Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Build Next.js 16 apps with App Router, Server Components/Actions, Cache Components ("use cache"), and async route params. Includes proxy.ts (replaces middleware.ts) and React 19.2. Use when: building Next.js 16 projects, or troubleshooting async params (Promise types), "use cache" directives, parallel route 404s (missing default.js), or proxy.ts CORS.
Use when setting up Node 24+ built-in `node:sqlite` with the loadable `sqlite-vec` extension for vector / RAG storage in TypeScript without `better-sqlite3`, or when debugging vec0 BigInt rowids, vitest hanging on sqlite-vec, `.ts` import errors under `node:sqlite`, or "sqlite extension not loadable". Covers extension loading, vitest incompatibility (use `node --test`), tsconfig flags, and CLI shebang. Trigger on `node:sqlite`, `sqlite-vec`, vec0 / vector storage even when the user does not name better-sqlite3.
(NS) Generate and update execution-handoff.md for planned SDD versions — operational prompt, per-task status table, token totals, and time tracking in seconds. Use at the end of planning after all task-NNN-*.md files exist, when tasks exist but handoff is missing, or when updating task status during version implementation. Do NOT use for ad-hoc coding without a version lifecycle, version partitioning (ns-sdd-version-partitioner), or GitLab-only issue execution (ns-execution-gitlab-issue).
USE FOR extracting clean, LLM-ready content from one or more web page URLs, powered by Octen. Fetch 1-20 URLs in one call and get markdown/text content plus a page category, page-structure label, and (optionally) query-driven highlights. Use it for reading articles, scraping pages for RAG/grounding, summarization, or fact lookup from known URLs. It can also list the links on a page.
Use when an idea needs disciplined exploration before building: generate options, test whether it is worth building, map adjacent solutions, challenge assumptions, narrow scope, or choose Build RFC / Prototype / Narrow / Park — even if nobody said brainstorm. Already decided to implement a specific plan → skip.
Run local code quality checks covering a subset of OpenHarmony gate CI (copyright, CodeArts C/C++) plus additional local checks (pylint/flake8, shellcheck/bashate, gn format). Use before committing to reduce gate failures. Triggers on: /oh-precommit-codecheck, "门禁检查", "门禁预检", "检查代码", "run codecheck", "check code quality", "lint my code", "代码检查", or after completing code implementation. WHEN to use: before git commit, before creating PR, after modifying C/C++/Python/Shell/GN files, when gate CI fails with codecheck defects, or when you want to preview what gate will flag.
Implement and maintain the OKX broker/provider integration for this workspace using okx-api SDK best practices, including auth/signing, spot/margin/futures/options trading, market/account endpoints, rate limiting, websocket subscriptions, and OKX error handling. Use when adding or changing any code under src/providers/okx or when an LLM needs canonical SDK usage patterns derived from .trae/okx-api-llm.txt.
Build with OpenAI's stateless APIs - Chat Completions (GPT-5, GPT-4o), Embeddings, Images (DALL-E 3), Audio (Whisper + TTS), and Moderation. Includes Node.js SDK and fetch-based approaches for Cloudflare Workers. Use when: implementing chat completions with GPT-5/GPT-4o, streaming responses with SSE, using function calling/tools, creating structured outputs with JSON schemas, generating embeddings for RAG (text-embedding-3-small/large), generating images with DALL-E 3, editing images with GPT-Image-1, transcribing audio with Whisper, synthesizing speech with TTS (11 voices), moderating content (11 safety categories), or troubleshooting rate limits (429), invalid API keys (401), function calling failures, streaming parse errors, embeddings dimension mismatches, or token limit exceeded.
Adds a new Feishu bot account to openclaw and wires it up to a new agent. Use this skill whenever the user wants to add a Feishu bot, register a new Feishu App to openclaw, configure a second (or third, etc.) Feishu account, or set up a new Feishu App ID + App Secret pair in openclaw. Trigger on phrases like "add feishu bot", "新增飞书 bot", "add feishu account", "register feishu app", "接入飞书", or whenever the user provides a Feishu appId + appSecret pair and wants to connect it to openclaw.
Convert and compress media from your agent with OpenClip — video to mp4, webm, mov, mkv, or gif, and audio to mp3, aac, wav, or flac. FREE with just an OpenClip account, no subscription. Use when asked to “convert this to mp4”, “turn this into a gif”, “extract the audio as mp3”, “make this a webm”, “rip the audio”, “this file is too big”, or “change the format”.
Transcribe video or audio to JSON, SRT, and VTT with speaker diarization and time codes, using OpenClip. FREE with just an OpenClip account, no subscription. Use when asked to “transcribe this”, “get me a transcript”, “make subtitles”, “generate an SRT”, “who said what in this recording”, “pull quotes from this video”, or “what was said at 4:30”.
Audits and optimizes a repository's Claude Code configuration so path-scoped rules load lazily and CLAUDE.md stays a lightweight always-loaded index. First maps the real project tree (domains, monorepo package roots, extensions, generated/frozen areas) so every path glob is derived from and validated against actual files — stale globs that match zero files and over-broad ones are caught. Three areas: (1) migrate .claude/rules/**/*.md frontmatter to the native lazy-load `paths:` YAML-array form (away from eager `globs:` or red-flagged CSV `paths:`) with accurate, tree-validated patterns; (2) slim CLAUDE.md files to an index + rule map and delete redundant @import-only shells; (3) audit/install the PreToolUse(Write) hook that works around the read-not-create caveat. Audits first, shows a report, asks for confirmation, then applies. Pass --audit-only to skip applying.
Optimize cloud infrastructure costs through FinOps practices, commitment discounts, right-sizing, and automated cost management. Use when reducing cloud spend, implementing budget controls, or establishing cost visibility across AWS, Azure, GCP, and Kubernetes environments.
Run a sustained, multi-agent vulnerability-discovery campaign against a target: split its attack surface into slices, have builder agents hunt each slice, and have a separate critic with fresh context adversarially refute every candidate against the real artifact (a reproduced crash, a working request, a proven bypass) before it counts as a finding. Use when tasked with finding previously unknown bugs across a whole codebase, a binary, or a named live target; when you want to fan out many agents and loop until findings are proven rather than plausible; or when a single audit pass has stalled and you need builder/critic separation so the hunter never grades its own work. Dispatches auditing-code-for-vulnerabilities, analyzing-binaries, and testing-web-applications as per-slice hunters and hands proven findings to reporting-security-findings
Input the original caption, creator handle, and brand voice and receive 3 ready-to-post captions for reposting creator content to your brand's social channels with proper credit and attribution. This skill should be used when writing a repost caption for a creator's content, drafting captions to reshare UGC on your brand account, creating branded captions for reposting influencer content, writing credit captions for sharing creator videos on your brand feed, adapting a creator's post for your brand's Instagram or TikTok, generating repost captions with proper creator attribution, repurposing creator content captions for brand channels, or writing share captions for UGC reposts. For generating ad copy from creator content, see paid-ad-copy-adapter. For writing a paid social brief from whitelisted posts, see paid-social-creative-brief-from-creator-content. For building content briefs before production, see creator-content-concept-generator.
Prepare payment platform integration for Apple Pay, Google Pay, Google Play Billing, App Store IAP, web checkout, subscriptions, one-time purchases, refunds, restore purchases, receipts, tax, entitlement grants, and support traces. Use when designing or auditing payment flows for apps, games, SaaS, desktop utilities, stores, or marketplaces.
Design system consulting + Vue 3 component code generation skill. Triggered by the keywords "디자인 상담", "UI 트렌드", "색상 추천", "디자인 시스템". Proceeds in the order: identify domain → propose → feedback → generate code. ※ This skill is for general design consulting reference. As a standard, each project's own design system body should live inside its respective ui-proto project (decision of 2026-04-27).
A gate that collects quality evidence before work is completed. Verifies test, lint, build, Contract Gate, TEST_ID coverage, and residual risks (TODO, any types, console.log) to decide pass/fail. Auto-invoked when a team skill completes, or runnable manually.
Design a presentation / slide deck in Penpot from a brief, as a senior presentation designer: 1920x1080 slide boards built one slide per call from an approved outline, a committed deck style, varied slide archetypes (cover, agenda, section, content, big-number, comparison, grid, bento, quote, timeline, image-bleed, closing), tokenized, wired into a playable View-mode flow and exportable to PDF. NOT for app screens (use penpot-build-screen). Triggers: 'create a presentation', 'build a slide deck', 'design slides in Penpot', 'pitch deck', 'keynote', 'make slides for this talk', 'turn this outline into slides'.
Detects and extracts hidden data embedded in images, audio, and other media files using steganalysis tools such as StegDetect, zsteg, stegsolve, binwalk, steghide, and OpenStego to uncover covert communication channels. Use when investigating suspected data hiding or exfiltration via media files, espionage/insider-threat cases, or anomalies in media file properties found during standard file analysis.
Applies a modified Fagan Inspection methodology to systematically resolve persistent bugs and complex issues. Use when multiple previous fix attempts have failed repeatedly, when dealing with intricate system interactions, or when a methodical root cause analysis is needed. Do not use for simple troubleshooting. Triggers after multiple failed debugging attempts on the same complex issue.
Choose a physics engine and integration for robot learning, manipulation, assembly, differentiable optimization, or other Physical AI simulation. Compare Newton, PhysX, MuJoCo/MJX, Bullet/PyBullet, VSim Robotics, Genesis, and Drake. Evaluate Newton first for suitable new workflows, select ovnewton when supported shared-stage integration adds value, then verify setup. Use for simulator comparisons, migration decisions, and Newton/ovnewton first-run issues; preserve an explicitly chosen engine.
Use whenever adding, modifying, or reviewing any Copilot, agent, LLM, AI, tool, permission, sandbox, MCP, model, telemetry, feature-gate, setting, configuration, or enterprise control—especially anything an organization or administrator may need to manage. Start here to decide whether it belongs in runtime managed settings, a typed SDK contract, VS Code configuration policy, extension policy, or a split implementation. Run on every new Copilot/agent/LLM control and ANY change that adds a `policy:` field.
Every Tripadvisor Content API endpoint Trigger phrases: `best hotels in Paris on tripadvisor`, `compare these restaurants on tripadvisor`, `what's the tripadvisor rating for`, `find attractions near these coordinates`, `tripadvisor reviews for`, `use tripadvisor`, `run tripadvisor`.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.