Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 961 files from 2 125 authors, of which 68 678 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Roll Playwright Java to a new version
Prepare a Playwright Java release after the rolling PR has merged — cut the release branch, mark the Maven version, draft the GitHub release, and tick the Java boxes in the internal checklist.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
> 紫微斗数专业排盘与解盘技能。当用户提到紫微斗数、紫微排盘、紫微命盘、命宫、 十二宫、主星、四化、大限、流年、斗数格局、飞星、三方四正、紫微星、天机星、 太阳星、武曲星、天同星、廉贞星、天府星、太阴星、贪狼星、巨门星、天相星、 天梁星、七杀星、破军星等相关内容时触发此技能。也适用于用户想了解自己的命运、 性格、事业、婚姻、财运等，且明确要求或暗示使用紫微斗数体系的场景。包含完整的 排盘、宫位解读、四化分析、大限流年推演等能力。正式排盘调用脚本完成固定计算， 模型只负责访谈与解读。
> 四柱八字专业排盘与解盘技能。当用户提到八字、四柱、天干地支、日主、十神、 大运流年、喜用神、格局、伤官配印、食神生财、五行旺衰、命局分析等相关内容时 触发此技能。也适用于用户想了解自己的命运、性格、事业、婚姻、财运等， 且明确要求或暗示使用八字体系的场景。包含完整的排盘、格局判断、十神分析、 大运流年推演等能力。
> 奇门遁甲排盘、解盘、择时、方位判断与理论教学技能。用户明确提到奇门遁甲、时家奇门、 奇门排盘、奇门解盘、奇门择吉、方位选择、趋吉避凶，或要求“用奇门”分析一件具体事情时， 必须使用本技能。正式排盘前先做结构化访谈，再调用脚本完成固定计算，最后再做解读与建议。
Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video, narrated explainer, video podcast, or animated infographic-style video from a topic — even if they don't say "video podcast" explicitly. Also trigger when the user wants to regenerate, re-render, rebuild, update, or iterate on a narrated video this skill already produced — e.g. they edited the script/prompt, changed the visuals, or swapped the background music and want the final video remade (reuse the existing videos/{name}/ directory, never start a new project). Do NOT trigger for generic video editing, trimming, format conversion, color grading, or non-narrative video tasks. Produces 4K video via research → script → TTS → Remotion → MP4 + BGM.
Design principles and creative direction for building HTML artifacts — pages, reports, plans, landing pages, demos, decks, and small tools. Use when creating or restyling any visual HTML deliverable and deciding its palette, type pairing, layout, theming, or overall register, or when the output must not look generically AI-generated.
Direct-invocation specialist for self-contained HTML diagrams whose layout, notation, and interaction clarify relationships, sequence, topology, state, hierarchy, or quantitative structure. Use when the user explicitly invokes html-diagram or the broad html skill routes a diagram request here. Do not activate independently from a general request.
Direct-invocation specialist for clear, self-contained HTML plans that preserve source material while improving hierarchy, sequence, ownership, dependencies, and reviewability. Use when the user explicitly invokes html-plan or the broad html skill routes a plan request here. Do not activate independently from a general request.
Direct-invocation specialist for polished, responsive, self-contained HTML mockups and interactive prototypes grounded in the user's conversation, product context, and design language. Use when the user explicitly invokes html-prototype or the broad html skill routes a mockup or prototype request here. Do not activate independently from a general request. Treat a mockup as a noninteractive fidelity mode within this skill, not as a separate skill.
Direct-invocation specialist for low-fidelity, self-contained HTML wireframes that test information hierarchy, content, navigation, task flow, and responsive structure before visual design. Use when the user explicitly invokes html-wireframe or the broad html skill routes a wireframe request here. Do not activate independently from a general request. Do not use for polished mockups or production-like interaction; use html-prototype for those.
Create or redesign self-contained single-file HTML artifacts with a visual direction shaped by the user's brief, project, and subject. Use when HTML is the deliverable for a report, explainer, landing page, presentation, tool, mixed artifact, or broad request. This is the collection's only implicit router. Route clear wireframe, prototype, mockup, plan, or diagram requests to the matching direct-invocation specialist when available. Do not use for ordinary application implementation when a standalone HTML file is not the deliverable.
Redesign GitHub README homepages or create project-native pure SVG, hybrid SVG-composed PNG/WebP, and opt-in animated GIF assets. Use when a user asks to beautify, redesign, rebrand, visually upgrade, simplify, or audit a GitHub README; create only a hero, section headers, diagrams, badges, motion graphics, showcase modules, or other README assets; or turn a repository homepage into a cohesive visual story. If whole-README work versus asset-only work is unclear, ask which scope the user wants. For hero-like assets where pure SVG and generated raster material are both viable, explain the tradeoffs and confirm the implementation before creating the asset.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Generate a Python code skeleton from an experiment blueprint
Search academic literature and generate research hypotheses
Produce an experiment blueprint from a research hypothesis
Draft a LaTeX research paper from all previous stage outputs
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
Scrape BOSS直聘 (job listing site) via Chrome CDP. Searches jobs by keyword/city/filters, fetches JD details, outputs structured JSON/CSV with plaintext salary, and can summarize scraped results into a job-market prompt. Use when user wants to search/analyze jobs on BOSS直聘 or zhipin.com.
Deploy a Kubernetes GPU cluster with DeepOps (Kubespray + GPU Operator) and prove it schedules GPU pods. Use when asked to deploy or rebuild Kubernetes on GPU servers with this repository.
Deploy a Slurm GPU cluster with DeepOps and prove it works. Use when asked to deploy, install, or rebuild Slurm on one or more GPU servers with this repository.
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
Check whether a DeepOps-deployed Slurm or Kubernetes GPU cluster is healthy and report a machine-readable verdict. Use for health checks, post-deploy verification, "is the cluster working?" questions, and after any node or driver change.
Reviews adk-bot pull requests by validating technical correctness against source code, checking PR states and formatting, and following Google's developer documentation style and ADK docs conventions. Triggers on "review bot PR", "check bot changes", or "verify bot issue".
Creates a new ADK integration documentation page (a Markdown file under docs/integrations/) for a third-party tool, plugin, observability platform, data store, MCP server, or connector. Gathers details, picks the right category template, and drafts a page that follows adk-docs conventions. Triggers on "integration-create", "create integration page", "new integration", "add an integration", "write an integration page".
Reviews an ADK integration documentation page (a Markdown file under docs/integrations/) or an integration pull request for correctness, structure, style, working code, valid links, and catalog conventions. Produces a prioritized review report, a recommended decision (approve, request changes, or close PR), a top-level review response, and draft line-anchored comments; only fixes issues when explicitly asked. Triggers on "integration-review", "review integration page", "review integration PR", "review this integration", "check integration docs".
Audits whether ADK API reference docs and version-pinned strings are up to date across all language SDKs. Compares in-repo versions against upstream releases and package registries, then reports what needs bumping and which process to follow, and emits an executable plan only when asked. Triggers on "audit API reference", "check API ref docs", "are API docs up to date", "bump API doc versions", "check SDK doc versions".
Load when the person wants to run or own apps on their own machine, replace a subscription (Netflix, Google Photos, Dropbox, a password manager), or asks about anything already set up with self-host, such as "where is my movie app?".
Generate the self-host release announcement visual when preparing a release or announcing newly added Apps. Discover added Apps between refs and render the approved Logo hub with pulses, rather than inventing a new layout.
Catalog edits in Go. Use for any task that adds an App, changes an App's image, port, Compose, env, notes or StandaloneGuide (even a one-line image bump), changes a Recipe, or hides or unhides an App. Each of these changes generated site and DCM data and hand-kept App counts. DCM-only Containers go to add-container; Homarr wiring goes to docs/agents/homarr-integrations.md.
DCM Container work. Use to add or edit a Container in dcm/src/tools/, including an issue labelled `container` and then `accepted`, and the pull request dcm-add-container.yml opens from it. A Container is a compose snippet DCM offers for a product the Catalog does not install. Catalog Apps go to edit-catalog.
Create new eval suites for the deepagentsjs monorepo. Handles dataset design, test case scaffolding, scoring logic, vitest configuration, and LangSmith integration. Use when the user asks to: (1) create an eval, (2) write an evaluation, (3) add a benchmark, (4) build an eval suite, (5) evaluate agent behaviour, (6) add test cases for a capability, or (7) implement an existing benchmark (e.g. oolong, AgentBench, SWE-bench). Trigger on phrases like 'create eval', 'new eval', 'add eval', 'benchmark', 'evaluate', 'eval suite', 'write evals for'.
Intelligent loading performance analysis with automated workflows for TTFB investigation (DNS/connection/server breakdown), render-blocking detection, script performance deep dive (first vs third-party attribution), font optimization, and resource hints validation. Includes decision trees that automatically analyze TTFB sub-parts when slow, detect script loading anti-patterns (async/defer/preload conflicts), identify render-blocking resources, and validate resource hints usage. Features workflows for complete loading audit (6 phases), backend performance investigation, and priority optimization. Cross-skill integration with Core Web Vitals (LCP resource loading), Interaction (script execution blocking), and Media (lazy loading strategy). Use when the user asks about TTFB, FCP, render-blocking, slow loading, font performance, script optimization, or resource hints. Compatible with Chrome DevTools MCP.
Intelligent Core Web Vitals analysis with automated workflows and decision trees. Measures LCP, CLS, INP with guided debugging that automatically determines follow-up analysis based on results. Includes workflows for LCP deep dive (5 phases), CLS investigation (loading vs interaction), INP debugging (latency breakdown + attribution), and cross-skill integration with loading, interaction, and media skills. Use when the user asks about Core Web Vitals, LCP optimization, layout shifts, or interaction responsiveness. Compatible with Chrome DevTools MCP.
Intelligent media optimization with automated workflows for images, videos, and SVGs. Includes decision trees that detect LCP images (triggers format/lazy-loading/priority analysis), identify layout shift risks (missing dimensions), and flag lazy loading issues (above-fold lazy or below-fold eager). Features workflows for complete media audit, LCP image investigation, video performance (poster optimization), and SVG embedded bitmap detection. Cross-skill integration with Core Web Vitals (LCP/CLS impact) and Loading (priority hints, resource preloading). Provides performance budgets and format recommendations based on content type. Use when the user asks about image optimization, LCP is an image/video, layout shifts from media, or media loading strategy. Compatible with Chrome DevTools MCP.
Intelligent interaction performance analysis with automated workflows for INP debugging, scroll jank investigation, and main thread blocking. Includes decision trees that automatically run script attribution when long frames detected, break down input latency phases, and correlate layout shifts with interactions. Features workflows for complete interaction audit, third-party script impact analysis, and animation performance debugging. Cross-skill integration with Core Web Vitals (INP/CLS correlation) and Loading (script execution analysis). Use when the user asks about slow interactions, janky scrolling, unresponsive pages, or INP optimization. Compatible with Chrome DevTools MCP.
Intelligent Core Web Vitals analysis with automated workflows and decision trees. Measures LCP, CLS, INP with guided debugging that automatically determines follow-up analysis based on results. Includes workflows for LCP deep dive (5 phases), CLS investigation (loading vs interaction), INP debugging (latency breakdown + attribution), and cross-skill integration with loading, interaction, and media skills. Use when the user asks about Core Web Vitals, LCP optimization, layout shifts, or interaction responsiveness. Compatible with Chrome DevTools MCP.
Web performance measurement and debugging toolkit. Use when the user asks about web performance, wants to audit a page, or says "analyze performance", "debug lcp", "check ttfb", "measure core web vitals", "audit images", or similar.
Intelligent network quality analysis with adaptive loading strategies. Detects connection type (2g/3g/4g), bandwidth, RTT, and save-data mode, then automatically triggers appropriate optimization workflows. Includes decision trees that recommend image compression for slow connections, critical CSS inlining for high RTT, and save-data optimizations (disable autoplay, reduce quality). Features connection-aware performance budgets (500KB for 2g, 1.5MB for 3g, 3MB for 4g+) and adaptive loading implementation guides. Cross-skill integration with Loading (TTFB impact), Media (responsive images), and Core Web Vitals (connection impact on LCP/INP). Use when the user asks about slow connections, mobile optimization, save-data support, or adaptive loading strategies. Compatible with Chrome DevTools MCP.
Intelligent loading performance analysis with automated workflows for TTFB investigation (DNS/connection/server breakdown), render-blocking detection, script performance deep dive (first vs third-party attribution), font optimization, and resource hints validation. Includes decision trees that automatically analyze TTFB sub-parts when slow, detect script loading anti-patterns (async/defer/preload conflicts), identify render-blocking resources, and validate resource hints usage. Features workflows for complete loading audit (6 phases), backend performance investigation, and priority optimization. Cross-skill integration with Core Web Vitals (LCP resource loading), Interaction (script execution blocking), and Media (lazy loading strategy). Use when the user asks about TTFB, FCP, render-blocking, slow loading, font performance, script optimization, or resource hints. Compatible with Chrome DevTools MCP.
Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when user says "compile", "build the slides", "rebuild the PDF", "run latex", "render the tex", or asks why a `.tex` file isn't producing a PDF. Operates on `Slides/*.tex`.
| Show current context status and session health. Use to check how much context has been used, whether auto-compact is approaching, and what state will be preserved.
Stage, commit, push, open a PR, and merge to main. Use ONLY on explicit commit intent — user says "commit", "ship it", "push this", "open a PR", "merge to main", "let's commit this", or prefixes with `/commit`. Do NOT auto-invoke on vague end-of-task phrases ("we're done", "wrap up") — those require explicit confirmation first. Runs the standard commit-PR-merge cycle; never force-pushes or skips hooks.
Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt / environment.yml / uv.lock, Stata version + ado package list), records seeds and RNG kind, optionally writes a pinning Dockerfile, and produces a paste-ready "Computational requirements" block. Use when user says "capture the environment", "snapshot my dependencies", "pin the versions", "make a renv.lock / requirements.txt", "make this byte-reproducible", or before releasing a replication package to openICPSR / the AEA Data Editor.
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
Distill the current conversation into a structured note (decisions made, open questions, file pointers with line numbers, next 1–3 actions) and save to `quality_reports/session_logs/` before auto-compression. Differs from `/checkpoint` (explicit stop-point snapshot) and from auto-compaction (which truncates rather than distills). Use when context is approaching auto-compact threshold, when a long pipeline has accumulated many decisions, or when the user says "compress", "distil this session", "before we hit auto-compact", "structured handoff before context resets".
Generate a co-author / collaborator handoff brief for a multi-author, multi-machine project — summarizing what changed since the last brief (git delta), the current state of each artifact (manuscript, analysis, slides), open questions, how to reproduce locally, and any restricted-data access steps. Use when user says "coauthor brief", "handoff brief", "bring my coauthor up to speed", "what changed since last week", "onboard a collaborator", "write a handoff for [name]", or before sending a co-author the repo. NOT a commit or a checkpoint — it is the cross-machine, cross-person summary `meta-governance.md` only partially covers.
Save a structured state snapshot before stopping or handing off. Captures the active plan, recent decisions, file pointers (with line numbers), open questions, and the next 1–3 actions into a checkpoint file under `quality_reports/checkpoints/`. Optionally proposes `[LEARN]` entries to add to MEMORY.md. Use when user says "checkpoint", "save state", "snapshot before I stop", "where am I", "wrap up the session for handoff", or before a long break / model switch / collaborator handoff. Companion to (NOT replacement for) the narrative session-log workflow.
Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data description, formats/metadata, storage/backup, access/sharing, preservation/archiving, and roles. Use when user says "data management plan", "DMP", "DMSP", "NIH data sharing plan", "write the data plan for my grant", or when a grant proposal needs a data-management section. NOT a submission tool — produces a draft the user pastes into the funder portal (DMPTool, NIH ASSIST, Horizon Europe portal).
Create a new Beamer lecture `.tex` from source papers and materials, with notation consistency checks and the project's preamble wired in. Use when user says "create a lecture on X", "new lecture from these papers", "start a deck on topic Y", "scaffold a new Beamer file", "build me a lecture from these PDFs". Scaffolds the full deck — NOT for compiling existing `.tex` (use `/compile-latex`).
Root-cause a failing or wrong empirical result with a disciplined reproduce → minimise → hypothesise → instrument → fix loop, instead of guessing-and-poking. Use when the user says "why is my regression wrong", "this number changed", "my script errors out", "the result won't reproduce", "debug this", "this estimate looks wrong", or "it worked yesterday". Tuned for research code (R/Stata/Python): type coercion, NA/merge blow-ups, factor levels, clustering/SE choices, weighting, collinearity/convergence, seeds, package-version drift. Use `--no-fix` to localize the root cause without editing shared or load-bearing files.
Render Quarto `.qmd` slides to HTML and sync to `docs/` for GitHub Pages. Use when user says "deploy", "publish the slides", "ship to pages", "push the lecture live", "render and publish", or after Quarto edits that need to go public. NOT for local Quarto render only — use `quarto render` directly for that.
End-to-end R data analysis pipeline — exploration → cleaning → regression → publication-ready tables and figures. Use when user says "analyze this dataset", "run a regression on X", "explore this CSV", "full analysis workflow", "get me summary stats and a regression", or points at a `.csv`/`.rds`/`.dta` and asks for empirical results. Produces numbered R scripts in `scripts/R/` and outputs to `scripts/R/_outputs/`.
Run a staggered difference-in-differences / event-study analysis to the Sant'Anna practitioner standard — drives the canonical packages (R `did`/`DRDID`/`didFF`/`contdid`; Stata `csdid`/`drdid`), enforces the doubly-robust default, a mandatory diagnostic + sensitivity suite, uniform-band inference, replicate-and-verify-against-source discipline, and ends in a graded credibility verdict. Use when user says "run a DiD", "event study", "staggered adoption", "Callaway Sant'Anna", "att_gt", "csdid", "did with multiple periods", or points at panel data with a treatment-timing variable. NEVER reimplements an estimator.
| Deep consistency audit of the entire repository infrastructure. Launches 4 parallel specialist agents to find factual errors, code bugs, count mismatches, and cross-document inconsistencies. Then fixes all issues and loops until clean. "audit", "find inconsistencies", "check everything".
Adversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load, motivation. Use when user says "devil's advocate", "poke holes in this deck", "push back on my slides", "stress-test the design", "what would a skeptical student ask?". Read-only; surfaces questions to force rethinking. Lighter than `/pedagogy-review`.
Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an `/interview-me` spec, delegates the data-management plan to `/data-management-plan` and the facilities statement to `/capture-environment`, and emits a funder-requirements checklist. Use when user says "draft a grant", "write a proposal", "NSF proposal", "NIH aims", "ERC application", "foundation grant", "specific aims", or "scaffold a grant proposal". NOT a submission tool — produces a draft the user uploads to the sponsor's portal themselves.
Claude Skills — questions
Answers built from the skills we actually parsed.