Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Install a per-turn canary signal (e.g. starting every reply with the user's name and a turn counter) so silent context degradation becomes visible the moment it happens, and run a recovery protocol when the canary trips. Use when the user mentions a "canary", "context canary", or "canary check", asks to detect context rot / compaction / drift, says "you stopped using my name" or "did you lose context", asks "how degraded is your context", or wants an early-warning system for long agent sessions.
Maintain and audit Codex/CCFA skills, triggers, references, scripts, docs/SVG diagrams, installation dependencies, and release validation. Use for skill maintenance, GPT model adaptation, and family routing cleanup. Do not perform research writing or review.
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydantic_ai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents from YAML, or test agent behavior.
Use when you want to expose an n8n workflow as a tool the coding agent can call. Two cases. (1) Wrap n8n API capabilities the MCP doesn''t natively expose: folder deletion, project create/rename, tag rename/delete, instance metadata, credential creation. (2) Expose a general-purpose workflow as an agent tool: a workflow that calls a third-party API, runs business logic, or does any task you want the agent to invoke. Triggers on "expose as MCP tool", "build a tool for my agent", "I need to know X" where X isn''t an MCP tool, "delete folder", "rename tag", or any capability gap.
Use when an n8n-mcp account targets more than one n8n instance — i.e. the `n8n_instances` tool is available, the user mentions multiple n8n instances or environments (prod vs staging, several teams or clients), several agents or chats work on one account in parallel, a workflow / datatable / credential / execution call returns an unexpected NOT_FOUND or reads data you don't recognize, or a call is refused with `INSTANCE_AMBIGUOUS` or `INSTANCE_NOT_FOUND`. Covers naming the target instance on each call with the `instance` argument, setting the default with `switch`, verifying the target before high-stakes work — credential writes above all — and recovering from misroutes and fail-closes. Always consult this skill before operating on a specific instance, before any credential create/update/delete on a multi-instance account, or when a call hits the wrong/empty data or an instance error.
Initialize and continue short-drama or animated-comic projects based on a file system, with a creator-first five-document routing system, a local Dashboard, and decisions on production formats and Look Development. Use when users request “create/continue a short-drama project,” “check progress/next steps,” “do Look Development,” “open dashboard/short-drama creator workspace,” “export production materials,” or when a task spans multiple creative stages. Handle clear writing, asset, prompt, storyboard, editing, or review requests directly with the corresponding sub-skill.
Manage persistent Knowledge Graph for specifications. Provides read, query, update, and validation capabilities for codebase analysis caching. Use when: spec-to-tasks needs to cache/reuse codebase analysis, task-implementation needs to validate task dependencies or contracts, spec-quality needs to synchronize provides, or any command needs to query existing patterns/components/APIs. Reduces redundant codebase exploration by caching agent discoveries.
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.
Agent wallet, identity, and paid tools in one package. Register an agent, fund it via Stripe or USDC, then use the balance for web search, AI image generation, AI video generation, AI music creation, X/Twitter search, email send/receive, SMS and voice calls, contacts management, and 100+ LLM models. The funding and identity layer for autonomous agents that need to spend money, send messages, make phone calls, or call paid APIs.
Exception path. Use integrate-fusion-agent for Atlas/chat/agent. Only when the user explicitly requires in-app useAtlasChat and connectToHostApp cannot provide the EOS sidebar (standalone app, always rejects). Triggers: useAtlasChat, in-app atlas chat, embedded chat, vendored atlas-agent. Not for generic "add a chat".
Read a GitHub Issue, create a detailed plan in `_/local-plans/<issue-number>-<slug>.md`, and implement the code **after user approval**. After implementation, perform a security review (OWASP Top 10), run tests, and commit using Conventional Commits. Use for implementation requests that include an Issue number or URL, such as “implement Issue #N” or “start on this Issue.”
Secret safety for AWS Secrets Manager, secret management, credentials, API keys, tokens, and passwords. Prevents AI agents from directly fetching secret values and teaches runtime dynamic references with asm-exec so plaintext never enters the LLM context window.
Connects AI agents to remote Windows desktop applications on Amazon WorkSpaces Applications (AppStream 2.0) through the managed Agent Access MCP server, and guides reliable desktop automation. Covers connecting an agent to the MCP endpoint (SigV4, streaming URL, and Active Directory SAML/Domain Join), BLOCKING vs POLLING connect modes, the computer-use tools (screenshot, click, type, key, scroll), screenshot-budget and action-batching discipline, MCP tool forwarding (forwarded___ tools), session lifecycle and expire-on-delete, and troubleshooting connection errors. Use when building or debugging an agent that drives a remote Windows desktop or GUI application via WorkSpaces Applications / AppStream — including "dcv session not ready", "client_disconnected", 400 signing-region, POLLING/connection_status, SAML assertion, or forwarded tool questions. Not for Amazon WorkSpaces Personal/Core virtual desktops or general AppStream fleet administration unrelated to agent access.
Automatically implement all descendant sub-issues under a parent issue in parallel using worktrees, while respecting dependency order, then review before push, create PRs, monitor CI, and bring them to a mergeable state. Use for “implement the issue tree in parallel,” “implement all sub-issues under this issue,” “implement the whole tree in parallel,” or “automatically develop the issue hierarchy.” Divide work into per-issue planning (Plan: session inheritance model) and implementation (Implement: sonnet). Review before push; push, create PRs, and start CI only after review passes. Specify external checks explicitly with args.externalChecks as {"app", "context"} pairs. Use [] to confirm “none” and avoid unnecessary waiting; if unspecified, automatic merge stops; the legacy slug-only format fails closed for automatic merge. Opt in to automatic squash merge with autoMerge: true and explicit externalChecks, including trusted context declarations for all Apps. This requires merge-exec self-fetch revalidation and an actual check of server-side branch protection. By default, autoMerge is false and execution stops at a mergeable state for a human to merge. You can also delegate to a server-side workflow sample (see upstream docs/implement-issue-tree/auto-merge-sample.yml) and branch protection. Control execution order with parallelism (parallel) and dependencies (dependsOn). For strict serialization by phase, use phaseGate: true (opt-in): serialize the direct children of the root (phase parents) in sub-issues list order, and do not start the next phase until all descendants of the previous phase are merged or closed. By default, phaseGate is false and only the current post-order priority applies. To see in advance how many issues can be started and how many will be blocked, use dryRun: true (returns an estimate without writing anything). See implement-issue for implementing a single issue and implement-review-pr for PR reviews.
Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows. Use when an agent needs to install, verify, troubleshoot, configure, or operate Open Computer Use through its native CLI, stdio MCP server, or direct Computer Use tool calls.
Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough words or an existing policy to V2 categories, adding custom categories or topic-following rules.
Run a spec-driven agent loop where coding tasks live as markdown specs that move through inbox → active → archive, get implemented by Claude Code or Codex, and pass a review gate before they count as done. Use when the user mentions "loop factory", a "spec-driven loop", an "agent factory", wants repeatable/reviewable agent work, or when a repo has a factory/specs/inbox or factory/specs/active directory. Also covers installing and scaffolding the loop-factory CLI into a project.
One-click contribution flow for OpenDesign (nexu-io/open-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD; translate docs; fix a typo / write a blog; report a bug), the agent validates and opens a PR (or issue) for you. Trigger words contribute to open design, ship my OD skill, ship my OD design system, translate OD docs, report an OD bug, od-contribute.
Master skill that runs the full PlanetScale safe best-practices assessment — inventory, engine review, Insights, Traffic Control, webhooks, schema recommendations, codebase instrumentation, and agent operating model — then produces a unified recommendations report. Never applies changes without explicit approval. Use when the user asks to run the full assessment, all skills, or PlanetScale best-practices review.
Search and ask questions about coding agent session history across Claude Code, Codex, and Cursor. Use when asking what was worked on, what was tried before, how a problem was investigated across sessions, what happened recently, or any question about past agent sessions. Also use when the user references prior sessions, previous attempts, or past investigations — even without saying 'sessions' explicitly.
Find or sharpen the project idea and write the scope doc. The first and most important planning conversation — a focused flipped-interaction interview that pulls the idea out of the learner's head, then cuts it down to a coherent proof of concept. Run after 1-start.
Begin Build With AI: Basics, the Devpost learning hackathon. Checks you're in a fresh project folder, introduces flipped interaction, learns about your idea and background, and writes the learner profile that every later skill reads. Run this first.
Check if the compound-engineering plugin is up to date and recommend the update command if not. Use when the user says "update compound engineering", "check compound engineering version", "ce update", "is compound engineering up to date", "update ce plugin", or reports issues that might stem from a stale compound-engineering plugin version. This skill only works in Claude Code — it relies on the plugin harness cache layout.
INVOKE THIS SKILL when routing a LangGraph agent with a decision model (TypeSafe Jev, SemIf) instead of an LLM, or when auditing an existing agent for LLM calls that only produce a routing decision. Covers langchain-typesafe Noul/Choice/Score, reading answers correctly, threshold design, and LangSmith Gateway wiring.
Execute approved PlanetScale changes end-to-end without per-step approval when the operator has explicitly acknowledged the risk. Defines the risk-acknowledgment contract, scoped autonomy levels, sensible execution ordering, continuous status reporting, halt conditions, and rollback discipline. Extremely safe, very enabling.
Update the skill list and repository structure tree in CLAUDE.md based on changes since the previous update commit (tracked in _/.last-update-docs). Use when adding a new skill, changing .claude/agents/ or .claude/rules/, or when asked to “update the docs” or “update CLAUDE.md.” Also includes guidance to consult when asked to strengthen code comments or documentation comments.
Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic, Bedrock, Gemini, Strands) to a managed config, or stage a full hardcoded-to-LaunchDarkly migration.
Manage short-code bundles that authorize the local starchild CLI to talk to this agent, including the agent-shell local-exec channel and the local MCP proxy (stdio MCP servers on the user's machine). Use when connecting or disconnecting the starchild CLI (e.g. mint a CLI bridge code, list my CLI bundles, revoke an old CLI session, let the agent run shell commands on the user's own machine, or drive a local app via a stdio MCP server — Blender, Figma, Godot, computer-use, etc.).
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.