Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Review or design Claude Code project configuration. Use when the user mentions `.claude`, `CLAUDE.md`, Claude configuration files, project-level Claude custom configuration, whether the configuration structure is reasonable, which configuration files to create, or wants to plan Claude configuration from scratch. By default, review or diagnose first, then give a plan; only when the user explicitly asks, further output recommended structure or sample files.
Use when the user asks to generate or update a project's CLAUDE or AGENTS context file from a codebase scan. Writes a focused file under 100 lines containing only the non-obvious build commands, conventions, and gotchas Claude Code needs.
Watch a tutorial or lecture video (URL or local path) and produce structured study notes. Downloads with yt-dlp, detects scene changes with ffmpeg, pulls a timestamped transcript (captions or Whisper API fallback), and writes a section-by-section markdown notes file with embedded screenshots to ~/claude-watch/library/<slug>/.
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds", "case summary", or "patient presentation".
Store key-value data globally with Cloudflare KV's edge network. Use when: caching API responses, storing configuration, managing user preferences, handling TTL expiration, or troubleshooting KV_ERROR, 429 rate limits, eventual consistency, or cacheTtl errors.
Build async message queues with Cloudflare Queues for background processing. Use when: handling async tasks, batch processing, implementing retries, configuring dead letter queues, managing consumer concurrency, or troubleshooting queue timeout, batch retry, message loss, or throughput exceeded.
Chinese web novel writing instruction and coaching (beginner-friendly, opt-in). Use when the user wants to learn how to write web novels, asks about writing techniques, wants to analyze why a trope works, requests an edit with instructional feedback, or says “Teach me to write” or “I’m a beginner.” Appears only when explicitly invoked by the user and is never automatically inserted into other writing skills.
Use when checking code quality, running security audits, testing coverage, finding SOLID/DRY violations, or setting up quality tools. Use when user says "audit this code", "check security", "run PHPStan", "code quality", "find violations", "SOLID check", "DRY check", "test coverage", "lint this", "security review", "is this production ready", "check for vulnerabilities", "code review", "grade this code", "watch mode lint", "deep review", "ultrareview", "schedule quality sweep". Supports Drupal (PHPStan, PHPMD, Psalm, Semgrep, Trivy, Gitleaks via DDEV) and Next.js (ESLint, Jest, Semgrep, Trivy, Gitleaks). Use proactively before deployment or after significant code changes.
Frontend-focused code review skill for React/TypeScript/Tailwind projects. Analyzes code quality, security vulnerabilities (XSS, CSRF), performance issues, accessibility (WCAG), React best practices, hooks usage, component architecture, responsive design, and SEO. Use when users request code review, want feedback on components, ask about frontend security, performance optimization, or accessibility compliance. Provides actionable feedback with severity levels and fix suggestions.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
The reference merchant agent, covering its flows, staged changes and host approval, metrics grounding, the analysis delegate, store memory, components, and marketplace rules. Load when building or reviewing an agent for the operators of a store, property, subscriber base, or venue.
Implement a framework-agnostic version badge component with a tooltip showing build info (version, commit, branch, timestamp) and recent changelog entries. Use when the user wants to add a version display to their app header or footer, surface build information in the UI, expose recent changelog entries as a tooltip, or when they mention "version badge", "build info display", or "commit SHA in UI". Supports Next.js, Nuxt, SvelteKit, Vite+React, and plain React/Vue/Svelte.
Get compressed MP4 files ready to post, without touching a single slider. Upload your large video files (MP4, MOV, AVI, MKV, up to 500MB), say something like "compress this video to under 100MB without losing quality", and download 1080p MP4 when it's done. Built for content creators, marketers, students who move fast and want smaller file sizes without manually adjusting bitrate settings.
Check and configure Justfile with standard recipes for project standards. Use when setting up a new Justfile for a project, auditing an existing Justfile for missing standard recipes, migrating from Makefile to Justfile, or ensuring Justfile follows team conventions (groups, comments, settings). Natural triggers: "set up justfile", "migrate makefile to justfile", "add just recipes".
When the user wants to solve complex scheduling, allocation, or combinatorial problems using constraint programming (CP). Also use when the user mentions "constraint programming," "CP-SAT," "constraint satisfaction," "all-different constraint," "global constraints," "propagation," "search strategies," or when the problem has complex logical constraints, scheduling with disjunctive resources, or allocation problems. For MIP, see optimization-modeling. For metaheuristics, see metaheuristic-optimization.
When the user wants to turn one piece of content into many, repurpose a video/podcast/post for other platforms, create social posts from long-form content, or says things like 'repurpose this,' 'turn this into,' 'social posts from,' 'newsletter from this video,' 'clips from this.' Takes one input and multiplies it across platforms.
Content atomization — turn one piece of content into many formats. Covers blog-to-thread, blog-to-carousel, podcast-to-blog, video-to-quotes, and more. Use for: content marketing, social media, multi-platform distribution, content strategy. Triggers: content repurposing, repurpose content, content atomization, content recycling, one to many content, multi platform content, cross post, adapt content, reformat content, blog to thread, blog to video, podcast to blog, content multiplication
How team-level patterns flow up into Bitwarden's Technical Strategy Ideas backlog and back down through BW Initiatives into team epics and stories. Covers recognizing which team-level patterns belong in the TSI backlog, framing an idea well enough for Architecture to evaluate it, the ARCH idea ↔ BW Initiative linkage, and defining epic-level and story-level work downward from an initiative. Use when noticing a cross-team pattern of pain that exceeds one team's scope, when surfacing ideas to the architecture group, when understanding how an initiative connects back to its originating idea, or when breaking epic-level work out of an initiative onto a team.
qa-skills shared knowledge base—dependency, NOT triggerable: executability standards, evidence grading, risk model, type matrix, templates, scripts. Never invoke standalone; always install with the skills, or references break. Shared knowledge base (dependency unit, not a triggerable skill): holds methods, templates, and scripts referenced across the suite. Never trigger independently for any testing task; install alongside other skills.
When the user wants to consolidate the financial results of multiple legal entities into a single set of statements. Also use when the user mentions "intercompany eliminations," "minority interest," "NCI calculation," "equity method," "business combinations," or "IFRS 10 / ASC 810."
Count how many independent origins are behind news coverage of a claim, instead of counting URLs. Queries GDELT for matching articles, collapses reprints and wire copy into single origins, and flags publication bursts that indicate syndication. Use when a claim appears to be confirmed by many outlets and you need to know whether that's many sources or one source many times.
Build a Crowdin app end to end and leave the user with a published app they can click — scaffold it with @crowdin/serverless-apps-cli, write the UI with @crowdin/serverless-apps-sdk, publish it into their Crowdin or Crowdin Enterprise organization, and open it for them. Use whenever someone wants something of their own inside the Crowdin UI — a panel in the translation editor, a tool or report in a project, a page in the organization menu, a dashboard over their projects — and also when they describe a localization chore they are tired of doing by hand. Covers phrasings like "create a Crowdin app", "add a tool to my Crowdin project", a bare "/create-app", and cases where the word "app" is never said. Also use it when a serverless Crowdin app already exists in the working directory and needs another module, a manifest change, or a republish. Not for the separate Crowdin CLI that syncs sources and translations through crowdin.yml.
Create truthful, human-centered marketing campaigns for an app or product, including positioning, channel copy, original artwork, editable layouts, README banners, and selective website integration. Use when asked to make launch materials, promotional artwork, social assets, campaign kits, ads, or marketing content from an existing product; to adapt a visual reference without copying it; or to add approved campaign art to product surfaces. Do not invent claims, fake UI, publish, deploy, or replace product proof without explicit evidence and authorization.
Create symbolic links (symlinks) on Windows, macOS, and Linux. Automatically selects the correct command for the current operating system to create a symlink to a directory or file. Use this skill when users need to create a symlink or share files/directories across different locations.
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
Use when the user wants to create any new Backstage package — plugin, module, processor, provider, scaffolder action, or library. Drives `yarn new` to scaffold the right template and optionally pre-wires common patterns (catalog access, identity, etc.) based on user intent. Triggers on phrases like "create a new plugin", "scaffold a Backstage plugin", "I want to add a frontend/backend plugin", "build a new module", "new backend module", "new catalog processor", "new entity provider", "new scaffolder action", or any request to add a new package to a Backstage repo.
Diagnose a broken or untrusted codebase and plan the fix. Runs the app for real, fans out parallel specialist sub-agents (security, database, core logic, frontend/UX, architecture), audits the git/CI/deploy setup, verifies the headline claims independently, then gives a plain-English findings list ranked by real-world cost, writes FINDINGS.md into the repo, and delivers a rebuild-or-fix-in-place verdict (fix in place wins by default, and having real users can veto a rebuild outright) before handing off to cs-build-import-codebase and creating the Kanban tasks. Works on any codebase in any language. Triggers, "my app is a mess", "audit my codebase", "what's wrong with my app", "diagnose this codebase", "should I rebuild or fix this", "find the bugs in my app", "review my whole app".
Turn an idea into a CodeSpring plan — from a sales-call recording, a transcript, a voice note, or someone just talking at you about what they want. Interviews the person (or mines the recording) for the job the app does, walks the screens with them, picks the platform from what the app actually needs to do, finds the one technically hard part and names a real solution for it (including existing open-source prior art), cuts to a v1 that can be sold, then writes the map — core features, sub-features, notes — and hands off to cs-build-create-prd and cs-build-create-tasks. The no-code-yet counterpart to cs-build-import-codebase. Triggers, "plan my app", "generate a plan", "turn this recording into a plan", "I have an idea for an app", "design my app in CodeSpring", "map out this idea", "I've got a client call recording, make the plan", "plan from scratch".
Turn a CodeSpring plan into a clickable local mockup the client can actually look at — one screen per core feature, real copy, plausible data, a proper token-driven design system with light and dark mode, and a style guide page showing the branding. Then run the review that surfaces what the written plan could not: screen order, hierarchy, position, and choices that turn out to be incomplete. Feeds every correction back into the CodeSpring notes and tasks. Runs AFTER the map and notes exist and BEFORE the PRDs are generated. Triggers, "make a mockup", "mock up the UI", "show me what it looks like", "build a prototype", "design the screens", "what would this app look like", "create a UI mockup for this plan", "I want to show the client something".
CTF digital forensics and signal analysis techniques. Use when a challenge provides a disk image (.dd/.E01), memory dump (.raw/.vmem), network capture (.pcap/.pcapng), steganographic image/audio, or Windows event logs (.evtx). Covers the full forensics chain: Volatility memory analysis, Wireshark traffic reconstruction, binwalk steganography extraction, file system recovery, and more
CTF miscellaneous challenge techniques. Use for CTF challenges that do not fall under pwn/crypto/web/reverse/forensics/osint, such as encoding puzzles, Python/Bash sandbox escapes, RF/SDR signals, game/VM reversing, K8s RBAC, floating-point tricks, Z3 constraint solving, and game theory. Use this skill only after ruling out the other categories
CTF open-source intelligence (OSINT) techniques. Use when a challenge requires finding clues from public information — such as tracing an identity from a given username/email, geolocating from a given photo, or recovering data from historical web snapshots. Covers social media investigation, Google Dorking, reverse image search, the Wayback Machine, DNS reconnaissance, Tor relay queries, and metadata extraction
CTF general solving orchestrator. Use when facing a CTF challenge of unknown type and needing to automatically analyze the challenge type and choose the correct solving path. Automatically dispatches the corresponding specialized skill (pwn/crypto/web/reverse/forensics/osint/malware/misc); suited to scenarios where a challenge file or service endpoint is given but the category is uncertain
Source code auditing methods in CTF challenges. Use when you find a .git directory, .bak/.zip backups, or source code leaked via /proc/self/environ. Unlike real code audits — vulnerabilities in CTF source are placed intentionally and usually there are only 1-2 key points. First find the dangerous function (sink), then trace the path from the input (source) to that function. Covers dangerous functions and vulnerability patterns in PHP/Python/Node.js/Java
Overall methodology for CTF Web challenges. Use when facing a CTF range, xbow benchmark, or web security competition. Includes quick challenge-type identification, a decision tree for choosing attack strategies, common challenge-design patterns, and criteria for deciding when to change direction. Used together with the specific vulnerability skills under exploit/
Professional workflow for creating bespoke vector and complex raster icons. Professional icon design workflow including Design (visual), Path (vector), Desire (conceptual), and 3D chroma-key modes. Features AI prompt engineering, automated binarization, alpha cleanup, and SVG optimization.
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.