Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Create Claude skills from book content (markdown files). Transforms long-form book knowledge into structured, context-efficient skill packages with granular reference files, workflows, and use-case guidelines. Use this skill when: - Converting a book (markdown) into a reusable Claude skill - Creating knowledge bases from technical books, guides, or documentation - Building skills that need progressive disclosure of large content - Structuring book knowledge for efficient context loading
Sweep the current conversation for durable knowledge - user preferences, project facts, operational gotchas, standing decisions, and unfinished next steps - and file each through explicit instructions, existing local conventions, or the private `.stow-notes.md` fallback, curating tiered, decaying destination files as it writes. Use when the user invokes /stow, asks to save or write down what was learned this session, or before a context reset or long break.
Coordinate coding agents through AMQ. Use for agent messages, inboxes, receipts, sessions, wake delivery, cross-project routing, managed launches, or AMQ diagnostics. Use amq-spec for collaborative design; do not use this for general message queues or single-agent work.
An execution-focused skill for developing, maintaining, distributing, and validating DeepSeek Harness (DSH) plugins. Covers host/client form assessment, bundle/profile contracts, Service and function plugins, tools, HTTP, persistence, slots, Conversation Node, client builds, HMR, GitHub installation, and real-world integration testing.
Everything In Its Right Place. The universal post-work organizer. After any significant work session, EIIRP runs a 7-phase audit: (1) inventory every output, (2) walk taxonomy to decide where each lands, (3) check schema-pack consistency against the brain's actual shape, (4) file enriched brain pages, (5) audit the skill graph for DRY+MECE, (6) verify resolvability, (7) report. Named after the Radiohead song. Nothing produced during significant work lives only in chat — knowledge becomes permanent, patterns become reusable. Also carries the always-on auto-fire gate: when >=500 words of structured analysis on a user-shared document is about to be delivered, file the brain page first, then deliver the analysis with the link in that same reply.
Write and resume a canonical handoff file for work that spans sessions, interruptions, or phases. Takes an optional mode argument, write or resume, and an optional task slug. Use when a task is paused, resumed, approaching a context limit, or split across review and implementation. Do not use for work that completes within the current session.
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".
Domain navigator for UI craft, visual design, brand, color, typography, mobile design, and interactive design engineering skills. Routes to skills for taste-driven UI, platform design (iOS/Android), components, color science, and the full visual design stack.
Concepts and strategy for using a connected Honcho as persistent memory of the user — the recall/record loop and session and peer design. Start here to understand how Honcho memory works, then connect — via a first-class integration for your environment if one exists (preferred), or raw MCP tools (covered here) or the honcho-cli skill (CLI). For embedding the SDK into a codebase, use honcho-integration.
Refresh a SINGLE app's durable AI context — a thin `CLAUDE.md` router over discovered reference docs so future sessions start knowing the repo without paying for stale guesswork. Detects the framework shape, discovers the real routes, exports, flows, and subsystems from code, rewrites the imported references, then keeps `CLAUDE.md` compact and always-loaded. User-only maintenance workflow that mutates durable project memory: every claim is GROUNDED in the real codebase, never invented, and human-authored rules are preserved rather than overwritten. Use to initialize or refresh one app's context map after meaningful changes.
This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token and cost estimation, choosing between single-agent and multi-agent at the project level, structured output design for downstream parsing, and structuring agent-assisted iteration. Use this when the unit of work is a whole project or a multi-stage pipeline. Route individual tool design to tool-design and individual skill-loading or context-budget tactics to context-optimization.
Interactive workflow for creating new skills for the skills-il organization. Guides through category selection, use case definition, folder scaffolding, metadata.json generation with bilingual metadata, instruction writing, Hebrew companion creation, and validation. Use when user asks to create a new skill, scaffold a skill for skills-il, write a SKILL.md, contribute a skill, new skill template, or liztor skill chadash. Enforces skills-il conventions (kebab-case naming, Hebrew transliterations, bilingual display names, progressive disclosure, validate-skill.sh compliance). Do NOT use for editing existing skills, creating skills for non-skills-il platforms, or generic markdown file creation.
Planning skill for AI-powered conversational agents. Qualifies the developer's use case across outcome sophistication, entry point, and customer profile to recommend the right Twilio Conversations architecture and implementation skills. Handles both high-level requests (“build me a voice AI assistant”) and specific ones (“integrate ConversationRelay with my OpenAI backend”).
Lập bản đồ cho một chunk việc QUÁ LỚN với một phiên agent và còn MÙ MỜ — dựng một bản đồ các ticket QUYẾT ĐỊNH trên ledger issue, rồi giải từng ticket một cho tới khi đường tới đích hiện rõ. Gọi bằng tay khi có một ý tưởng lớn chưa rõ hình dạng, TRƯỚC cả /propose. Chỉ-gọi-tay.
Configure project guidance for AI/coding agents to use Allure agent mode during test work by detecting local test commands, Allure capabilities, result paths, and evidence conventions, then creating short root agent routers plus docs/allure-agent-mode.md. Use when the goal is agent workflow guidance, evidence review workflow, expectations, and project-specific test-work instructions; not when the primary goal is installing Allure adapters, making tests emit results, adding report scripts, or configuring CI publishing.
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).
Build serverless TypeScript functions on Zavu Cloud — declare agents + tools in code with defineAgent / defineTool, deploy with `npx zavudev deploy`, debug with `npx zavudev agents executions`. Use this skill whenever the user wants code-driven AI agents, custom tool handlers, or event-driven business logic.
Integration guide for Morph's WarpGrep (fast agentic code search) and Fast Apply (10,500 tok/s code editing). Use when building coding agents that need fast, accurate code search or need to apply AI-generated edits to code efficiently. Particularly useful for large codebases, deep logic queries, bug tracing, and code path analysis
Use in the BuilderIO/skills repo whenever adding, updating, publishing, documenting, validating, or wiring a public skill. Covers the repo-local skill files, root catalog docs, plugin metadata, @agent-native/skills dynamic install path, optional managed AGENTS/CLAUDE instruction blocks in ../agent-native/framework, and generated/synced Plan skill gotchas.
This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment.
Deeply researches a codebase, designs a feature through an annotated plan file, then decomposes it into an implementable issue hierarchy (parent + sub-issues with dependencies) on GitHub or Backlog. Nothing is published until you approve the exact content. Installs upstream's create-issue skill, which absorbed the earlier design-sprint skill.
An embedded development skill set for AI coding assistants, providing LLMs with end-to-end MCU firmware development capabilities. Covers multi-toolchain builds (Keil / IAR / CMake / PlatformIO), flashing, GDB debugging, serial monitoring, Modbus / CAN / VISA protocol debugging, peripheral driver adaptation, and pipeline orchestration. Supports Linux, macOS, and Windows.
Interview the user until the plan is clear, before any code gets written. Use when the user shares a new product idea or feature, or asks to build something whose person, problem, core action, or scope is not already documented in an approved IDEA_SCOPE.md or scoping doc. Also use when they say “grill me”, “poke holes”, “stress-test this”, “what am I missing”, or seem unsure what to build. Skip small fixes, copy tweaks, and work already covered by an approved scoping doc.
This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal task briefs that define terms and an exact success predicate linguistically, enumerate non-counting outcomes, set persistence rules with explicit stop and return conditions and effort floors, manage a diverse portfolio of parallel approaches with an approach registry and blocked-route bookkeeping, and gate the return on adversarial audit. Route agent topology and coordination protocols to multi-agent-patterns, runtime control surfaces and loop governance to harness-engineering, evaluator and quality-gate construction to evaluation, judge design to advanced-evaluation, and compaction or memory mechanics to context-compression and memory-systems.
Host an MCP server as a private, single-tenant Keboola data app — a dedicated remote MCP endpoint on your own Keboola compute (Keboola MCP is the built-in example, but it wraps any streamable-HTTP / FastMCP server) with client auth. Use when a user wants a private or self-hosted MCP endpoint, or would benefit from one but hasn't asked (see "When to use this"). Keywords: host/self-host MCP server as Keboola data app, private/remote MCP endpoint, deploy MCP to Keboola.
Fetch trending programming models from OpenRouter rankings. Use when selecting models for multi-model review, updating model recommendations, or researching current AI coding trends. Provides model IDs, context windows, pricing, and usage statistics from the most recent week.
Reviews and strengthens an existing implementation plan through adversarial rubber-duck dialogue. Scores completeness, feasibility, scope, testability, risk, and assumptions; asks one pointed question at a time; verifies checkable claims against local code and docs; and writes resolved answers back into the plan file until every dimension reaches 5/5. Use when asked to “review my plan”, “rubber duck this”, “stress test this plan”, “is this plan ready”, “challenge my plan”, “get this plan to 5/5”, “make this plan bulletproof”, “what am I missing”, “verify this”, “is this true”, “prove it”, “check this claim”, or “fact-check”, or before starting implementation on a non-trivial plan. For creating a plan from scratch, use plan-creator. For reviewing a code diff, use pr-reviewer.
Use this skill when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR preparation, and human approval boundaries
Master prompt engineering for AI models: LLMs, image generators, video models. Techniques: chain-of-thought, few-shot, system prompts, negative prompts. Models: Claude, GPT-4, Gemini, FLUX, Veo, Stable Diffusion prompting. Use for: better AI outputs, consistent results, complex tasks, optimization. Triggers: prompt engineering, how to prompt, better prompts, prompt tips, prompting guide, llm prompting, image prompt, ai prompting, prompt optimization, prompt template, prompt structure, effective prompts, prompt techniques
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.