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.
47,966 skills from 2,309 repositories · updated 11 hours ago
47,966 skills
- replica-reconJakeschincariol/replica-skillReverse-engineers any app into a recon map: screen inventory, user flows, component list, inferred data model and a feature matrix, from public pages, screenshots, app store listings, help docs and the user's own account. The first step of the Replica pack. Use when the user says "clone this app", "reverse engineer X", "how does X work", "map out X", "what screens does X have", "I want to build my own version of X", "copy this app", or pastes an app's URL or App Store link and wants to rebuild it.OtherNo warnings★ 6.6K↓ —
- linkedin-thread-monitorsergebulaev/linkedin-skillsTrack which of your LinkedIn comments earned author replies. Flags the 6-24h warm-reply window where thread momentum peaks, classifies threads as hot/warm/cool/dormant, and routes warm ones to linkedin-reply-handler for follow-up drafts. Powered by Apify, no LinkedIn login. Triggers on "what threads need follow-up", "author replied", "monitor my comments". Not for analyzing likers on a post (use linkedin-engager-analytics).MarketingNo warnings★ 5.4K↓ —Also in 1 other repo
- designlang-tokensManavarya09/design-extractUse when styling UI for v0.dev — references the extracted design system tokens instead of inventing colors, spacing, or typography.DesignNo warnings★ 4.4K↓ —
- performance-rcagrafana/skillsInvestigates CPU, memory, and contention problems with Grafana Pyroscope profiles via the gcx CLI. Compares affected and baseline workloads, locates changed application stacks, and tests root-cause hypotheses against symptom and change evidence. Use when a service shows high CPU, growing memory, GC pressure, lock contention, or hot functions, when code regressed after a deploy, or when given a suspect service, flame graph, trace, or profiling anomaly report. For profiling setup use pyroscope; for profilecli-based analysis use profilecli-insights.OfficialTestingNo warnings★ 297↓ —
- egm-reviewNewgoogle/elephant-goldfish-modelOrchestrates the EGM Goldfish Review Protocol. Used as part of the EGM process to perform design document reviews. Executes five review phases: Initial Zoom Out Review, Comprehension Review, Design Critique, Intermediate Zoom Out Review, and Implementation Readiness.EngineeringNo warnings★ 6.5K↓ —Also in 1 other repo
- melonjs-mathmelonjs/melonJSUse this skill for vector and matrix maths in melonJS — Vector2d, Vector3d, their observable variants, Matrix2d, Matrix3d, and the math utility functions. Covers which methods mutate and which allocate, the vector pool and when clone() is the wrong tool, interpolation with lerp, slerp, damp and moveTowards, and the argument defaults that silently drop a component. Triggers on: Vector2d, Vector3d, ObservableVector2d, ObservableVector3d, Matrix2d, Matrix3d, vector, vector maths, dot, cross, normalize, length, distance, angle, lerp, slerp, damp, moveTowards, project, clamp, degToRad, radToDeg, clone, vector pool, vector3dPool, setMuted, setCallback, my vector is wrong, z is zero, scale ignores z., moveTowards ignores z, projectN, currentTransform, setTransform, matrix, transform matrix, column-major, val, Float32Array, basis matrix, orientation matrix, Noise, getNoise1d, flicker, wobble.OtherNo warnings★ 6.4K↓ —
- verifyzenbu-labs/terminal-browserDrive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.MediaNo warnings★ 4.3K↓ —
- bug-bountyelementalsouls/Claude-BugHunterComplete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind maps, threat modeling), vulnerability hunting (IDOR, SSRF, XSS, auth bypass, CSRF, race conditions, SQLi, XXE, file upload, business logic, GraphQL, HTTP smuggling, cache poisoning, OAuth, timing side-channels, OIDC, SSTI, subdomain takeover, cloud misconfig, ATO chains, agentic AI), LLM/AI security testing (chatbot IDOR, prompt injection, indirect injection, ASCII smuggling, exfil channels, RCE via code tools, system prompt extraction, ASI01-ASI10), A-to-B bug chaining (IDOR→auth bypass, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth), bypass tables (SSRF IP bypass, open redirect bypass, file upload bypass), language-specific grep (JS prototype pollution, Python pickle, PHP type juggling, Go template.HTML, Ruby YAML.load, Rust unwrap), and reporting (7-Question Gate, 4 validation gateSecurityNo warnings★ 5.4K↓ —
- testinggrafana/skillsProbe, load-test, and instrument frontends from Grafana Cloud. Covers Synthetic Monitoring (HTTP / DNS / TCP / Ping / Traceroute / Multihttp / k6-browser scripted checks from 20+ global probes, alert on `probe_success` + TLS-cert expiry), Grafana Cloud k6 (distributed load tests across AWS load-zones, scenarios, `http_req_duration` thresholds, CI integration via `grafana/k6-action`), and Frontend Observability with Faro Web SDK (RUM, Core Web Vitals, custom events, `pushError`, distributed-trace correlation). Use when checking website / API uptime from multiple regions, gating a release on a load test, watching for TLS-cert renewal, instrumenting a React/Vue app, tracking Core Web Vitals, or correlating frontend errors to backend traces — even when the user says "is my login flow up?", "monitor my API", "ping our endpoint every minute", "release-gate load test", "browser performance monitoring", "session replay", or "RUM" without naming Synthetic Monitoring / k6 / Faro.OfficialTestingNo warnings★ 297↓ —
- push-to-registryhashicorp/agent-skillsPush Packer build metadata to HCP Packer registry for tracking and managing image lifecycle. Use when integrating Packer builds with HCP Packer for version control and governance.OfficialMediaNo warnings★ 910↓ —
- fondo-hello-worldjeremylongshore/tons-of-skills-marketplaceVerify Fondo setup by checking financial data sync, reviewing categorized transactions, and confirming R&D tax credit eligibility. Trigger: "fondo first sync", "fondo verify", "fondo hello world", "fondo test".TestingNo warnings★ 2.9K↓ —
- rag-evalNVIDIA/skillsFilesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.OtherNo warnings★ 3.8K↓ —
- plain-englishjeremylongshore/tons-of-skills-marketplaceExplain supplied contract clauses in clear language while preserving conditions, exceptions and source locators. Use when a non-lawyer wants to understand an agreement. Trigger with "explain this contract", "plain-english" or "translate this contract to plain English".LegalNo warnings★ 2.9K↓ —
- modern-cpptrailofbits/skillsGuides C++ code toward modern idioms (C++20/23/26). Use when writing new C++ code, modernizing legacy patterns, or working on security-critical C++. Replaces raw pointers with smart pointers, SFINAE with concepts, printf with std::print, error codes with std::expected.SecurityNo warnings★ 7.9K↓ —
- nemo-retrieverNVIDIA/skillsUse when searching, extracting, ingesting, or querying a document collection with the NeMo Retriever 26.8.1 CLI, including local LanceDB indexes and deployed Retriever services. Use for PDFs, images, Office files, HTML, text, audio, and video; not for editing documents or web search.DevOpsNo warnings★ 3.8K↓ —
- speak-cost-tuningjeremylongshore/tons-of-skills-marketplaceOptimize Speak API costs through usage monitoring, tier selection, and efficient audio processing. Use when implementing cost tuning, or managing Speak language learning platform operations. Trigger with phrases like "speak cost tuning", "speak cost tuning".MediaNo warnings★ 2.9K↓ —
- tao-list-capabilitiesNVIDIA/skillsAnswer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks "what can TAO Skill Bank do", "list TAO models", "which TAO workflows are available", or "what supports AutoML".OtherNo warnings★ 3.8K↓ —
- golang-code-stylesamber/cc-skills-golangGolang code style conventions — line length and breaking, variable declarations, control flow clarity, when comments help vs hurt. Use when writing or reviewing Go code, asking about style or clarity, or establishing project coding standards. Not for naming conventions (→ See `samber/cc-skills-golang@golang-naming` skill), linter configuration (→ See `samber/cc-skills-golang@golang-lint` skill), or doc comments (→ See `samber/cc-skills-golang@golang-documentation` skill).EngineeringNo warnings★ 3.7K↓ —
- golang-pkg-go-devsamber/cc-skills-golangGolang package and module lookup via `godig`, a pkg.go.dev API client (CLI + MCP server). Use for any Go/Golang library's documentation, API signatures, symbols, usage examples, which versions exist, licenses, whether a dependency has CVEs, or who imports a package — prefer this over Context7 for any Go package or module. Read-only, no auth. Not for upgrading dependencies (→ See `samber/cc-skills-golang@golang-dependency-management` skill), choosing a library (→ See `samber/cc-skills-golang@golang-popular-libraries` skill), or local symbols and an already-used dependency's resolved source, call sites, and generic instantiations (→ See `samber/cc-skills-golang@golang-gopls` skill).EngineeringNo warnings★ 3.7K↓ —
- mcore-split-prNVIDIA/skillsSplit a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.OtherNo warnings★ 3.8K↓ —
- media-useUpdatedheygen-com/hyperframesGet or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.OfficialMediaNo warnings★ 75.8K↓ —
- skill-article-outlineZJU-REAL/Easel生成长文大纲：基于搜索分析生成 H2/H3 标题结构、段落字数目标、图表位置和 FAQ 规划，适用于公众号文章、知乎专栏、博客。 当用户说"文章大纲""长文结构""公众号大纲""知乎回答框架""写作提纲""文章框架""H2/H3 结构"时使用。WritingNo warnings★ 4.2K↓ —
- content-amplifieraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "amplify influencer content with paid media", "set up whitelisting or Spark Ads", "decide which posts to boost", "repurpose influencer content", "turn one video into multiple ads", or "build a UGC asset library"; produces (paid mode) a content-selection scorecard, a paid amplification strategy (whitelisting/boosting/dark posts), audience targeting, and a budget+optimization plan, or (repurpose mode) a rights-tracked content inventory, a 1-video-to-10+-asset repurposing map, per-format transformation specs, and a 30-day distribution plan. Not for gating whether a deliverable is publishable or FTC-compliant — use creator-content-auditor; not for the always-on brand posting calendar — use social-calendar-builder; not for drafting a net-new idea into platform-native packages — use social-creative-builder. 复用达人内容 / 内容放量.MediaNo warnings★ 3K↓ —
- press-media-relationsaaron-he-zhu/aaron-marketing-skillsUse when the user asks to "build a media list for my launch", "write a launch press release", or "pitch press under embargo"; produces a three-tier media and analyst list (Tier 1 exclusive candidates, Tier 2 vertical press, Tier 3 communities and newsletters), an embargo pitch timing skeleton keyed to the launch-registry date, a press-release draft in standard structure with no fabricated quotes or numbers, and an analyst briefing outline. Not for press-kit assets — use launch-asset-packager; not for follow-up sequence mechanics — use outreach-manager; not for post-launch news-echo monitoring — use launch-monitor. 媒体名单/禁运期pitch/新闻稿/分析师简报WritingNo warnings★ 3K↓ —
deepspeed
Orchestra-Research/AI-Research-SKILLs
OtherUpdated Oct 11, 2026
From the author
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill deepspeed -a claude-code
Installs to .claude/skills/deepspeed/ · 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: MIT
Safety checks on SKILL.md
- Uses sudoLow
Why 91
Security95
Provenance90
Maintenance100
Licence100
Adoption65
Files (10)
- SKILL.md
- references/08.md
- references/09.md
- references/2020.md
- references/2023.md
- references/assets.md
- references/index.md
- references/mii.md
- references/other.md
- references/tutorials.md