Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
Run a strict multi-iteration Reflex Loop with phases (PLAN, PRODUCE||PREPARE, EVALUATE, CRITIQUE, REFINE) to improve an artifact until quality gates pass or iteration limits are reached. Use when user asks for iterative refinement, quality-gated generation, or "generate -> critique -> refine" loops.
Manage authorized project work through Agent Kanban and Realmroot Toolbox, typically in scheduled-task or heartbeat-triggered Sessions. Proactively inspect what needs doing, delegate execution to other Agents, and coordinate and review their Tasks as a manager.
Manage the full lifecycle of Alibaba Cloud Realtime Compute for Apache Flink SQL: analyze schemas, author and validate SQL, manage Drafts, Deployments, Jobs, Savepoints, Session Clusters, Catalogs, Connectors, UDFs, variables, and deployment targets, synchronize configuration to Git, and troubleshoot logs, Metrics, Checkpoints, exceptions, plans, and backpressure. Use when the user asks about Alibaba Cloud Flink, VVR, VVP, Flink SQL, its job lifecycle, or troubleshooting. Operate the platform through the Python CLI; historical Metrics use a user-supplied VVP Cookie. Verify scope and authentication before platform operations. High-risk actions usually require confirmation; explicit confirmation for the resolved target in the same request satisfies the gate.
Resource saturation from system.metrics, system.events and system.asynchronous_metrics - memory, load average, connections, running queries, background pools, parts per partition, block device queues - plus short history. Use when the server feels slow or overloaded, queries queue or get rejected, or load and connection trends are needed.
ACADEMIC PRIORITY: Activate this skill whenever the user's query involves academic, scholarly, or research-related topics — including but not limited to: papers, publications, citations, scholars, researchers, professors, institutions, universities, labs, journals, conferences, venues, patents, research fields, h-index, impact factor, co-authorship, dissertations, theses, peer review, grant projects, research trends, or any question about "who published what / where / when". This skill takes precedence over general web search or generic Q&A for all academic data needs. Full-featured AMiner skill with 29 APIs and 6 workflows. Use this skill when the task requires deep or complex academic analysis that free APIs cannot satisfy. Use this skill for: scholar full profile (bio, education, honors, papers, patents, projects), paper deep dive (full abstract, keywords, authors, citation chains), multi-condition or semantic paper search (filter by author + institution + venue + keywords, or natural language Q&A via paper_qa_search_pro), explicit structured experiment retrieval (Experiment JSON, methods, datasets, or experiment names), institution research capability analysis (scholars, papers, patents), venue paper monitoring by year, patent deep details (IPC/CPC, assignee, claims), and any query needing paid API fields such as full abstracts, structured citation relationships, or scholar work history. Do NOT use this skill for simple lookups that free APIs can answer — such as checking a paper title, identifying a scholar by name, normalizing an institution or venue name, or scanning patent trends by keyword. For those, use aminer-free-academic instead. Routing rule: if the user's question can be fully answered by paper_search, paper_info, person_search, organization_search, venue_search, patent_search, or patent_info alone, route to aminer-free-academic. Otherwise use this skill.
Austrian public transport (VOR AnachB) for all of Austria. Query real-time departures, search stations/stops, plan routes between locations, and check service disruptions. Use when asking about Austrian trains, buses, trams, metro (U-Bahn), or directions involving public transport in Austria.
Reduce time-to-first-API-call (TTFAC) by optimizing every step of the developer onboarding journey. This skill covers authentication simplification, sandbox environments, interactive documentation, and identifying and eliminating common failure points. Trigger phrases: "API onboarding", "time to first API call", "TTFAC", "developer onboarding", "first API call", "auth simplification", "sandbox environment", "interactive docs", "try it now", "API playground", "developer activation", "onboarding friction"
Design, implement, or visually refine a web interface when the visible experience is a primary deliverable. Use for greenfield UI, redesigns, reference matching, and visual polish; skip backend-only work and behavior-only frontend changes.
Upload, share, or take down PR and validation media (screenshots, artifacts) on a self-hosted attach Worker through the installed attach CLI (`attach` or `gh attach`), or enroll a GitHub App agent for `att_` uploads. Use for any request to attach, upload, host, get a URL for, or delete media on attach.uinaf.dev (or a custom ATTACH_API_BASE), and for attach login/logout. Do not use for Worker deploy, vault, Cloudflare ops, or building another upload client.
Send, receive, and manage email at scale with Amazon Simple Email Service (SES). Use when building email sending, identity verification, deliverability monitoring, email validation, tenant management, or multi-tenant email platforms. Covers V2 API patterns, DKIM/SPF/DMARC authentication, configuration sets, suppression lists, bounce/complaint handling, and dedicated IP management.
WeChat Official Account image posts | nine-grid | multi-image push | image messages | stickers — stickers and multi-image pushes: from ideation, image-order planning, and AI image generation to reviewing the whole image set, producing a style-consistent set of images plus a caption for each. Publishing goes through the normal article pipeline (assemble into an article, then formatting + publish); WeChat's native "image message" must be sent manually in the Official Account backend. Aimed at Official Account operators, self-media, and IP accounts. Trigger words: "贴图", "多图推送", "发组图", "图片消息", "九宫格", "做一组图", "图片帖子", "发几张图", "不写正文发图", "只发图不写字". For article inline images/covers use aws-wechat-article-images; for multi-step chaining (write + review + layout + images + publish) use aws-wechat-article-main.
Author-side PR lifecycle babysitter and companion to review-pr. Use when the user wants to tend an existing GitHub PR through CI, review threads, description sync, mergeability, auto-fixes, or asks to babysit a PR with or without an existing manifest.
Use when defining voxel blocks in RON (`name`, `textures`, `flags`), building a runtime palette mapping `BlockId -> BlockDef`, baking per-block textures into a KTX2 atlas (`ktx2` + `zstd_rust` features), or binding the atlas as `StandardMaterial.base_color_texture` with an `ImageSampler` so meshed quads sample by face index. Generic Bevy 0.20 voxel-data patterns — no game-specific data baked in.
Use when setting up or running linting and formatting in a JavaScript or TypeScript project with Biome — the single fast Rust tool that lints, formats, and organizes imports, replacing the ESLint + Prettier pair (the JS analog of Ruff). Covers installing Biome v2, the biome.json config (formatter, linter rule groups, the assist/import-organize actions, VCS integration, overrides, monorepo extends), the CLI (biome check --write, biome ci for CI), migrating from ESLint/Prettier, the v1->v2 deltas (e.g. --apply became --write), and authoring custom lint rules as GritQL plugins. Use when adding a lint/format gate, writing or fixing a biome.json, or porting an ESLint/Prettier setup. Not the Turborepo task wiring (compose with that skill).
Best practices for writing Blender Python add-ons using the bpy API, covering operators, panels, properties, registration, and API-safe scripting. Use when creating a Blender add-on, defining bpy.types.Operator or Panel classes, registering PropertyGroup settings, writing register()/unregister() functions, working with bmesh, or debugging add-ons in Blender's Python console.
Amazon-style Working-Backwards PRFAQ: a future press release plus internal and external FAQs that stress-test a product concept before any building begins. Produces prfaq.md in the configured output folder. Use when the user says: "write a PRFAQ", "working backwards", "press release", "future press release", "stress-test the concept", "validate the idea before building", "internal FAQ", "external FAQ", "Amazon-style product brief", or "PRFAQ for [product/feature]". Also use when someone wants to clarify or update an existing PRFAQ, or validate a draft against the Working-Backwards criteria. Supports three intents: Create / Update / Validate.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
16 history-based Bridgebound triggers from Flip The Script - Demo Pipeline, Closed-Lost, Executive Churn, Email Engagement, and Reciprocity. Use when re-engaging past prospects, reactivating closed-lost deals, or building win-back campaigns.
Comprehensive Bun runtime expertise covering all major features. Use when working with Bun projects, migrating from Node.js, or leveraging Bun-specific APIs. Activates for: Bun.serve, Bun.file, bun:test, bun:sqlite, bun install, bun build, bunfig.toml, TypeScript in Bun, package manager operations, bundler configuration, and Node.js compatibility questions.
Use when the user wants to monitor major events of industry competitors, extract public opinion events / product launches / press conferences / endorsements / naming sponsorships / industry policies / large marketing campaigns, and get response suggestions for their own product. Manual trigger: /competitive-watch
Use when users want creative inspiration, storyboards or replication prompts for viral videos, analysis of visual elements and keyframes in trending content, or insight into the creative approach behind breakout videos in an industry. Manually trigger with: /inspiration
Generate music using Volcengine Imagination API. Supports vocal songs, instrumental BGM, and lyrics generation. Use when the user wants to create songs, background music, soundtracks, write lyrics, or mentions "music generation", "BGM", or "songwriting".
Build a 13-week rolling cash flow forecast from bank exports, AR aging, AP bills, payroll, and recurring commitments -- the report that tells a small business whether it survives the quarter. Flags the crunch weeks early enough to act.
Expert guidance for building conversational AI applications with Chainlit framework in Python. Use when (1) creating chat interfaces for LLM applications, (2) building apps with OpenAI, LangChain, LlamaIndex, or Mistral AI, (3) implementing streaming responses, (4) adding UI elements like images, files, charts, (5) handling user file uploads, (6) implementing authentication (OAuth, password), (7) creating multi-step workflows with visible steps, (8) building RAG applications with document upload, or (9) deploying chat apps to web, Slack, Discord, or Teams.
Read-only inspection of a single GitHub PR lifecycle — checks CI, review feedback (threads, review bodies, top-level comments), description sync, and mergeability, and returns PASS or FAIL with per-gate findings. The read-only lifecycle check that babysit-pr calls. Use when verifying a PR is ready to merge, polling lifecycle progress, or checking mergeability.
Cinema 4D MCP expert for extracting scene data, writing C4D Python scripts, and controlling Cinema 4D through MCP tools. Activate when: (1) using cinema4d MCP tools (get_scene_info, list_objects, execute_python_script, add_primitive, etc.), (2) writing Python scripts for Cinema 4D extraction or manipulation, (3) working with MoGraph cloners/effectors/fields, (4) baking animation data from C4D scenes, (5) debugging C4D Python API errors, (6) extracting Redshift material or camera data. Covers critical gotchas, correct extraction patterns, MoGraph baking, timeline evaluation, API compatibility, and known failure modes.
Optimize CircleCI configuration for speed, reliability, and maintainability. Use when users ask to improve `.circleci/config.yml`, reduce CI runtime, tune caching/workspaces/parallelism, remove pipeline waste, or fix flaky pipeline behavior caused by configuration choices.
Use this skill when categorizing code review findings into severity levels. Apply when determining which emoji and label to use for PR comments, deciding if an issue should be flagged at all, or classifying findings as CRITICAL, IMPORTANT, DEBT, SUGGESTED, or QUESTION.
Uses the Codacy Analysis CLI to run local static analysis on repositories or specific files. Handles installation, initialization, dependency management, dry-runs, and analysis with JSON output. Use whenever the user wants to analyze code locally, run static analysis, scan for bugs or security issues, lint files, check code quality without pushing to Codacy, or run tools like ESLint, Ruff, Semgrep, RuboCop, or any other supported analyzer on their machine. Also trigger when the user asks to analyze staged changes, scan a PR locally, or set up local Codacy analysis.
Enriches pull request code reviews with Codacy data — quality issues, security findings, coverage, and duplication. Use whenever the user asks to review a PR, check what a pull request introduced, verify PR coverage, look at PR quality, or find new issues in a PR. Also use when another code-review skill is active (e.g. CodeRabbit) to layer Codacy data on top. Trigger this skill for any pull request review workflow, even if the user just says "review PR 42" or "what's wrong with this PR".
Review the changes since a fixed point (commit, branch, tag or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code do what the originating issue/spec asked for?). Run both reviews in parallel sub-agents and report side by side. Use when the user wants to review a branch, a PR, work in progress, or asks to "review since X".
Generally-applicable conventions for how code is written and arranged — tooling/package manager, import style, file & component naming, comments, and where files live (colocation vs. global folders). Use whenever creating, naming, moving, or importing a file, running project commands, or deciding where a new module belongs. Consult BEFORE writing the code so the conventions are baked in, not retrofitted. If a convention below matches the work, apply it — don't ask, just follow it (call out the choice in one line so the user can override).
Delegate coding tasks to Codex, Claude Code, or Pi agents via acpx (ACP protocol). Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Prefer acpx over raw PTY/exec for all coding agent delegation.
Color grade clips the way a professional colorist does — normalize, balance, match, then build a look — using inspect_color scopes and apply_color (exposure, white balance, wheels, curves, hue curves, LUTs). Use when the user asks to color, grade, match shots, fix white balance, fix exposure, neutralize a cast, or apply a look/film stock.
Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP server. Cloud-only — connects to the hosted service, not a local ComfyUI install. Use for any "generate/edit an image", "make a video", "text to 3D", or ComfyUI workflow task.
Decode a commercial lease before signing or renewing -- true all-in occupancy cost (base rent plus NNN/CAM plus escalations), the clauses that hurt small tenants (personal guarantees, relocation, restoration), and the negotiation asks landlords routinely grant. The lease is most SMBs' biggest fixed cost and least-read document.
When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," "content planning," "editorial calendar," "content marketing," "content roadmap," "what content should I create," "blog topics," "content pillars," or "I don't know what to write." Use this whenever someone needs help deciding what content to produce, not just writing it. For writing individual pieces, see copywriting. For SEO-specific audits, see seo-audit. For social media content specifically, see social-content.
Prepare YOUR data room for a fundraise, acquisition, or bank diligence -- builds the checklist for your deal stage, sweeps your folders for what you already have, produces a gap report, and organizes everything into the structure buyers and investors expect. The sell-side complement to cowork-deal-room.
Build an insurance-grade home inventory from a folder of photos and receipts -- identifies items, pulls values from receipts, estimates replacement costs, organizes by room, and outputs the documentation an insurance claim actually requires. Update mode keeps it current after new purchases.
Point Cowork at your invoices and payments records -- builds an AR aging report, drafts escalating follow-up emails matched to each invoice's age and the client relationship, and runs as a weekly scheduled task so nothing slips past 30 days unnoticed.
Drop a folder of vendor quotes, proposals, and SOWs on Cowork -- normalizes them into one comparison matrix, computes true total cost of ownership, surfaces the terms each vendor buried, and arms you with negotiation leverage points and reference-check questions.
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.