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. 86 696 files from 2 113 authors, of which 68 413 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.
Create rich HTML documents for project specs, implementation plans, design exploration, RFCs, and brainstorming. Use whenever the user asks for a spec, plan, RFC, design doc, brainstorm, or wants to explore approaches/options/alternatives — even when they don't explicitly say "HTML". Strongly prefer HTML over markdown for any planning artifact longer than a screen, especially when the artifact will be shared with reviewers or fed back to the agent for implementation.
Generate keyboard-navigable HTML slideshow decks for presentations, tech talks, leadership briefings, onboarding walkthroughs, and any sequential visual narrative. Use whenever the user wants slides, a deck, a presentation, a tech talk, a brown-bag, a briefing, or any sequential walkthrough — especially when they want to share via a link rather than as a PowerPoint or Keynote file. Prefer HTML over .pptx whenever the deck contains live code, embedded interactivity, or will be shared as a URL.
>- Tears down server mode for html-skills for THIS Claude Code session — kills the receiver, stops the `Monitor` armed by `html-skills-listen`, and cleans up its temp files. Parallel sessions are unaffected. Invoke when the user is done with interactive html-skills artifacts ("I'm done with html-skills", "stop the listener", "end html-skills session"), OR at session end if the user mentions cleanup. Safe to invoke when nothing is active — it reports inactive and exits.
>- Sets up the per-session local receiver and `Monitor` for interactive html-skills artifacts so user submissions arrive as session notifications instead of as copy-paste round-trips. Other html-skills interactive skills (html-mind-map, html-throwaway-editor, html-brainstorm-grid, html-comparison-matrix, html-interactive-playground, html-design-prototypes, html-testing-checklist) invoke this skill from their pre-flight block, BEFORE writing the HTML artifact. Idempotent — safe to invoke every time. Returns a localhost URL the parent skill injects as `window.__CLAUDE_SUBMIT_URL__` in the artifact. Don't invoke unprompted in unrelated conversations — this only fires when an interactive html-skills artifact is about to be produced.
Create SVG-based technical diagrams inside HTML — flowcharts, sequence diagrams, state machines, data-flow diagrams, dependency graphs, request/response timelines. Use whenever the user wants to visualize, illustrate, diagram, or sketch a technical concept, system, or process. Strongly prefer SVG over ASCII art, mermaid blocks, or markdown text for anything spatial or relational. Reach for this whenever an explanation involves arrows, boxes, layers, or sequencing — even when the user doesn't say "diagram".
Generate thorough, interactive HTML testing checklists that help developers and testers systematically verify software — a real test plan organized into end-to-end flows, with a prominent progress bar, pass/fail/blocked step states, filter and search navigation, and syntax-highlighted code and command snippets. Always ends with a Submit button (calls `submitToClaude`) so results come back to the agent for failure triage and fixes. Use whenever the user wants to test, QA, verify, or validate a change, feature, release, PR, or bug-fix batch — "help me test this", "test plan", "QA checklist", "verification checklist", "smoke-test list", "regression checklist". Bug lists in issue trackers (Monday, Linear, Jira, GitHub…) are natural input — render the open items as a two-way checklist whose rows keep ticket ids, and offer to write verdicts back to the tracker after Submit. Every embedded snippet passes a redaction step so credential-shaped values never land in the artifact.
Build single-purpose, throwaway HTML editors for one specific piece of data — drag-and-drop boards, form-based config editors, side-by-side prompt tuners, dataset curators, annotation tools. Always end with a Submit button (calls `submitToClaude`) so the result can be sent back to the agent. Use whenever the user wants to triage, reorder, edit, annotate, curate, prioritize, or pick values where typing prose would be tedious — Linear tickets, feature flags, prompts, datasets, transcripts, anything. Secret values (API keys, tokens, passwords) are never embedded verbatim — they are masked to references; the artifact and submit payload carry key names and masked previews only.
Create HTML timelines and roadmaps with status pills, dependency arrows, and milestone markers — for quarterly planning, project retrospectives, release histories, incident timelines, sprint visualizations. Use whenever the user wants to visualize a sequence of events over time, a plan, a roadmap, a release schedule, or look back at how a project unfolded. Reach for this whenever the explanation has a clear time axis, even if the user doesn't say "timeline".
Create and revise HyperFrames HTML video compositions with CSS, GSAP timelines, composition IDs, reusable components, render commands, and proof-frame validation. Use when an agent needs to build a scene, edit a composition, render HyperFrames output, or debug HyperFrames-specific scene behavior.
Preserve visual continuity across video scenes with previous-final-frame starts, camera swipes, carryover frames, transition QA, and boundary proofing. Use when a scene must begin from the exact last frame of a previous scene, when adding camera-move transitions, when replacing scene endings, or when debugging stale starting frames.
Generate, style, preview, and burn captions, and build music/percussion beds with ducking, loop/tail selection, fade-outs, and final silence. Use when captions are requested, captions are out of sync, subtitle style needs approval, background music competes with voiceover, or music must start/end at exact moments.
Integrate raw product demo recordings into agent-created videos, including crop decisions, zoom preservation, camera swipe transitions, UI readability checks, and timing around narration. Use when a user provides screen recordings, product walkthrough clips, SaaS demos, app footage, browser recordings, or asks to transition into/out of product demo footage.
Build and revise FFmpeg-based video assemblies from scene renders and narration, including audio probing, scene retiming, pauses, trim/concat, setpts, atempo, phrase-to-visual cue alignment, and final timeline manifests. Use when narration length, visual beats, product moments, or scene boundaries must sync precisely.
End-to-end video production workflow for coding agents using HyperFrames, FFmpeg, captions, audio sync, music beds, and render QA. Use when a user asks for a complete video, multi-scene edit, launch video, product/demo video, UGC-style edit, enterprise explainer, or final assembled MP4 from prompt/script/assets.
Verify final video renders and make tiny safe edits without breaking approved sync, including proof frames, contact sheets, media probing, stale theme scans, exact timestamp checks, carryover-frame refreshes, and re-render-only-affected-scenes workflows. Use when a user asks for final QA, HD/render verification, a small text/audio/color change, or regression checks after approved timing.
Reusable visual and motion design systems for agent-created videos, including premium motion language, glassmorphism, chart/data storytelling, CTA layouts, logo rows, table frames, color tokens, and brand consistency. Use when a video scene needs polished visual direction, Apple/VisionOS-style motion, enterprise design, theme cleanup, reusable components, or reference-image final-frame matching.
Convert rough video prompts, scripts, reference images, and edit notes into decision-complete scene specs and storyboards for agent-led video production. Use when a user describes a scene, gives timestamped narration, asks to preserve previous scenes, references a concept image, or requests a multi-scene video plan.
Analyzes successful product customers to identify patterns, then finds similar accounts that are good cross-sell candidates with fit scores and reasoning. Use when user asks "who should I pitch this product to", "find cross-sell opportunities", "which customers should buy Product X", "identify upsell targets", "product expansion candidates", or "who else would buy this".
Identifies potential duplicate Accounts, Contacts, or Leads in Dataverse using intelligent fuzzy matching that catches nicknames, abbreviations, phone format variations, and address similarities. Use when user says "find duplicates", "check for duplicate accounts", "are there any duplicate contacts", "duplicate detection", "clean up duplicates", "merge duplicates", or "data quality check".
Generates personalized outreach messages by pulling context from Dataverse records. Creates tailored emails for new prospects, re-engagement, follow-ups, or cross-sell. Use when user says "draft an email to [contact]", "write outreach for", "help me reach out to", "compose email", "re-engage this contact", "follow-up email", "prospecting email", or "outreach message for".
Delivers a prioritized morning summary covering today's meetings, overdue tasks, pipeline alerts, and recommended actions from Dataverse. Use when user says "what's on my plate today", "daily briefing", "morning summary", "what do I need to focus on today", "start my day", "daily digest", "today's priorities", or "what's happening today".
Analyzes opportunity data and activity notes to generate competitive intelligence including win/loss rates by competitor, patterns, and rep-ready battlecard talking points. Use when user asks "how are we doing against [competitor]", "competitive analysis", "competitor win rate", "battlecard for [competitor]", "competitive landscape", "why are we losing to [competitor]", or "competitor intelligence".
Generates meeting briefings by aggregating account info, contacts, opportunities, cases, and activity history into structured prep documents with talking points and discovery questions. Use when user says "prep me for my call", "brief me on this account", "meeting prep", "I have a meeting with [company]", "account briefing", "customer briefing", or "prepare for customer meeting".
Generates customized sales assets including one-pagers, proposals, executive summaries, ROI summaries, and mutual action plans from Dataverse context. Use when user says "create a one-pager", "draft a proposal", "generate executive summary", "build ROI summary", "create mutual action plan", "sales asset for [account]", "proposal outline", or "customer-facing document".
Identifies accounts showing warning signs of churn by analyzing activity trends, support cases, and engagement signals. Scores risk and prioritizes intervention targets. Use when user asks "which accounts are at risk", "churn risk analysis", "find accounts that might leave", "customer health check", "at-risk customers", "retention warning signs", or "account health score".
Creates comprehensive handoff documentation for sales reps going on vacation or transitioning deals. Generates structured briefs with deal status, activities, next steps, contacts, and risks. Use when user says "I'm going on vacation", "create handoff brief", "coverage brief for my deals", "vacation handoff", "out of office brief", "transition my deals", or "backup documentation".
Processes expense receipts and creates expense report entries following company policies with approval thresholds and validation rules. Use when user says "log this expense", "process this receipt", "create expense entry", "submit expense", "add to expense report", uploads a receipt image, or provides purchase documentation to expense.
Analyzes an opportunity's current state and engagement history, compares against won deals, and recommends the most effective next action with reasoning. Use when user asks "what should I do next on this deal", "next steps for this opportunity", "how do I move this deal forward", "what's the best action for this opp", "deal coaching", or "opportunity next action".
Guides sales reps through structured lead qualification using BANT+ methodology. Evaluates leads, suggests discovery questions, scores quality, and recommends next steps. Use when user says "qualify this lead", "help me qualify", "BANT analysis", "score this lead", "should I convert this lead", "lead qualification questions", or "assess lead quality".
Analyzes sales call transcripts to extract key information and automatically logs the call as a Phone Call activity in Dataverse. Use when user says "log this call", "process this transcript", "save this call to CRM", "create a phone call record from this transcript", uploads a call recording transcript, or pastes meeting/call notes to be logged.
Generates a weighted sales forecast from Dataverse opportunity data. Calculates committed, best-case, and pipeline views by rep and team; compares to quota; flags risks and upside. Use when user asks "what's my forecast", "quarterly forecast", "pipeline forecast", "where's my number", "forecast report", "am I going to hit quota", "sales projection", or "revenue forecast".
Analyzes closed opportunities to identify patterns between won and lost deals. Compares sales cycles, activities, stakeholder engagement, and deal characteristics for actionable playbook insights. Use when user asks "why are we losing deals", "win loss analysis", "what makes deals win", "analyze lost opportunities", "sales pattern analysis", "compare won vs lost deals", or "improve win rate".
Reviews opportunities in the sales pipeline to identify stuck deals, missing next steps, weak qualification, and unbalanced stages. Use when user asks "how is my pipeline looking", "analyze pipeline health", "which deals are stuck", "pipeline review", "find at-risk deals", "identify stalled opportunities", or "audit my open deals".
Helps create a GitHub issue that strictly follows the conventions in CONTRIBUTING.md. Use this skill when asked to create, draft, or open a GitHub issue or bug report.
Helps review your own pull request or local changes before opening a PR. Analyzes diffs against project conventions and checks out branches locally to ensure you can apply changes. Requires the `gh` and `git` CLI tools.
Use this skill when asked to write or draft a commit message. It ensures commit messages follow the conventions in CONTRIBUTING.md.
Investigates an Autophysicist workspace run. Use to understand what went wrong and could be improved in the single-agent iterative research process.
Use when scraping JavaScript-heavy pages or SPAs, crawling multiple URLs concurrently, extracting structured data with reusable CSS/JSON schemas, or building automated web data pipelines. Wraps the Crawl4AI library (`crwl` CLI and Python SDK) with schema-generation patterns for LLM-free extraction. Triggers on crawl4ai, crwl, scrape JS-heavy site, scrape SPA, headless browser scrape, schema-based extraction, batch crawl, sitemap crawl, web data pipeline. SKIP when a static HTML page can be read with `defuddle` / `fetch-web` — those are faster cold-start and don't need a browser.
Generate A-share end-of-day market review reports with Pandadata data, covering trade-date checks, index performance and valuation, market breadth, limit-up/down sentiment, industries/concepts, 龙虎榜, block trades, margin financing, northbound holdings, risk notes, and optional scheduled after-close automation. Use when the user asks for 今日复盘, 收盘总结, 每日市场报告, A股复盘, 龙虎榜复盘, 北向资金动向, or to set up an automated daily market review.
| Transform any research material into SEO+GEO-optimized blog posts for Knox Hub. Takes any input (URL, article text, notes, video transcript, competitor post, topic idea) and rewrites it as natural human-sounding content, then fills in table of contents, sticky sidebar, and full article content in Markdown. Output is ready to copy-paste into your blog/CMS post editor. Use when asked to "write a post", "rewrite this", "сделай пост", "напиши статью", "перепиши это для блога", "create blog post", or any content creation task.
Analyze playwright test results
Based on the Recursive Language Models (RLM) research by Zhang, Kraska, and Khattab (2025), this skill provides strategies for handling tasks that exceed comfortable context limits through programmatic decomposition and recursive self-invocation. Triggers on phrases like "analyze all files", "process this large document", "aggregate information from", "search across the codebase", or tasks involving 10+ files or 50k+ tokens.
A comprehensive design operating system synthesized from 10 canonical design books. Covers research, typography, color theory, composition, branding, logo design, storytelling, web design, creative process, and professional practice.
A comprehensive design operating system synthesized from 10 canonical design books. Covers research, typography, color theory, composition, branding, logo design, storytelling, web design, creative process, and professional practice.
Practical guidance for choosing, writing, loading, and debugging eBPF programs. Prioritizes correct toolchain and hook selection, map choice, kernel-version fit, verifier triage, and concise production-ready examples using libbpf, ebpf-go, and bpftrace.
Helps agents develop, review, test, secure, optimize, design, integrate, package, and release modern WordPress plugins. Use for WordPress plugin architecture, Gutenberg block work, block.json, REST API, WP admin screens, shortcode implementation, Settings API, WP-CLI workflows, PHPUnit tests, wp-env environments, Plugin Check, WordPress.org release preparation, security audit, performance optimization, plugin UI/UX design, Classic Editor compatibility, SEO/cache/theme/page-builder integrations, and compatibility audits.
| Call local Grok CLI, Kimi Code CLI, and Claude Code CLI with the strongest current default models and native tools. Use this qiaomu skill workflow when the user wants to run Grok 4.5 for X/web search, image/video generation, research, or multi-tool agent work; run Kimi K3 (1M) for frontend UI/CSS/React/Vue work; run Claude Fable 5, Opus 4.8, or Sonnet 5 for coding/review/refactors; run independent multi-model comparisons concurrently with native stream progress, artifact verification, private logs, cancellation, and failed-job retry; choose between the three CLIs; or wrap non-interactive CLI invocations. Trigger on phrases like "用 grok cli", "用 kimi cli", "grok 搜 X", "kimi 写前端", "qiaomu-model-cli", "调用 grok4.5", "调用 k3 1m", "用 claude code", "用 fable 5", "opus 4.8 改代码", "分别调用三个模型", "多模型横评". Not for generic cloud API registry management (use qiaomu-llm) or OpenCLI site adapters.
用精简流程帮你从想法进入 spec、design、build，并按需执行 QA 与发布门禁。
Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.
Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.
Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
Use when a spec needs customer-facing UX, visual direction, screen acceptance, design references, formal assets, Figma handoff, or design gates before build.
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.
Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
Use when building, modifying, or reviewing user-facing UI, responsive states, accessibility, visual fidelity, functional QA, monkey testing, or product-grade frontend polish.
Refines ideas iteratively. Refine ideas through structured divergent and convergent thinking. Use "idea-refine" or "ideate" to trigger.
Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing.
Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.
Claude Skills — questions
Answers built from the skills we actually parsed.