PMLR camera-ready with conference presentation in early summer.ProductivityNo warnings★ 1.4K↓ —
- 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↓ —
- judge-task-lifecyclesno-ai/sno-stationJudge how a memory changes active-task state and whether it refers to an existing task. Use for mem-claw task-lifecycle model calls.ProductivityNo warnings★ 1.1K↓ —
- planning-with-filesOthmanAdi/planning-with-filesPersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. Optional gated mode can request continuation only when the host supports it and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.PlanningNo warnings★ 27.9K↓ —
- cikm-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning a CIKM project calendar across the May abstract/paper gates, June short-track gates, August notification and camera-ready, and the November conference, including the post-submission phase now live in the 2026 cycle, multi-track coordination, and fallback planning toward CIKM 2027 or sibling venues.ProductivityNo warnings★ 1.4K↓ —
- oma-skill-creationNewfirst-fluke/oh-my-agentCreate or revise OMA skills and their references. Use for skill routing, execution contracts, conditional loading, and authoring validation.OtherNo warnings★ 1.4K↓ —
flaky-skill
alibaba/skill-up
TestingUpdated 23 hours ago
From the author
A skill with potentially flaky behavior for testing retry
Install
npx skills add alibaba/skill-up --skill flaky-skill -a claude-code
Installs to .claude/skills/flaky-skill/ · 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 onlyNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance78
Maintenance100
Licence100
Adoption51
Files (6)
- README.md
- SKILL.md
- evals/cases/flaky-success-retry.yaml
- evals/cases/second-case-parallel.yaml
- evals/eval.yaml
- evals/evals.json