Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
This skill helps an LLM generate correct AxAgent observability code using @ax-llm/ax. Use when the user asks about axGlobals.onUsage, usageContext, centralized or multi-tenant usage accounting, actorTurnCallback, onContextEvent, agentStatusCallback, onFunctionCall, reportSuccess, reportFailure, getChatLog(), getUsage(), resetUsage(), debug traces, progress updates, or telemetry for AxAgent runs.
This skill helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax. Use when the user asks about RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, stage prompt controls, executorModelPolicy, maxRuntimeChars, agent.test(...), llmQuery(...), recursionOptions, or long-running agent runtime behavior.
Use this skill to run BMad (Breakthrough Method of Agile AI-Driven Development) as a harness-agnostic control-plane protocol that turns human intent into bounded, inspectable, resumable agent work. Compress intent into a five-field contract (Why, Capabilities, Constraints, Non-goals, Success signal); classify work as direct/bounded/initiative and route to the smallest safe path; carry decisions in durable artifacts; review as triage; route failure to the layer where ambiguity entered; and gate autonomy on observable acceptance with machine-readable status (draft/ready-for-dev/in-progress/in-review/done/blocked). Use when a change request, feature, delegated build, or multi-agent epic needs intent capture, bounded implementation, review, and resumability in any agent harness. Do not use for validating whether a problem is real (product-discovery), shaping bets before planning (product-shaping), formal spec/gate pipelines (spec-driven-development), or the issue-to-PR delivery flow (neckbeard)
Build and operate on-chain AI agents on BNB Chain using the bnbagent Python SDK — register agent identities (ERC-8004), and transact through escrowed agentic commerce (ERC-8183) as a provider (accept jobs, deliver work, get paid) or client (create, fund, dispute, refund jobs). Also covers x402 micropayment signing. Use for anything involving BNB Chain agent identity, agent-to-agent paid jobs, BSC escrow jobs, or ERC-8004/ERC-8183/x402.
Session-start briefing from Origin. Reads the project status file (the /handoff-maintained ledger of Active/Backlog work), then loads identity, preferences, and topic-relevant memories so the agent walks in with context. Surfaces any memories the daemon has flagged for human revision before the session uses them. Invoked as `/brief [topic]`. Call FIRST at session start, before any other Origin verb.
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full, ultra (default), supra (legacy alias: super-compress), silence. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Claude Code extensibility: agents, skills, output styles. Capabilities: create/update/delete agents and skills, YAML frontmatter, system prompts, tool/model selection, resumable agents, CLI-defined agents. Actions: create, edit, delete, optimize, test extensions. Keywords: agent, skill, output-style, SKILL.md, subagent, Task tool, progressive disclosure. Use when: creating agents/skills, editing extensions, configuring tool access, choosing models, testing activation.
Coding Agent Harness engineering methodology. For teams doing long-horizon project development with Coding Agents (Codex, Claude Code, Gemini CLI, etc.), build a complete harness engineering system on the user's project. Includes: project diagnosis, AGENTS.md + CLAUDE.md entry file generation, coding-agent-harness/ directory setup, Planning Loop, SSoT governance, Delivery Operating Model, Repository Governance, CI/CD, Long-Running Task Protocol, Adversarial Review Report, Review Routing, Worktree parallel development, Regression SSoT and Evidence Depth tiered regression, Walkthrough / Closeout Index closeout, Cadence Ledger, task-local lesson candidates and promoted lesson detail documents, Harness Ledger global context write-back ledger. Use this skill when the user asks to set up a coding agent development process, establish a regression testing system, design AGENTS.md / CLAUDE.md, plan an execution framework for long-horizon agent tasks, sub-agent review loops, adversarial review reports, build a harness, or mentions harness engineering. Also applies to scenarios such as "help me set up a set of agent development standards", "how to keep AI from drifting off on long tasks", "how to do regression testing for agents", "help me initialize the project's harness".
Scaffold Claude Code configuration specifically for Craft CMS projects. Generates CLAUDE.md and .claude/rules/ files tailored to the project type (plugin, site, module, hybrid, or monorepo). Only for Craft CMS projects — not for Next.js, Laravel, or other frameworks.
Plans a change as an ADR that records the decision, plus an implementation plan that belongs to it. Use this skill when the user asks to plan a feature or change, or to revise an existing plan or ADR. Do not use for implementing a plan (use implement-plan) or for small changes that involve no real decision.
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
Answer questions using Darwin's evolutionary thinking, patient observation, and resistance to confirmation bias. Use when the user explicitly asks for this figure's perspective, mentions "darwin-perspective", or wants to apply his core methods to analyze a problem; do not trigger automatically for general questions.
Optimize and build programmatic prompt systems with Stanford DSPy. Signatures, modules (Predict, ChainOfThought, ReAct), optimizer/teleprompter selection, compilation, caching, evaluation. Use when doing programmatic prompt optimization or building compiled prompt programs. Do not use this skill for unrelated requests; route to the nearest named specialist.
Detect CLOUD_AGENT vs LOCAL_WORKSPACE and apply the matching agent constraints. Use at session start when choosing tests, credentials, Hub continuity fallback, or whether local skill CLIs (e.g. graphify) exist. Hub MCP unavailable (not runtime alone) triggers the forge `[ADHD]` issue mailbox; never invent Hub or graphify state.
Plan, implement, review, and validate general ets_runtime changes with a planner/worker/reviewer workflow. Use when working under arkcompiler/ets_runtime, or when handling ets_runtime feature work, bug fixes, refactors, test additions, and compile-validation tasks.
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.
Use this skill when the agent exposes app-specific surfaces by registering custom MCP tools and resources inside the Flutter app (mcp_toolkit dynamic registry — AgentCallEntry, addEntries). Covers tool vs resource vs evaluate-expression, Map-based handlers, schema strictness, discovery via fmt_list_client_tools_and_resources, fmt_client_tool, fmt_client_resource, and lifecycle pitfalls.
INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.
[Hyper] Use when the user wants to invoke Google Gemini CLI (`gemini`) for reasoning, research, or AI assistance. Trigger phrases: "use gemini", "ask gemini", "run gemini", "call gemini", "gemini cli", "Google AI", "Gemini reasoning", or when users request Google's Gemini models, research with web search, plan-mode review, or want to resume a previous Gemini session. Do not use for generic writing, runbook cleanup, or local edits that do not require the Gemini CLI.
Teaches an agent graph engineering — both halves. Knowledge graphs (ontology design, entity/relation/event extraction, fusion, GraphRAG/memory serving; distilled and translated from Southeast University's graduate Knowledge Graph course, npubird/KnowledgeGraphCourse, 4.4K stars) and task graphs (agent orchestration — parallel fan-out, verifier separation, the stop rule, human gates). Use when asked to build a knowledge graph, extract entities/relations from text, design an ontology, dedupe/merge entities, add graph memory or GraphRAG to an agent, orchestrate multi-agent workflows as a graph, or LEARN graph engineering — in teaching mode the agent explains each stage with worked examples and generates visual diagram artifacts.
A one-question version of grilling. Used to sharpen the user's plan, decision or idea through follow-up questions, but asks only one question per round to avoid throwing multiple questions at once. Suited to users who explicitly ask to "ask only one question at a time" or who want a slower, more focused design interview.
Harbor CLI command reference and usage patterns. Covers harbor run, harbor jobs, harbor trials, harbor datasets, harbor adapters, harbor tasks, harbor view, harbor sweeps, harbor traces, harbor cache, and harbor admin commands. Use this skill whenever running Harbor evaluations, managing datasets, viewing results, debugging tasks, exporting traces, or working with any harbor CLI command. Also use when constructing harbor command lines, looking up flag names, or troubleshooting CLI errors.
Execute one task file from docs/specs/<slug>/ end-to-end — ground in the PRD/TechSpec, implement only the slice, and hand back evidence under the execution mode's settlement contract. Starts immediately when assigned, with no confirmation prompt. Use when the user says "run task_03", "execute the next task", "pick up a task", or when an implementation loop or daemon assigns a task file from a spec folder.
Initialize new JPKB projects with standardized documentation and folder structure. JPKB-specific version with category folders and fixed base path. Use when creating a new project in the jpkb repository, when the user says "init project", "new project", or when the target is the JPKB projects folder.
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.