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.
47,938 skills from 2,309 repositories · updated 8 minutes ago
47,938 skills
- paperjsxcomposio-community/awesome-codex-skillsGenerate PPTX presentations, DOCX documents, XLSX spreadsheets, and PDF reports from structured JSON input using PaperJSX.DocumentsNo warnings★ 17.1K↓ —
- sentencepieceOrchestra-Research/AI-Research-SKILLsLanguage-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.ProductivityNo warnings★ 14.1K↓ —
- linkedin-interviewersergebulaev/linkedin-skillsInterview the user for the raw material their posts are made of. Builds a lasting Story Bank of roles, numbers, turning points, scars and positions, or runs a focused interview that turns one topic into a post spine. Use when a draft has nothing concrete to draw on, or the user says interview me. Not for learning how they write (use linkedin-humanizer --mode profile).MarketingNo warnings★ 5.4K↓ —Also in 1 other repo
- roblox-simulator-economyNewgamedev-skills/awesome-gamedev-agent-skillsDesign, balance, and implement the economy of a Roblox simulator, tycoon, clicker, or idle game in Luau: upgrade cost curves, buy max, income per second, rebirth/prestige requirements and multipliers, offline earnings, big-number display (1.5K, 3.4M, 2.0Qa), server-authoritative purchases, repairing tampered or old save data, and odds disclosure for paid random items such as eggs, crates, and spins. Includes a Lune pacing calculator. Use when choosing or checking baseCost/costGrowth/rebirth numbers, writing upgrade/currency/rebirth/offline code, or when progress stalls, a rebirth takes far longer than the last, numbers display as 1000K, offline earnings pay too much, or players gain currency they did not earn.DesignNo warnings★ 5.8K↓ —
- linkedin-reply-handlersergebulaev/linkedin-skillsDraft a reply to one LinkedIn comment from its URL, or sweep a whole thread from just the post URL and draft a reply to every comment worth answering, in one batch. Use for replying to a comment, following an author reply, or clearing all comments on a post. Resolves the correct parentComment (LinkedIn flattens threads to 2 levels), filters low-value comments before a sweep, and posts via Publora on approval. Not for top-level comments (use linkedin-comment-drafter).MarketingNo warnings★ 5.4K↓ —Also in 1 other repo
- binlog-generationdotnet/skillsGenerate MSBuild binary logs (binlogs) for build diagnostics and analysis. USE FOR: adding /bl:{} to any dotnet build, test, pack, publish, or restore command to capture a full build execution trace, prerequisite for binlog-failure-analysis and build-perf-diagnostics skills, enabling post-build investigation of errors or performance. Requires MSBuild 17.8+ / .NET 8 SDK+ for {} placeholder; PowerShell must quote the complete switch as '-bl:{}'. DO NOT USE FOR: non-MSBuild build systems (npm, Maven, CMake), analyzing an existing binlog (use binlog-failure-analysis instead), binlog MCP startup failures (use troubleshoot-binlog-mcp).TestingNo warnings★ 5.8K↓ —
- excel-multi-sheet-dynamic-analysisOpenSenseNova/SenseNova-Skills用于分析包含多个Sheet的Excel文件，动态判断数据量级以决定是否转换为Parquet进行大文件处理，并支持跨Sheet的特定字段统计、数据清洗、交叉分析与可视化，最终生成带下载链接的汇总报告。DocumentsNo warnings★ 6K↓ —
- linkedin-hook-extractorsergebulaev/linkedin-skillsReverse-engineer the hook formula from a viral LinkedIn post URL. Returns which of the 20 canonical 2026 formulas it uses (anaphora, R.I.P., year-pivot, time-anchor, curiosity-gap, contrarian, comment-gate, emotional cold-open, named-gratitude, and 11 more), why it worked, and a blank template. Use to learn from a competitor's post, not to write your own (use linkedin-post-writer).MarketingNo warnings★ 5.4K↓ —Also in 1 other repo
- dowhybrycewang-stanford/Auto-Empirical-Research-SkillsCausal inference framework for answering "does X cause Y?" beyond correlation. DoWhy (Microsoft Research) provides the identify-estimate-refute loop: define a causal graph (DAG), identify the causal effect using backdoor/frontdoor/instrumental variable criteria, estimate treatment effects with multiple estimators, and validate results with automated refutation tests. Use when: distinguishing causation from correlation, estimating treatment effects (ATE, ATT, CATE), designing and analyzing A/B tests with confounders, using instrumental variables, performing counterfactual reasoning ("what would have happened if..."), validating causal claims with sensitivity analysis, working with observational data where randomization is impossible, or any analysis where the question is "what is the CAUSAL effect of X on Y" rather than just "how do X and Y relate?"TestingNo warnings★ 4.8K↓ —
- nansen-prediction-marketsinternet-court/internet-court-skillPolymarket screeners — discover trending events, top markets by volume, and search for specific markets. Use when browsing what's happening on prediction markets.PlanningNo warnings★ 7K↓ —
- hunt-spa-apielementalsouls/Claude-BugHunterDiscover a single-page-app's hidden backend API from its public JS bundle, then test that API for broken access control / missing authentication. One of the highest-yield web plays in modern recon — SPAs ship their entire backend route map to the browser, and the API behind them is frequently missing the auth middleware the login page implies. Built from an authorized engagement where this play found an unauthenticated financial API that an ASM scan reporting hundreds of "Criticals" completely missed. Use whenever a target serves a JS-heavy SPA (React/Vue/Angular/Next), an "app"/"console"/"dashboard"/"portal" subdomain, or any `*api*` host shows up in recon. Leaked build artifacts (source maps / .env / .git / asset-manifest) are owned by hunt-source-leak; API version-inventory and behavioral diffing by hunt-shadow-api; this skill owns mapping a live SPA's backend routes from its JS bundle and testing them for broken access control / missing auth.EngineeringNo warnings★ 5.4K↓ —
- compute-env-setupaipoch/open-sciencePrepare reproducible setup instructions and validate a user-managed named software environment on an Open-Science SSH Compute Host, including direct SSH and Slurm hosts. Use when a remote job needs packages, modules, cache variables, or a repeatable activation that the host does not already provide.ScienceNo warnings★ 5.4K↓ —
- melonjs-inputUpdatedmelonjs/melonJSUse this skill for keyboard, pointer, mouse, touch and gamepad input in melonJS. Covers the bindKey action indirection, registerPointerEvent on regions, the isKinematic requirement that silently blocks pointer events, which of several overlapping objects receives an event and how to consume it, world vs screen pointer coordinates, and gamepad mapping onto the same actions. Triggers on: input, bindKey, isKeyPressed, KEY, registerPointerEvent, releasePointerEvent, pointerdown, pointerup, pointermove, POINTERMOVE, gamepad, bindGamepad, triggerKeyEvent, virtual gamepad, touch controls, joystick, gamepad-plugin, KEYDOWN, KEYUP, press any key, splash screen, click, touch, drag, hit test, event propagation, stop propagating, overlapping, which object gets the click.TestingNo warnings★ 6.4K↓ —
- hunt-sessionelementalsouls/Claude-BugHunterHunt Session Management vulnerabilities — session fixation (no regeneration on login), insufficient invalidation on logout / password-change / email-change, predictable or low-entropy session IDs, JWT-as-session with no exp/revocation, refresh-token rotation/reuse-detection gaps, OAuth/SSO session linkage, device-bound-session (DBSC) downgrade, and cookie attribute issues (Secure/HttpOnly/SameSite/__Host-). Validate with TWO real sessions (attacker A + victim B), body-diff every 200, and OOB confirmation for theft chains. Medium to Critical (fixation→admin hijack, no-invalidation→persistent ATO).SecurityNo warnings★ 5.4K↓ —
- git-commitThinkInAIXYZ/deepchatGenerate well-formatted git commit messages following conventional commit standardsEngineeringNo warnings★ 6.4K↓ —
- importing-a-codebaseJetBrains/thinkrailUse when asked to create the initial spec graph for an existing codebase that has source code but no specs. Normally reached via setting-up-a-project.PlanningNo warnings★ 6.4K↓ —
- setting-up-a-projectJetBrains/thinkrailUse when asked to set up, onboard, initialize, or spec a project with no spec graph, or when invoked by the app's Set-up-project card. Not for ordinary work in an already-specced project.PlanningNo warnings★ 6.4K↓ —
- 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↓ —
- boltzaipoch/open-scienceStructure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al. 2025, github.com/jwohlwend/boltz). Reach for this skill to validate designed binders against a target, to co-fold a protein with a SMILES or CCD ligand, or to get an open-source AlphaFold3 alternative with optional binding-affinity prediction.ScienceNo warnings★ 5.4K↓ —
- writing-workflow-skillsJetBrains/thinkrailUse when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.WritingNo warnings★ 6.4K↓ —
- scgptaipoch/open-scienceEmbed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology. Use this skill when: (1) Producing cell embeddings from an AnnData for clustering/integration, (2) Zero-shot or fine-tuned cell-type annotation, (3) Gene-level representation for perturbation/GRN tasks. For probabilistic single-cell models (scVI etc.), use the scvi-tools library.ScienceNo warnings★ 5.4K↓ —
- vc-industry-researchzebbern/claude-code-guideGenerate professional primary market / venture capital industry research reports, including sector deep-dives, investment memos, and market analysis. Produces detailed PDF reports covering TMT, consumer, healthcare, and industrials. Triggered by requests to analyze an industry, create a market report, write a sector deep-dive, or generate any PE/VC-style research document in Chinese or English.ScienceNo warnings★ 4.7K↓ —
- melonjs-sprites-and-animationmelonjs/melonJSUse this skill when creating sprites, playing frame animations, or working with texture atlases in melonJS. Covers Sprite construction from a plain image or an atlas region, addAnimation/setCurrentAnimation, TextureAtlas for TexturePacker/ShoeBox/Aseprite, tint, flip, NineSliceSprite, and the centred anchorPoint that offsets naive positioning. Triggers on: Sprite, new Sprite, addAnimation, setCurrentAnimation, isCurrentAnimation, TextureAtlas, TexturePacker, Aseprite, ShoeBox, atlas, region, framewidth, frameheight, tint, flipX, flipY, NineSliceSprite, animation.MediaNo warnings★ 6.4K↓ —
- web2-reconelementalsouls/Claude-BugHunterWeb2 recon pipeline — subdomain enumeration (subfinder, Chaos API, assetfinder), live host discovery (dnsx, httpx), URL crawling (katana, waybackurls, gau), directory fuzzing (ffuf), JS analysis (LinkFinder, SecretFinder), continuous monitoring (new subdomain alerts, JS change detection, GitHub commit watch). Use when starting recon on any web2 target or when asked about asset discovery, subdomain enum, or attack surface mapping.BrowserNo warnings★ 5.4K↓ —
openrlhf-training
Orchestra-Research/AI-Research-SKILLs
PlanningUpdated Oct 11, 2026
From the author
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill openrlhf-training -a claude-code
Installs to .claude/skills/openrlhf-training/ · 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: MIT
Safety checks on SKILL.md
- Uses sudoLow
Why 91
Security95
Provenance90
Maintenance100
Licence100
Adoption65
Files (5)
- SKILL.md
- references/algorithm-comparison.md
- references/custom-rewards.md
- references/hybrid-engine.md
- references/multi-node-training.md