Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Create HTML technical documentation with code blocks, API workflows, system architecture diagrams, and syntax highlighting. Use when users request technical documentation, API docs, API references, code examples, or developer documentation.
Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch/PR diff audits focused on bugs, breaking changes, security issues, devex regressions, and feature-gate leaks.
Create production-grade frontend interfaces with strong UX and visual craft. Use when building web components, pages, dashboards, forms, landing pages, modals, or any UI. Use when user says 'build a form', 'create a dashboard', 'design a component', 'make a landing page', or asks for UI/UX work. Use even when the user just says 'make this look better' or pastes screenshots/mockups without explicitly naming a design task.
Generate UTM-tagged URLs for campaign tracking. Create consistent, organized tracking links for Google Analytics, HubSpot, and other analytics platforms. Supports bulk generation, naming conventions, and campaign documentation. Use when creating tracking links, campaign URLs, or organizing marketing attribution.
Create, switch, list, show, rename, or delete wuji SDK user profiles, and export/import calibration bundles (hand model + tactile model) between machines, all via the `wuji user` CLI. These are named calibration profiles under ~/.wuji — NOT operating-system accounts — so use this skill (never edit code or touch OS users) for any request to delete a user, switch/change the current user, rename a user, create or list users, resolve the 'default user cannot calibrate' block, or move/inspect calibration data. Delete and import are destructive; the skill covers the safe, confirmation-first way to run them.
Generates xUnit.net tests in C#. Covers Fact/Theory, constructor injection, IClassFixture, and FluentAssertions. Use when user mentions "xUnit", "[Fact]", "[Theory]", "Assert.Equal", "C# xUnit". Triggers on: "xUnit", "[Fact]", "[Theory]", "Assert.Equal C#", "xUnit.net".
Use when you need to create a new Maven-based Spring Boot 4.0.x project using SDKMAN-managed Java and Spring Boot CLI tooling. This should trigger for requests such as Create a Spring Boot Maven project; Bootstrap Spring Boot project with SDKMAN; Generate a new Spring Boot service; Create Spring Boot 4 Maven project; Scaffold Spring Boot service with Java 25. Part of Plinth Toolkit
Provides framework-agnostic Docker and container image guidance for Java projects, including Dockerfile design, multi-stage Maven builds, jlink custom runtimes, micro runtime distributions such as Alpaquita, JVM container ergonomics, non-root execution, image metadata, .dockerignore, reproducible builds, vulnerability scanning, SBOM awareness, and production-safe container defaults. Use for requests such as reviewing a Java Dockerfile, improving Docker image security, adding a jlink runtime to a Java container, containerizing a Java project, optimizing Java container image size, or reviewing Docker build reproducibility. Part of Plinth Toolkit
Builds Airtable filters parameters for the MCP tools that list or display records — field-type-aware comparison operators, choice and collaborator IDs, date ranges, and nested AND/OR logic. Use when the user wants to find, filter, narrow down, or search Airtable records by field values, even when they don't explicitly say "filter."
Creates and retrieves AI video and image-related assets via the Arcads external API (Seedance 2.0, Sora 2, Veo 3.1, Kling, Grok Video, Nano Banana, b-roll, scene, script/actor flows). Loads prompts from the bundled prompting guide and model library, respects HTTP Basic auth from ARCADS_API_KEY, and polls assets/videos until ready. Use when the user mentions Arcads, external-api.arcads.ai, Seedance, Sora2, Veo, Kling, Nano Banana, b-roll, UGC scripts, or generating marketing creative through Arcads.
Universal archivist for personal file archives (Dropbox/B2/Gmail-takeout/local-mount/hard-drive-dump). Filters for high-value content (the user's own writing, ideas, relationships) and surfaces it interactively. REFUSES TO RUN without an explicit gbrain.yml `archive-crawler.scan_paths:` allow-list.
Design and build complete web experiences from scratch—award-level product and marketing pages, cinematic scroll-directed sites where the page is directed like a film, and multi-screen products (app, dashboard, admin, settings, onboarding, docs site) built as one design system with every component, state, and route in one style. Use whenever the user wants to create or redesign a landing page, website, hero section, portfolio, promo or product page; wants scroll animations, storytelling pages, or a site that feels like a movie; or says “make it beautiful”, “make it wow”, “cinematic”, or “design system”—even if they name no technique. Generates its own assets via local CLIs (images, video frames, depth maps, 3D), and gates every ship with an executable anti-slop linter and a screenshot verification loop. Not for polishing a UI someone else built, and not for backend-only work.
AWS cost optimization and FinOps workflows. Use this skill whenever the user mentions AWS costs, cloud spending, FinOps, Reserved Instances, Savings Plans, or cost reduction. Triggers include finding unused resources, analyzing the AWS bill, rightsizing EC2 or RDS instances, evaluating Spot instances, detecting cost anomalies, migrating to Graviton or newer instance generations, implementing tagging for cost allocation, setting up AWS Budgets, conducting monthly cost reviews, comparing RI vs Savings Plans, and optimizing storage, network, or database costs.
Use when layouts need to adapt to different screen sizes, iPad multitasking, or iOS 26 free-form windows — decision trees for ViewThatFits vs AnyLayout vs onGeometryChange, size class limitations, and anti-patterns preventing device-based layout mistakes
Formats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use when user asks to "format markdown", "beautify article", "add formatting", or improve article layout. Outputs to {filename}-formatted.md.
Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). Use when implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, instant navigation validation, 'use cache: private', pass-through/interleaving patterns, GET Route Handler caching, debugging cache issues, and reviewing Cache Component implementations.
Generate complete character sprite sheets for the Claude Office Visualizer agents. Creates all animation frames (idle, walking, typing, handoff, coffee) with consistent character design across all sheets. Uses an iterative approval workflow and reference-based generation for consistency.
Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up slow pandas. Provides chDB DataStore — same pandas API, ClickHouse engine underneath. Also handles reading from S3, MySQL, PostgreSQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake as DataFrames and joining across sources. TRIGGER when: user mentions DataFrame, parquet, csv, "fast pandas", "speed up pandas", or cross-source DataFrame joins; user imports `chdb.datastore` or `from datastore import DataStore`. SKIP this skill for raw SQL syntax (use chdb-sql instead), ClickHouse server administration, or non-Python DataStore API work.
Day-one data bootstrapping for a new brain. Sequences the highest-leverage data sources to go from empty brain to useful brain in one session. Uses ClawVisor for safe credential handling — the agent never holds raw API keys. Covers Gmail import, calendar sync, contacts seeding, X/Twitter archive, conversation imports, and file archives. Use when a user has just finished gbrain setup and asks "now what?"
Makes AI-generated prose sound natural and human-written. Covers tone analysis, sentence variation, voice consistency, readability improvement, and AI-typical pattern removal including hedging, filler words, and over-qualification. Use when improving blog posts, marketing copy, or narrative documentation. Use for tone consistency, readability, sentence rhythm, and removing AI-typical writing patterns.
End-to-end Cordova-to-Capacitor migration orchestrator. Analyzes the Cordova plugin (plugin.xml, native iOS/Android source, JS bridge, hooks, third-party dependencies), produces a structured migration plan as YAML conforming to capacitor-plugin-generator's input contract, invokes the generator skill in structured mode at a user checkpoint, then consolidates intermediate notes into a single MIGRATION.md. Use when the user says "migrate this cordova plugin", "convert cordova to capacitor", "assess migration feasibility", "what blocks this migration", "port this cordova plugin to capacitor", or "estimate the effort to migrate". Do not use for generating new Capacitor plugins from scratch (use capacitor-plugin-generator instead), debugging runtime issues in an already-migrated plugin, or migrating an entire Cordova application; scope is plugin-level only.
Audits designs across 19 professional categories including typography, color/contrast, spacing, visual hierarchy, consistency, WCAG, forms, motion, dark mode, responsive, loading/empty/error states, microcopy, i18n/RTL, elevation, iconography, navigation, design tokens, ethical design/dark patterns, and Nielsen heuristics. Scores 0-100 with severity-ranked issues.
Helps users discover, search and install agent skills from the marketplace. Use when the user wants to find a skill, discover new capabilities, find specific tools (especially sandboxes) or install a skill. This skill should be used when the user is looking for functionality that might exist as an installable skill. Also supports progressive disclosure to recommend sandbox-related skills when relevant. 用于帮助用户在市场中搜索、发现和安装 Agent 插件（Skills）。 当用户想要查找功能、安装特定工具或寻找沙箱（sandbox）时使用。 Triggers: "查找插件","搜索技能","搜索 X 技能","安装技能","安装 X 技能","如何做 X","沙箱","安全沙箱","find a skill for X", "how do i do X", "search for skill", "install skill", "I need a skill for X", "sandbox", "aio sandbox"
Find feature flags that were soft-deleted in the active project within a recent time window. Use when the user asks "what flags were deleted in the last N days", "show me recently deleted feature flags", "who deleted flag X", "audit recent flag deletions", or anything similar. Handles the non-obvious gotcha that system.feature_flags exposes the deleted boolean but does not expose a deletion timestamp — the actual deleted-at time lives in the per-flag activity log and must be cross-referenced.
End-to-end remediation workflow for PR review feedback by PR number. Use when Codex must export CodeRabbit issues for a PR, fix every issue completely, commit all fixes in a single commit, and resolve GitHub review threads afterward. Don't use for general PR reviews unrelated to CodeRabbit, draft PRs without review threads, or merge-strategy decisions.
Eight aesthetic anchors (Swiss, Industrial, Brutalist, Aurora Maximalism, Chaotic Maximalism, Retro-Futuristic, Organic, Lo-Fi), each locking palette, typography, and texture to specific CSS tokens. Pick one per brief and the skill generates matching code, with a content rule against fabricated demo data and filler labels.
Read and manage Google Calendar events, agendas, free-busy status, and invitations via the Calendar v3 REST API. Use when the user mentions Google Calendar events, today's agenda, this week's meetings, finding conflicts, listing invitations, checking free time, or scheduling, rescheduling, or cancelling a meeting.
SUPERSEDED by /claudex-loop (formerly /crucible; adds a Phase 0 research/recon pass + rebuilt interview) — prefer that skill unless you explicitly want this one. Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of the decision tree is resolved. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE); Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-me-codex", "grill me then have codex review", "grill me and stress-test the plan", "interview me about this plan then get a second model on it", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants both alignment AND a cross-model sanity check before implementation. Builds on Matt Pocock's grill-me (MIT). For the docs-aware variant use /grill-with-docs-codex; if you already have a plan and want only the Codex review use /codex-review. NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes
Consolidate PostHog error tracking issues that are the same actual error reported under different fingerprints. Use when the user asks "why do I have so many TypeError issues that look the same?", "merge these duplicates", "stop splitting this error into new issues", or wants to clean up fingerprint sprawl. Decides between a one-shot merge of existing issues and a durable grouping rule that keeps future events from creating new fingerprints. Does NOT group conceptually similar bugs across different runtimes, SDKs, or call sites.
Design a project-specific harness and create specialist agents and the skills they use. Use when the user asks to configure, build, or design a harness, engineer a harness, or create an agent team. Also use when building an automation system for a new domain or project, or restructuring or extending an existing harness. Use for operating or maintaining an existing harness, such as harness checks, audits, status reviews, or agent/skill synchronization. Use the harness:evolve skill to review execution results and incorporate feedback.
HTML PPT Studio — author professional static HTML presentations in many styles, layouts, and animations, all driven by templates. Use when the user asks for a presentation, PPT, slides, keynote, deck, slideshow, "幻灯片", "演讲稿", "做一份 PPT", "做一份 slides", a reveal-style HTML deck, a 小红书 图文, or any kind of multi-slide pitch/report/sharing document that should look tasteful and be usable with keyboard navigation. Triggers include keywords like "presentation", "ppt", "slides", "deck", "keynote", "reveal", "slideshow", "幻灯片", "演讲稿", "分享稿", "小红书图文", "talk slides", "pitch deck", "tech sharing", "technical presentation", "피피티", "발표자료", "발표 자료 만들어줘", "슬라이드 만들어줘", "카드뉴스", "발표 대본", "프레젠테이션".
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 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
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.