Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Structured roundtable discussion framework with a truth-seeking moderator who invites representative figures for dialectical debate on any topic. Use when user says "圆桌讨论", "圆桌", "roundtable", "辩论", or wants to explore a topic through multi-perspective structured debate.
Audit, prune, and improve agent guidance markdown files in repositories. Use when the user asks to check, audit, update, improve, or fix AGENTS.md, CLAUDE.md, or related guidance files. Adds missing commands and gotchas, removes stale entries, deduplicates, and keeps the file small and relevant. Scan for guidance files, evaluate quality against templates, output a quality report, then make targeted updates.
Research workspace context, APIs, implementation options, or external evidence before planning. The terminal artifact is always a spec at specs/<slug>.md; a plans/research/<slug>.md memo is optional supporting evidence when substantial investigation was needed. Accepts an optional goal path for provenance; see loam::setting-goals.
Best practices for MariaDB replication and high availability — Galera Cluster, GTID replication, semi-synchronous replication, parallel replication, and application patterns for HA environments. Use when setting up replication, designing applications for HA, working with Galera Cluster, asking about MariaDB GTID, handling replication lag in application code, or choosing between replication topologies. IMPORTANT — MariaDB GTID format is incompatible with MySQL GTID, and Galera Cluster needs no server plugin to load but does require the separate galera wsrep provider library (galera-4).
Universal MCP client for connecting to any MCP server with progressive disclosure. Wraps MCP servers as skills to avoid context window bloat from tool definitions. Use when interacting with external MCP servers (Zapier, Sequential Thinking, GitHub, filesystem, etc.), listing available tools, or executing MCP tool calls. Triggers on requests like "connect to Zapier", "use MCP server", "list MCP tools", "call Zapier action", "use sequential thinking", or any MCP server interaction
(forwward) Interprets medical records, clinical notes, FHIR data, and advises on medical data UI with OCR interpretation, clinical summarization, and drug interaction flags. Triggers on patient records, clinical data, medical PDFs, health-tech products, or medical data presentation.
Meilisearch — fast, open-source search engine with typo tolerance, faceted search, and AI-powered hybrid search. Use when building with Meilisearch or asking about its index configuration, search parameters, filters, facets, API keys, geosearch, ranking rules, or integration with JavaScript/TypeScript clients. Fetch live documentation for up-to-date details.
An AI-native skill for parsing PDF, Office, and image files into clean Markdown with MinerU, a fast, zero-config document parser for AI agents. Works with NO token via the lightweight Agent API and auto-upgrades to the Standard API (token) for large files, batches, and DOCX/HTML/LaTeX export. Use when: (1) Converting PDF/Word/PPT/Excel/image to Markdown, (2) Extracting text, tables, formulas, or running OCR on scanned documents, (3) Batch-parsing a folder in parallel, (4) Piping parsed Markdown straight back to an agent or into Obsidian
Use this skill when producing speech, narration, dubbing, localization, advertising voice, voice-clone previews, or interactive voice with MiniMax speech/audio APIs. It covers MiniMax T2A HTTP, WebSocket streaming, async long-form TTS, Speech 2.8/2.6/02 model selection, system and custom voices, rapid voice cloning, voice design, pronunciation/language/emotion controls, pricing and limits, artifact custody, consent and rights checks, and production QA.
Generates Python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says "evaluate my model", "run a benchmark", "test model performance", "how did my model perform", "compare models", or similar requests.
Structure the body and close of a short-form video into a reusable Narrative Brief with explicit arc choice, beat sequence, product integration timing, emotional arc, and CTA design. Use after the hook mechanism and viewer question are locked and before storyboard or prompt writing starts.
Migrates a nuqs codebase off pre-v2.5 patterns — deprecated `throttleMs`, hand-rolled setTimeout/useState debounce around `useQueryState`, unchecked `parseAsJson` casts, unversioned `nuqs/adapters/react-router` imports, or `ParserBuilder<T>` type references. Scans the repo, produces a dry-run report, asks for confirmation, applies AST codemods, then runs `tsc --noEmit` + the user's lint as a gate. Trigger even if the user only mentions "upgrade nuqs" or "migrate to nuqs v2.5+" without naming the specific patterns — they almost always exist in pre-v2.5 codebases.
Apply the Opquast Digital Quality Framework (245 rules, 14 categories) when building, reviewing, or auditing websites and web applications. Use for web development quality assurance, accessibility compliance, security hardening, privacy implementation, e-commerce best practices, and holistic digital quality checks.
Drive structured autoresearch iteration after evo:discover and the baseline commit. Use when the user invokes /evo:optimize or asks to try ideas, try variants, run experiments, use available GPUs, improve the current best/frontier, continue an evo search, or compare candidate changes in an evo workspace. The orchestrator plans and spawns optimization subagents; candidate edits/runs belong to those subagents. Width is set via subagents=N (1 for serial workloads, larger for parallel); the loop's structural value applies at any width.
Build safe, version-pinned telemetrygen commands for synthetic OTLP traces, metrics, and logs. Use for "send sample traces to this collector," "load-test an OTLP endpoint," "generate traffic to verify a processor, OTTL transform, or tail sampling," and "produce test data for dashboards." Also use when choosing telemetrygen transport, TLS, attributes, counts, duration, or rate. Not for application SDK instrumentation or production collection that does not use telemetrygen.
Every Discovery v2 endpoint plus offline search, multi-venue watchlists, residency dedup, and on-sale tracking no API call exposes. Trigger phrases: `what concerts in <city> this weekend`, `what's playing at <venue>`, `where is <artist> playing`, `presale watch`, `ticketmaster events`, `use ticketmaster`, `run ticketmaster`.
Open a GitHub PR dashboard in the browser. Use when the user asks to see their pull requests, open the PR dashboard, show PRs for a date range, or check PR status. Trigger phrases include "show my PRs", "open PR dashboard", "pull request dashboard".
Create, modify, test, or package Python provider adapters under python/providers, including framework-specific dependencies, public imports, type inference, and provider metadata. Use for Python provider work only; use python-sdk for core SDK changes.
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.
Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.
Use when a Meta Quest app is built with Meta Spatial SDK in Kotlin: lane fit, toolchain, ECS, panels as Android views, hybrid apps. NOT for native OpenXR (quest-native), Unity, WebXR (quest-webxr), or profiling (quest-perf). Opt out: no xr, без xr. Triggers: “Spatial SDK” / “Спатиал SDK,” “MRUK”.
Help users write correct R code for async, parallel, and distributed computing using mirai. Use when users need to run R code asynchronously or in parallel, write mirai code with correct dependency passing, set up parallel workers, convert from future or parallel, use mirai_map, integrate with Shiny or promises, or configure cluster/HPC computing.
Provides index-first documentation navigation and implementation constraints for Ray mini program development. Use when building pages or UI, encapsulating and refactoring components, integrating Ray APIs and device capabilities, working with lifecycles and routing, converting images to code, handling i18n and styles, or troubleshooting and upgrading. Before implementing, locate capabilities via references/ray/INDEX.md and the routing docs; never invent APIs or lifecycle hooks.
React Hook Form performance optimization for client-side form validation using useForm, useWatch, useController, and useFieldArray. This skill should be used when building client-side controlled forms with React Hook Form library. This skill does NOT cover React 19 Server Actions, useActionState, or server-side form handling (use react-19 skill for those).
Implement performant responsive images with srcset, sizes, lazy loading, and modern formats (WebP, AVIF). Covers aspect-ratio for CLS prevention, picture element for art direction, and fetchpriority for LCP optimization. Use when adding images to pages, optimizing Core Web Vitals, preventing layout shift, implementing art direction, or converting to modern formats.
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
Build integrations with Snippe (api.snippe.sh), a Tanzania payment processing API. Use this skill whenever the user mentions Snippe, is working on payment integrations for Tanzania (mobile money via M-Pesa, Airtel Money, Mixx by Yas, Halotel; credit/debit cards via Visa/Mastercard; dynamic QR codes), needs to accept TZS payments, sends payouts to Tanzanian mobile wallets or banks (CRDB, NMB, NBC, ABSA, Equity, KCB, Stanbic, etc.), verifies Snippe webhooks, or handles Snippe errors and idempotency. Covers the v2026-01-25 API — authentication, payments, hosted checkout sessions, disbursements, webhooks, and error handling.
When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms. Also use when the user mentions "LinkedIn post," "Twitter thread," "social media," "content calendar," "social scheduling," "engagement," or "viral content." This skill covers content creation, repurposing, and platform-specific strategies.
Scores how completely an implementation fulfills a PRD/spec, case by case, and produces a single comparable final grade. Invoke only when explicitly named (e.g. run spec-driven-eval); do not auto-trigger. Use when benchmarking spec-driven implementations, grading acceptance criteria, evaluating whether a feature was 100% implemented, comparing multiple implementations of the same PRD, or auditing implementation and test coverage (unit and e2e) against product requirements. Do NOT use for planning or building features (use tlc-spec-driven), writing PRDs, or general code review unrelated to a spec.
Use when authoring, revising, normalising, or reviewing a doctrine product specification/PRD - the durable product intent, requirements, success measures, behaviours, and verification basis for an evergreen capability. use before creating or scoping slices that descend from shared product intent. use when a request asks for product requirements, functional requirements, non-functional requirements, product scope, acceptance gates, out-of-scope boundaries, success measures, or agent-readable product context. do not use for one-off change planning, implementation design, technical architecture, or phase execution.
This skill provides three-act screenplay structure with beat placement. Covers opening image, inciting incident, midpoint, all is lost, climax, and page targets for a 110-page feature screenplay. Use when: planning screenplay structure, analyzing narrative arc, placing story beats, or validating structural integrity.
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.
