Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Applies targeted improvements to an existing pm-skills skill based on feedback, validation reports, or convention changes. Reads current files, previews proposed changes, writes on confirmation, and suggests a version bump. Use when improving a skill after validation or feedback.
Integrates SAP Cloud SDK for AI into JavaScript/TypeScript and Java applications. Use when building applications with SAP AI Core, Generative AI Hub, or Orchestration Service. Covers chat completion, embedding, streaming, function calling, content filtering, data masking, document grounding, prompt registry, and LangChain/Spring AI integration. Supports OpenAI GPT-4o, Llama, Gemini, Amazon Nova, and other foundation models via SAP BTP.
The user's dedicated browser for agents, a real browser signed into their accounts, with live logins and a persistent profile. Use it for any task that touches a website or browser (open, read, act, fill, sign in, download, verify). The user installed it precisely so agents default here unprompted, over in-app browser tools, devtools/playwright automation, or headless fetching. When the user says "use neo", "use browserclaw", "use BrowserOS", or "use BrowserOS neo", use BrowserOS neo over MCP.
Plan and execute large refactor or rewrite efforts efficiently with parallel multi-agent analysis and implementation. Use when a user asks to refactor many files, split workstreams, analyze a target code area, and coordinate sub-agents with clear ownership and dependency-aware execution.
Checks for newer pm-skills releases, compares local vs. latest version, previews what would change, and updates local files after user confirmation. Generates a structured update report documenting changed files, new capabilities, and the value delta between versions. Use when you want to bring a local pm-skills installation up to date.
Deprecated compatibility skill. In generic npx skills environments this must degrade honestly to a resumable handoff, because real transcript-backed thread import is not guaranteed. Prefer save-handoff here, and use native connectors when you need actual session capture.
Critiques an implementation plan—or a wayfinder map/ticket—from multiple angles (security, simplicity, edge cases, scope creep, codebase conflicts, tech-specific best practices) via parallel critic subagents. Trigger: user says “kritisiere den plan,” “plan check,” “plan-kritik,” “blinde flecken,” or “/plan-critics”—also invoke when a planning agent wants to validate its own plan before presenting it, or a wayfinder session wants a resolution checked before closing a ticket. Must be called at top level (not inside a subagent)—it uses the Task tool.
Use when asked for an implementation plan or execution contract for one or more GitHub issues or an in-chat task, including a read-only review of the next safe step, without drafting or provider access, when the source or contract is incomplete, or a retained approved GitHub plan has an existing amendment chain or a changed published integration decision needing durable consumption.
Guides authoring, reviewing, and validating agent skills (SKILL.md + metadata.json + references/ + scripts/) in this Capgo skills repository and similar ones. Covers trigger and negative-trigger design, lean SKILL.md with a when-to-load reference index, traps over basics, verification and error-handling sections, version tagging of facts, subagent-oriented skills (main-agent vs subagent split), optional when_to_use frontmatter, inline snapshots with allowed-tools, skillgrade evals, and this repo's canonical skills/ to plugins/ mirroring and registration. Use when creating a new skill, tightening a skill's description or triggers, splitting a long skill into references, or fixing `bun run lint-skills` failures. Do not use for app documentation, README or marketing copy, or library code that is not a skill.
Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
Manage this repo's agent skills with the skilly CLI — add or remove bundles/skills, pull hub updates. Use when the user wants skills or bundles added, removed, or updated. For a skills.sh URL use the skills CLI directly, not skilly. Not for repo bootstrap (that is `skilly setup`, run once).
Implement an approved spec or focused task through stale-safe source edits. Use this skill when the user says "implement this", "cook this spec", or "fix this bug". Use it for `/cook .cheese/specs/<slug>.md`. Also use it when the user says "go" with clear acceptance criteria. Run it alone for an unambiguous task. Use `--prototype` when the user says "prototype this", "go prototype it", or "spike this out" and wants to refine the result round by round. A spec helps but is not required. Do not use it for fuzzy planning (`/mold`). Do not use it for no-write discussion (`/culture`) or review-only work (`/age`).
Route generative media requests before any creative planning or provider execution. Use this when the user asks to generate, modify, dub, animate, or assemble image, video, audio, workflow, or analysis-derived media and the first decision is which generation controller should own the job.
Coordinates multi-session, delegated, or long-running work with persistent state, recovery checks, and explicit status transitions. Use when a task spans multiple turns, multiple agents, background jobs, or scheduled loops, or when interrupted work must be resumed reliably.
LangSmith tracing and trace debugging for AgentSeek templates. Covers CLI installation, adding tracing to LangGraph apps, querying traces, and inspecting run IO. Use when debugging agent backends, investigating slow traces, or adding observability to a template.
Use when a workflow or capability must become a new agent skill, when an existing skill must be updated or standardized without losing its purpose, when a user-level or project-level variant is needed, or when a skill needs validation, evaluation, scaffolding, scripts, tests, or a Mise task graph.
Laravel AI SDK for building AI-powered features. Use when creating agents, generating images or audio, working with embeddings, vector search, or testing AI features. Triggers on tasks involving laravel/ai, AI agents, tool-calling, structured output, streaming, embeddings, reranking, or AI faking in tests
Search, install, and manage Agent Skills locally and from GitHub, then help decide whether the task really needs a skill or another customization primitive. Use when looking for skills, installing skills, managing a skill collection, or choosing between a skill, prompt, instruction, or agent.
Install, initialize, verify, and troubleshoot RTK (Rust Token Killer) for AI coding agents. Use when you need to reduce shell command token output, confirm the correct `rtk` binary is installed, choose between Homebrew, install.sh, or Cargo installation, wire up `rtk init` for Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, or OpenCode, or use compact wrappers such as `rtk git status`, `rtk read`, `rtk grep`, `rtk test`, `rtk lint`, and `rtk gain`. Triggers on: rtk, rust token killer, token saver cli, rtk init, rtk gain, codex rtk, gemini rtk, opencode rtk, claude hook token reduction.
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.
Use when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval, realtime progress, provider rate limits, crash-safe execution, and Agent Evals handoff. Covers AgentKit, `step.ai`, `step.run`, `step.waitForEvent`, native realtime, and when to use lower-level Inngest primitives instead of an in-memory agent loop. Use `inngest-agent-evals` with this skill when the user wants scoring, sessions, experiments, deferred scorers, or outcome-based evaluation for the agent.
Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete stateful, server-managed Agent resources (including mounting files, skills, and tools) before executing conversations.
Use this skill when adding or changing AI chat, text generation, reasoning, tools, model selection, or structured JSON output in a Customware-generated React Router and Hono app. It covers the server-only Customware AI Gateway, AI SDK with the OpenRouter adapter, AI Elements UI, supported model choices, and mandatory live model and structured-output checks.
Run the CCS Align seat's hourly breathing cycle — verify the local claude-mem worker is healthy, pull needle observations through search → timeline → get_observations, land them in a seat-owned middle cache via atomic grab → append → filter exclude-marks → replace, manage exclude marks, and walk house → project → seat rules to detect conflicts (SHADOW_HOUSE, DENY_ALLOW, DRIFT, CLOCK_HEADER) with an append-only rules-report.md. Use when asked to run CCS Align, breathe the alignment seat, refresh the middle cache, exclude or restore an observation, walk rules, check rules conflicts, or check the Worker Watch board.
Use this skill when coordinating independent agents with explicit ownership, dependencies, integration, and verification. Activates on mentions of swarm, parallel agents, multi-agent, orchestrate, fan-out, wave dispatch, research army, unleash, dispatch agents, or parallel work.
Collect structured visual feedback from humans using AnyCap's annotation tool, or create and iterate on diagrams using the interactive whiteboard (Excalidraw). Covers image annotation, URL/web page review with screen recording, video review, audio feedback, and collaborative diagramming with Mermaid input. Use when you need a human to point at things, mark regions, draw on screenshots, review a web page or UI, narrate feedback over a recording, provide any spatially-grounded visual input, create or iterate on architecture diagrams, flowcharts, or wireframes. Also use when you need to present work-in-progress to a human for approval or revision. Trigger on: get feedback, show to user, review UI, annotate, mark up, visual feedback, screen recording, user review, human-in-the-loop, approval flow, interactive review, whiteboard, diagram, draw, flowchart, wireframe, architecture chart.
Turn a high-leverage design decision into a validated spec through grounded dialogue. Use it when a leverage trigger fires (auth, irreversible effects, concurrency, contracts, destructive ops, a new slice, a cross-slice dependency, an invariant gap) or when the user asks for a spec or design. Typical phrases include "let's design X", "shape this into a spec", "what should the API for Z look like", and "/mold". A feature ask with zero fired triggers is a `/cook` mini-spec, not a mold; route it through `/cheese`. Do NOT use it for free-form discussion without artifact intent (`/culture`), direct implementation (`/cook`), or research-only questions (`/briesearch`). Ceremony scales to the ask through `references/tiers.md`, so a small clear change gets a validated mini-spec without a write-approval turn.
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.