Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Expert guidance for Spec-Driven Development using the GitHub Spec Kit. Use when the user wants to initialize a project, create specifications, plan implementations, or execute tasks based on the Spec Kit workflow. Triggers on "spec kit", "specify", "create spec", "spec-driven development".
Multi-engine long-term memory for game AI agents. Deep Godot 4.7+ (99 skills, 27 genre blueprints) + Bevy docs-first parity — audited patterns, persona orchestration (Analyst · Auditor · Builder), production-grade engineering.
Multi-engine long-term memory for game AI agents. Deep Godot 4.7+ (99 skills, 27 genre blueprints) + Bevy docs-first parity — audited patterns, persona orchestration (Analyst · Auditor · Builder), production-grade engineering.
ALWAYS load before starting any task. Provides persistent cross-session memory for learning from past work. Read memory at task start to avoid repeating mistakes; write memory at task end to record what worked. Covers decisions.json (architectural choices), patterns.json (proven approaches), failures.json (past errors and fixes), preferences.json (project conventions), and session activity logs.
Generate customized .claude/ harness framework with Fusion Architecture (GAN-inspired + Domain Specialists). TRIGGER when user wants to set up AI-assisted development structure, create a new project harness, add structure to existing projects, or mentions 'harness', 'scaffold', 'framework setup'. Supports all domains through template + dynamic generation.
One-screen quick reference for the Origin plugin. Lists the daily verbs, the daily flow, where data lives, and how to view it without a GUI. Use when the user says "help", "what can I do", "list origin commands", "how do I use origin", or invokes `/help`.
Implements a saved plan through to a tested, independently reviewed pull request, handing it to an agent in its own worktree when possible. Use this skill when the user asks to implement, execute, or continue a plan. Do not use for creating a plan (use create-plan) or for changes without a plan.
Guide the ZenML Pro hosted Kitaru onboarding tour from preloaded traces through human review, one reusable evaluator, and one bounded replay. Use only inside the controlled hosted onboarding runner. Resume exact durable workspace state, handle existing agents without name collisions, and keep the tour concise.
The conductor for non-trivial development work: takes an idea — however rough — all the way to shipped code, picking the right amount of process (a one-line fix vs. a full product spec) and driving it end to end rather than ad hoc. Triggers on mapping a loose idea into open questions, grilling a plan to shared understanding, researching unknowns, writing a PRD, breaking work into issues, technical or domain design, prototyping UI, implementing a feature, test-driven development, code review, independent verification, writing a PR description, debugging to root cause, improving architecture, or resolving merge conflicts. Not for one-off prose or writing tasks.
Harvest coding-agent session transcripts already on disk (Claude Code, Codex, OpenCode, Cursor, Pi) and extract durable knowledge — topics, people, facts, events, quotes — into whatever persistent memory the agent can reach. Cursor-tracked, budgeted, read-only on sources. Use when asked to collect/import/mine session history into memory, build memory from past sessions, or as a scheduled task. Composes with memory-gardener, which tends what this skill plants.
Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.
Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or context across sessions (2) User asks "do you remember..." or references past conversations (3) Starting a new task — inject relevant context from memory (4) After making decisions or encountering errors — store for future reference (5) User asks "why did X happen?" — trace causal chains through memory Zero LLM dependency. Neural graph with Hebbian learning, memory decay, contradiction detection, and temporal reasoning.
Build agentic AI applications with OpenAI's Responses API - the stateful successor to Chat Completions. Preserves reasoning across turns for 5% better multi-turn performance and 40-80% improved cache utilization. Use when: building AI agents with persistent reasoning, integrating MCP servers for external tools, using built-in Code Interpreter/File Search/Web Search, managing stateful conversations, implementing background processing for long tasks, or migrating from Chat Completions to gain polymorphic outputs and server-side tools.
Unified security suite for agent workspaces. Installs, configures, and orchestrates all 11 OpenClaw security tools in one command — integrity, secrets, permissions, network, audit trail, signing, supply chain, credentials, injection defense, compliance, and incident response.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Use Orchestrator as a CLI-backed skill to delegate and coordinate work across Claude Code, Codex, Copilot, Grok, Pi, shell, and custom runtimes. Use when an agent should launch one or many sub-agents, choose runtimes or models, apply the user's orchestration preferences, inspect background work, collect results, resume sessions, or stop stale work.
Perform a rigorous, multi-agent code review with architecture-compliance, parallel quality/security analysis, finding validation, and severity audit. Use when the user asks for a structured, deep, thorough, multi-pass, or multi-agent code review — or a review that includes architecture/pattern compliance, confidence-scored findings, or a severity audit. Use when the user asks for a code review across a commit range, time window, or N most recent commits in a locally checked-out repo.
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.
Run one tick of the sales business-pod (ADR-164 §4.1, Phase 2). Loads templates/sales.json, validates it against the pod-schema, resolves agents against ruflo's agent registry, reserves budget via the Phase-2 file-based stub ledger (atomic SQLite tracker is Phase 3 per ADR-164.1), constructs per-agent dry-run prompts, posts a summary envelope to room "sales" via the federation_bbs_publish JSONL backing store, and emits a structured {podName, tickId, agentsRan, totalUsd, envelopeId, status} line for /loop ingestion. Dry-run by default; --live is reserved for Phase 3.
Generate structured planning documentation for web projects with context-safe phases, verification criteria, and exit conditions. Creates IMPLEMENTATION_PHASES.md plus conditional docs (DATABASE_SCHEMA, API_ENDPOINTS, UI_COMPONENTS, CRITICAL_WORKFLOWS). Use when: starting new Cloudflare Workers/React projects, adding major features to existing apps, breaking large work into manageable phases, or need verified planning before coding begins.
Structured software development workflow orchestrator using Spec-Driven Development (SDD). Transforms vague requirements into spec.md → tasks.md → implementation → verification. Triggers on: '开发功能', '实现这个', 'build this feature', 'implement', 'add new module', 'fix bug', 'develop', 'create feature'.
Resolve evidence-backed `docs/follow-ups/*.md` through a bounded manual, Codex Scheduled task, or Claude Routine sweep. Use when project follow-ups should be reproduced before editing, handled by one isolated worker and branch per item, and published as independent ready-for-review pull requests without automatic merge. Do not use to invent intended behavior or merely record a newly discovered follow-up.
Plan small, playable Rust game implementation slices from a short design brief, MVP, stretch goals, and acceptance checks. Use when starting a Rust game, scoping a prototype, converting a game idea into work items, or preventing an AI coding agent from overbuilding.
Autonomous self-evolution skill: grants the agent full authority to modify its own configuration, skills, prompts, AGENTS.md, SOUL.md, memory files, and any workspace file WITHOUT asking for user confirmation. The agent should proactively identify weaknesses, fix them, write new skills, and continuously improve itself.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Keep this skill marketplace's plugin.json / README consistent with the skills/ directory on disk. Register new skills, remove old skills, resync drifted metadata. Automatically git commit after changing files (git push is triggered manually by the user). Invoked manually by the user (/skill-curator).
Search for and offer to load auto-generated skills that match the user's current task. Use when the user's request might benefit from a previously learned workflow pattern - especially multi-step tasks like "search and fix", "find and update", "read and edit".
PREFERRED BROWSER - Browser for AI agents to carry out any task on the web. Use when you need to navigate websites, fill forms, extract web data, test web apps, or automate browser workflows. Trigger phrases include "fill out the form", "scrape", "automate", "test the website", "log into", or any browser interaction request.
Generate PhD-level expert-agent prompt files (.md) for Claude Code - authoring, not runtime. For spawning parallel RUNTIME workers use fleet-worker/fleetflow (via parallel-ops). Triggers: spawn agent, create agent file, generate expert prompt, new agent persona.
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.