Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Generates an x-ray.md pre-audit report covering overview, enhanced threat model (protocol-type profiling, git-weighted attack surfaces, temporal risk analysis, composability dependency mapping), invariants, integrations, docs quality, test analysis, and developer/git history. Triggers on “x-ray”, “audit readiness”, “readiness report”, “pre-audit report”, “prep this protocol”, “protocol prep”, “summarize this protocol”.
An academic paper formatting assistant based on a standardized directory structure. Supports PDF, .doc, .docx, and .md input formats, and automatically selects an OCR pipeline, reformatting pipeline, or direct MD conversion pipeline. Includes environment cleanup confirmation, checkpoint recovery, smart image cropping, incremental DOCX generation by unit, dual-unit quality checks, intermediate state saving, and BibTeX reference management. All intermediate files go in resources/ and final outputs in outputs/.
Run a comprehensive WCAG accessibility audit covering perceivable, operable, understandable, and robust principles. Use this skill whenever the user wants to audit accessibility, review WCAG compliance, fix accessibility issues, prepare for accessibility certification, address an accessibility lawsuit risk, or systematically improve a site's accessibility. Triggers on accessibility audit, WCAG audit, a11y audit, accessibility compliance, ADA compliance, screen reader test, keyboard navigation, accessibility report, fix accessibility, axe scan. Also triggers when accessibility issues have been reported and need systematic remediation.
Teaches agents how to use @getalby/cli to operate a bitcoin lightning wallet via Nostr Wallet Connect (NIP-47). Use whenever the user wants to send or receive money, pay an invoice, check wallet balance, create invoices, convert between fiat and sats, retry an HTTP request that returned 402 Payment Required, or discover paid API services. Pays HTTP 402 resources across all major payment protocols — L402, x402, and MPP and all main networks (USDC on Base, Solana, Tempo) — from the lightning wallet. Also supports atomic swaps to any on-chain cryptocurrency/stablecoin address (e.g. USDC/USDT).
Use when designing new high-level system architecture, reviewing existing designs, or making architectural decisions. Invoke to create architecture diagrams, write Architecture Decision Records (ADRs), evaluate technology trade-offs, design component interactions, and plan for scalability. Use for system design, architecture review, microservices structuring, ADR authoring, scalability planning, and infrastructure pattern selection — distinct from code-level design patterns or database-only design tasks.
Rebuild and validate AutoCAD drawings from a source DWG, a PDF-derived intermediate DWG, or a raster reference image paired with authoritative dimensions and drawing requirements. Use when Codex must profile and exactly reproduce a .dwg, convert a PDF into a validated intermediate DWG before exact redraw, or convert an image plus metrics into parameter-driven AutoLISP/AutoCAD geometry and optional 3D solids.
Tell callidescope what to do — the command-line flags (--check, --write, --addresses, --config, --format, and an override for every configured field, from --directories and --exclude through --include-tests, --maximum-depth, --maximum-breadth, --json, --markdown, and --mermaid) and the callidescope.config.ts they layer over, covering the two depth and breadth limits, entry points, exclusions and excluded callees, and where a run writes its JSON, markdown, and mermaid reports. Use when wiring a depth gate into CI or a commit hook, when a whole-workspace run is slow, when choosing between --check and --write, when a repository has no callidescope configuration yet, when a traced project has no callidescope.config.ts of its own or one that leaves a field out, when a project needs its own depth or breadth limit, when a package low in the graph measures nothing, when a trace judges code it should not, when everything is reported as an orphan root, or when deciding where a committed report should live.
Run callidescope and read what it printed — a whole-workspace trace, one project's gate verdict, or the depth and breadth commands against one or more callables, each addressed as file#qualified-name. Use when running callidescope or npx callidescope, when reading a call stack or a breadth row, when reading what a per-project gate or trace target printed, when reading a project readme's Limits table, when a depth printed as "≥ n" needs interpreting, when reading a committed markdown report, mermaid diagram, or JSON report, when a run narrowed with --directories reports a frame, a stack, or a project the run was never pointed at, when a depth moved without an edit that explains it, or when asking who calls this, what does it call, what would this rename touch, and where should this callable be split before a refactor starts.
Create OpenCode plugins using the @opencode-ai/plugin SDK. Use for building custom tools, event hooks, auth providers, or tool execution interception. Use proactively when developing new plugins in .opencode/plugin/ or ~/.config/opencode/plugin/. Examples: - user: "Create a plugin to block dangerous commands" → implement tool execution before hook with blocking logic - user: "Add a custom tool for jira" → design tool schema and implementation using SDK context - user: "Show toast on file edit" → react to file edit events and display status message - user: "Build a custom auth provider" → implement auth flow for new model provider - user: "Intercept git commits" → add hook to validate commit messages before execution
Python backend for Databricks Apps — FastAPI (default), Flask, Dash, Streamlit, Gradio, Reflex. Default for a new Databricks App is `databricks-apps` (AppKit — Node/TypeScript/React) — reach for it first. Use this skill only when the user asks for a Python backend, extends an existing Python app, or the team is Python-only. Covers OAuth auth, app resources, SQL warehouse and Lakebase connectivity, foundation-model / model-serving APIs (via `databricks-python-sdk`), AI Search (Vector Search) queries (via `databricks-vector-search`), and deployment via CLI or DABs.
Audit designs against 19 rules across Figma files and code (HTML/CSS/React/Vue/Tailwind). Auto-detects framework and design system (MUI, Chakra, shadcn/ui, Ant Design, Radix, Bootstrap). Runs code superpowers across all 19 categories: aria, focus, contrast, tokens, responsive, motion, forms, navigation, spacing, states, microcopy, elevation, iconography/SVG. Flags color blindness risk. Audits dark patterns, ethical design, Nielsen's heuristics. Outputs before/after diffs, developer handoff reports, wireframe-to-spec. English and Korean. Triggers on: check my design, review my UI, audit my layout, is this accessible, design review, color contrast, WCAG, a11y, pixel perfect, Figma audit, CSS check, dark patterns, is this GDPR compliant, is this manipulative, is my form accessible, is my dark mode correct, wireframe to spec, heuristic review, Nielsen audit, usability heuristics, 디자인 검토, 접근성 확인, 색상 대비, 다크 패턴, 와이어프레임 스펙.
Currency handling patterns for the Dinero.js money library. Use when working with multiple currencies, converting between currencies, defining custom currencies, storing monetary values in databases, or integrating with payment services like Stripe or PayPal. Triggers on currency conversion, database schema design for money, or payment API integration with Dinero objects
Build high-converting sales funnels using Russell Brunson's proven framework. Use when: **Launching an online product** and needing a complete funnel strategy; **Converting cold traffic** into paying customers systematically; **Increasing customer lifetime value** through value ladder design; **Writing sales pages, webinars, or email sequences** with proven scripts; **Reverse-engineering competitor funnels** to model what works
Senior FDA consultant and specialist for medical device companies including HIPAA compliance and requirement management. Provides FDA pathway expertise, QSR compliance, cybersecurity guidance, and regulatory submission support. Use for FDA submission planning, QSR compliance assessments, HIPAA evaluations, and FDA regulatory strategy development.
Feishu cloud drive enhanced command group. Chunked large-file uploads (automatically split into 3 parts at ≥20MB), streaming downloads, asynchronous document exports (markdown quick path / sheet+bitable csv / sub-id / bounded polling + resume), asynchronous document imports, file/folder moves (automatic folder polling), rich-text comments (text/mention_user/link + wiki URL parsing + inline comments), generic asynchronous task queries, one-way local ↔ cloud drive mirroring (pull/push/status, SHA-256 content diff + --delete-* --yes double confirmation), and v2 doc_wiki/search flat-filter search (folder-tokens / space-ids / creator-ids / only-title). Use when the user requests "upload a large file," "download a cloud drive file," "export as pdf/markdown/xlsx," "import docx into cloud docs," "move a folder," "add a document comment," "@ someone in a document comment," "comment from a wiki link," "check asynchronous task status," "resume a drive task," "chunked upload," "cloud drive mirroring," "directory sync," "compare local files with cloud drive," "SHA comparison," "search documents by folder," "feishu drive," or "lark drive." This skill coexists with the older file/media/comment command group and offers enhanced capabilities (User Token support, asynchronous resume, rich-text comments); file/media remain available for basic scenarios.
Review loop for agent-made media on Flask (flask.do, a video review and feedback app, not the Python web framework). Use when rendering, generating or editing a video, animation, motion graphic or image that a person has to watch to approve (Remotion, HyperFrames, ffmpeg, Blender, generated media), when the work will take rounds of feedback, when someone other than the user reviews it (a client, a teammate), or when the user is away from the terminal. Also use when the user mentions Flask, a flask.do link, notes on a cut, or sharing a draft for review. Covers connecting Flask, uploading a version, sharing its link, waiting for time-coded feedback, reading it and uploading the next version. Not for reviewing text or code.
Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or isolate work for review; whenever a user mentions a stack, branch layers, dependent PRs, or gh stack; or when a stack is checked out.
Expert blueprint for horror games: sawtooth tension pacing, Director macro-AI, sensory predator AI, sanity/stress FX, and scarcity loops. Use when building psychological/survival horror, dual-brain stalker AI (cheating Director + honest LoS/sound), flashlight/fog atmosphere, or safe-room saves. Keywords: horror_game, tension_pacing, director_system, sensory_perception, sanity_system, volumetric_fog, AI_reaction_time.
Post-mortem on what the user has already published - which posts actually worked, why, and what to stop doing. Use when the user pastes their LinkedIn analytics or past posts and asks "what's working", "why did this flop", "read my analytics", "audit my content", or wants to know what to double down on.
Handle the replies under the user's own LinkedIn posts - draft answers to every comment, sorted by which ones are worth answering. Use when the user pastes the comments on their post, says "reply to these", "handle my comments", "someone said X on my post", or is dealing with a critic or a lead in the comments.
Getting a MapLibre GL JS source to actually render — TileJSON `url` versus hand-wired `tiles` templates, matching `source-layer` names to the tile schema, layer order and inserting below labels, `promoteId` and the feature ids that feature state needs, and the CORS and glyph failures behind a blank map. Use when a source is configured but nothing is drawing, or when setFeatureState does nothing.
Deconstruct a novel for game adaptation. Compress a raw novel, deconstruction library, or writing project into a SOURCE_BIBLE with cited textual evidence, extracting world rules, player verbs, spaces, character will, systems, and visual anchors—without inventing a genre yet. Use for gameable book analysis, analyzing a novel for game adaptation, or extracting game systems from a book. Gamify book deconstruction. Compress a raw novel, deconstruction library, or writing project into a SOURCE_BIBLE with necessary textual evidence, extracting world rules, player verbs, spaces, character will, systems, and visual anchors without prematurely inventing a game genre. For requests such as gamified book deconstruction or analyzing the basis for adapting a novel into a game
Gets payroll ready to run without anyone getting shorted: pulls timesheets from Gusto, QuickBooks Payroll, or an uploaded spreadsheet, totals regular, overtime, and PTO hours by person, flags every anomaly it finds — missed punches, overtime spikes, rate changes, mid-period hires and terminations, hours off the schedule — and stages the run for the owner to approve line by line before a dollar moves. Anomalies are always raised, never quietly corrected. Once the owner runs it, the journal posts to the ledger or goes to the bookkeeper. Reach for this whenever payroll comes up at all — “run payroll,” “payroll is due,” “check the timecards,” “did everyone clock out,” “how many hours did the crew put in,” “why is payroll so high this week,” “I need to pay the guys Friday” — and use it after cash-flow-snapshot when the owner is worried about whether payroll clears.
Edit videos in Pireel Studio through the `pireel` MCP server — first-run setup, local and stock media import, transcript editing, multi-source montage, multiple editable outputs, storyboarding, designed graphics, captions, themes, and export. Read this whenever the user wants to install or connect Pireel or edit, cut, remix, storyboard, illustrate, caption, theme, or export a Pireel video, and before the first Pireel MCP call or after a tool failure. Routes to the matching bundled playbook
Platform device model skill for Linux driver binding. Use when implementing platform_driver probe/remove, sysfs attributes, device properties, or deferred probe. Activates on queries about platform_device, platform_driver, driver model, sysfs, probe remove, or Linux device bus.
Venue- and market-type-agnostic strategy, sizing, and backtesting layer for binary prediction markets (Kalshi, Polymarket, ForecastEx). Covers the durable edge thesis, fee-aware selection, fractional-Kelly sizing, and leak-free validation methodology.
Edward de Bono's Random Stimulus technique — force-fit a random unrelated object, place, or phenomenon onto a creative target to break familiar association patterns. Use for product ideation, feature naming, brand direction, copywriting, architecture and design choices when ideas from outside the problem space would help. Triggers include "random stimulus", "random word", "force-fit", "de Bono", "inject a random object", "stare out the window", "see the tree and squeeze an idea". Do NOT use for analytical work like debugging, code review, or implementation tasks.
Interactive image/video previews, deployment option comparison (serverless, dedicated, self-hosted, batch), Workflow publishing, device management, and Vision Events. For raw API URL patterns, auth, and request/response formats, see roboflow-api-reference.
Guide and execute the migration of asynchronous code from RxJava to Kotlin Coroutines and Flow. Use this skill when a user asks to convert RxJava (Observables, Singles, Completables, Subjects) to Coroutines (suspend functions, Flows, StateFlows).
Expert SEO content strategy for SaaS and B2B sites. Use when doing keyword research, planning content clusters, creating pillar pages, optimizing on-page SEO, fixing technical SEO issues, building links, refreshing content, implementing programmatic SEO, mapping search intent, optimizing for SERP features, or measuring content performance. Use for SEO audits, content gap analysis, and organic growth strategy.
Reconcile session outcomes into persistent project memory files. Updates project state, backlog, and status via section-aware merging — not a session dump. Use at the end of any significant work session. Use when: 'session close', 'close session', 'save session', 'update memory', 'wrap up', 'end of session', or before ending a big session.
Implement the Syncfusion Blazor Stepper component for multi-step workflows. Use when creating step-by-step navigation UI, wizards, form workflows, or progress tracking. Covers step-based navigation, wizard interfaces, step validation, animations, templates, and stepper customization in Blazor applications.
Build reproducible developer environments for real projects: local toolchains, runtime versions, Docker Compose or dev containers, onboarding flows, local service parity, bootstrap scripts, and environment troubleshooting. Use when the user needs a repo to run consistently across machines, containers, or staged environments, even if they only say setup dev environment, onboarding, Docker, devcontainer, local parity, bootstrap, or make this runnable. This is the canonical broader environment-setup skill. Route narrower `.env` and app-config questions to `environment-setup`.
Token optimization best practices for MCP server and tool interactions. Minimizes token consumption while maintaining effectiveness. USE WHEN: user mentions "token usage", "optimize tokens", "reduce API calls", "MCP efficiency", asks about "how to use less tokens", "MCP best practices", "limit output size", "efficient queries" DO NOT USE FOR: Code optimization - use `performance` instead, Text compression - this is about API usage patterns, Cost optimization (infrastructure) - use cloud/DevOps skills
Fetch trending and hot-search news data from Toutiao (www.toutiao.com), covering popular Chinese content across politics, finance, social events, international news, technology, and entertainment. Outputs trending headlines, popularity scores, and links.
Scaffold the Antithesis harness for customers running Kubernetes: Convert Helm charts, Kustomize templates, or raw Kubernetes manifests into a minimized set of manifests for Antithesis. Verify the Kubernetes manifests are in the correct shape with snouty validate and a local cluster deploy. Hand off to antithesis-launch if the user wants to submit a run. At the end, the user is ready to run antithesis-workload to build tests. If the desired setup is docker-compose, defer to the antithesis-setup skill.
Build robust backend systems with modern technologies (Node.js, Python, Go, Rust), frameworks (NestJS, FastAPI, Django), databases (PostgreSQL, MongoDB, Redis), APIs (REST, GraphQL, gRPC), authentication (OAuth 2.1, JWT), testing strategies, security best practices (OWASP Top 10), performance optimization, scalability patterns (microservices, caching, sharding), DevOps practices (Docker, Kubernetes, CI/CD), and monitoring. Use when designing APIs, implementing authentication, optimizing database queries, setting up CI/CD pipelines, handling security vulnerabilities, building microservices, or developing production-ready backend systems.
Gets Claude talking to a tool that has no official connector. Identifies the system, first checks Claude's connector directory for an existing connector, and if none exists, connects the tool through Zapier—never by hand-building against a raw API—with credentials handled safely and approval gates for anything that writes. Turns “my ERP isn't supported” into an afternoon. Use whenever the owner names a tool that isn't connected, including “can you connect to my,” “make my tools talk to each other,” “there's no API for this,” “pull data out of my field service software,” “I use ServiceTrade and it's not on the list,” or “is there any way to get at this data.” Use whenever an unsupported system is blocking something else.
Act on a callidescope run that failed—a per-project gate reporting a stack over that project's limit, a breadth gate, a gate that read none of its project's own files, a stale committed report, an unreadable tsconfig, a run that traced nothing, or a rejected command line or configuration. Use when callidescope or an inferred gate target exits non-zero; when a stack got deeper in a change; when deciding whether a failing gate is a code fix or a limit fix; when choosing or moving a project's own maximumDepth or maximumBreadth; when a printed maximumDepth disagrees with the number a gate judged; when a committed report disagrees with a fresh run; when a declared entry-point address resolves to nothing or several targets; when a traced project has no callidescope.config.ts of its own or one that omits a field; or before reaching for maximumDepth to make a failing check pass
All-in-one skill for CLAUDE.md files. Two modes: `audit` finds drift (claimed facts no longer matching code), leaked secrets, duplicates, instruction-budget bloat, and prescriptive-vs-descriptive imbalance across all CLAUDE.md files in your projects. `improve` measures one CLAUDE.md against Anthropic's official best practices (200-line budget, removability test, emphasis tuning, 3-tier hierarchy) plus community-validated guidance, then proposes concrete rewrite diffs applied only after user approval. Default behavior auto-detects: in a project with a CLAUDE.md → improve mode; otherwise → audit all. Use when: 'audit claude.md', 'check claude md drift', 'lint CLAUDE.md', 'claude md audit', 'refresh instructions', 'improve CLAUDE.md', 'restructure CLAUDE.md', 'tune CLAUDE.md', 'apply CLAUDE.md best practices', 'is my CLAUDE.md good', 'CLAUDE.md is too long', 'rebalance CLAUDE.md', or quarterly as a hygiene check
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.