Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Meta-cognitive decision support that analyzes current context and surfaces intelligent next-step options to the user. Use this skill when: (1) User explicitly invokes /checkpoint, (2) Significant work has been completed and a checkpoint is valuable, (3) Uncertainty or ambiguity exists about requirements or approach, (4) Task complexity has expanded beyond initial scope, (5) Before finalizing or committing to ensure nothing is missed. This skill pauses execution, assesses the situation holistically, and presents 2-5 contextually-appropriate options via AskUserQuestion, with a recommended option and rationale.
Claude Code CLI tool expertise. Features: autonomous coding, slash commands, MCP servers, Agent Skills, hooks, plugins, CI/CD integration. Capabilities: setup/config, troubleshooting, skill creation, MCP integration, enterprise deployment, workflow automation. Actions: configure, troubleshoot, create, deploy, integrate Claude Code. Keywords: Claude Code, Anthropic, CLI tool, slash command, MCP server, Agent Skill, hook, plugin, CI/CD, enterprise, CLAUDE.md, agentic coding, terminal tool, workflow automation, code generation, skill creation, configuration, authentication, API key. Use when: learning Claude Code features, configuring settings, creating skills/hooks, setting up MCP servers, troubleshooting issues, CI/CD integration, enterprise deployment questions.
Local mirror of OpenAI Codex product documentation (learn.chatgpt.com/docs): CLI, Cloud, web app, IDE extension, hooks, skills, plugins, MCP, subagents, AGENTS.md, prompts, rules, sandboxing, models, pricing, security, and configuration. Use whenever the user asks how Codex behaves, how to install or configure Codex, or what a Codex flag, slash command, or feature does (including informal phrasing such as "hooks", "--resume", "sandbox modes", "cloud environments"). Read this skill's references/ before generic web search for Codex product questions. Do NOT use for Claude Code, Cursor, or other agents -- in particular, do not use for "Claude Code hooks" or general OpenAI API, ChatGPT, Realtime, or non-Codex coding help.
Audit Codex installation health and workspace context quality by combining the built-in `codex doctor` report with read-only checks for AGENTS.md scope, instruction bloat or duplication, Skills, MCP, hooks, config, thread-provider history scope, Git state, and repository-root hygiene. Use whenever the user asks for `/doctor`, `/checkup`, Codex health checks, context cleanup, AGENTS.md cleanup, unused or broken Skills/MCP/hooks, missing history after provider changes, slow or polluted context, or asks why Codex is ignoring rules. Default to diagnosis only; never edit, disable, delete, trust, install, update, authenticate, move, or clean anything without a separately approved finding-level diff.
Roll an oversized or slow Codex task into a fresh user-visible task with compact continuity. Use only for an explicit handoff or context rollover; not for ordinary continuation, delegation, full-history forks, Git migration, or handoff files.
Run the cold-start interview to learn your commercial contract practice and write it into the team practice-area configuration. Use on first use of the plugin, when the config file is missing or still contains template placeholders, or when the user says "set up the plugin", "configure commercial contracts", "guide me", or "let's get started". This is the only skill that should run on a fresh install.
Deliver an approved task through an auditable multi-model panel with test, review, and verification evidence. Use when the user requires a recorded panel trail for implementation. For the normal fast path, use implement-and-review or implement-tasks.
How the reference commerce agents of either role are structured, covering the loop, where each rule lives, skills, the backend interface, delegates, and model fields. Load when designing or reviewing the structure of a shopping or merchant agent.
Authoring and running behavioral evals for a shopping or merchant agent, covering the case shape, authoring rules, code graders and judges, the run pattern, and poisoned fixtures. Load when writing eval cases or rubrics or deciding how a suite runs.
The reference agents' cache-stable request assembly, covering the static system and per-request context split, the fixed tool list, the rolling conversation breakpoint, which config fields are prompt bytes, and verification. Load when writing or reviewing a commerce agent's prompt assembly, when cache reads are zero, or when a turn's latency or cost is the question.
The rules the reference agents enforce in code for third-party content, writes, grounding, identity, and memory, each with its module, plus two adversarial-eval rules. Load when handling untrusted tool results, guarding a write tool, or scoping what an agent remembers.
The reference presentation-tool contract, covering server-side enrichment, suggestion chips, the event stream, progressive rendering, both roles' built-in components, and adding a vertical component. Load when building or reviewing how a commerce agent's output reaches a frontend.
Compresses verbose intermediate agent handoffs into concise, loss-aware English while preserving decisions, facts, constraints, identifiers, paths, commands, acceptance criteria, references, and unresolved questions. Use only as an inline utility when a parent workflow needs a smaller temporary handoff; never replace canonical documents or route the project.
AI consultation CLI — query Gemini, Codex, or Claude for reviews and analysis. ALWAYS check this skill before running any `consult` command. Use when reviewing specs, plans, implementations, or PRs with external models, running parallel 3-way reviews (cmap), or checking consultation stats. The `-m` model flag is always required except for `consult stats`.
Export the conversation context. Write the purpose, intent, design decisions, and constraints shared in the conversation to the `.dev/contexts/` directory, and if a PR exists, also post them as a PR comment. Hand off to the next worker (reviewer, AI in another session, bug-hunting AI, etc.). Use when the user says "export the context", "export the conversation context", or "save the conversation to .dev".
Import conversation context. Reads past conversation context stored in the `.dev/contexts/` directory and uses it for continuing development or reviews. Use when the user says "load the context", "import conversation context", or "read the .dev context".
Guided customization of a commercial contract practice-area configuration — change one setting without re-running the full cold-start interview. Adjust risk posture, escalation contacts, review-guideline positions, NDA classification preferences, drafting style, review preferences, or matter workspace paths. Use when the user says "change my [some setting]", "update my config", "edit my review guidelines", "adjust my settings", or "customize".
Use this skill when the user's prompt requires (1) researching a topic across multiple sources, comparing options or alternatives, analyzing trends or history, understanding markets or industries, or reviewing literature or studies and (2) synthesizing that research into a comprehensive, narrative report. If you're planning to search the web or internal knowledge bases, consider using this skill. This skill coordinates research subagents, so use it only when you have a tool for spawning subagents (the Agent or Task tool); otherwise, research the question directly.
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.
(NS) Generate and update execution-handoff.md for planned SDD versions — operational prompt, per-task status table, and time tracking in seconds. Use at the end of planning after all task-NNN-*.md files exist, when tasks exist but handoff is missing, or when updating task status during version implementation. Do NOT use for ad-hoc coding without a version lifecycle, version partitioning (pm-version-partitioner), or GitLab-only issue execution (execution-gitlab-issue).
AI film production pipeline orchestrator for end-to-end content creation. Use when: coordinating production pipeline, generating scripts to film, orchestrating team, production planning, full workflow from concept to final edit. Keywords: film, pipeline, orchestrator, production, workflow.
Use when asked to find skill opportunities in a codebase, audit a repo for automatable workflows, decide what skills to write, or mine git history, existing automation, and recent Claude Code session transcripts for recurring multi-step procedures worth turning into agent skills.
This skill enables cross-model dialogue between Claude and Gemini with shared visual memory. Use when the user wants to generate images, have visual dialogues with AI, create scientific illustrations with continuity, or have multiple AI perspectives respond to the same prompt. Key trigger phrases: "generate an image", "visual dialogue", "ask the daimones", "resonance field", "Minoan tarot", "cross-model", "KV cache", "MESSAGE TO NEXT FRAME".
Produces and refreshes `.docs/handoff.md`, a 200-line session-continuity runbook for coding agents. Captures git state, working-tree changes, last validation commands, session decisions, blockers, resume checklist, references, and greenfield scaffolds. Triggers on: "update handoff", "session handoff", "refresh handoff", "/handoff", "/handoff init", "resume checklist", "cold-start primer". Use this skill when ending, pausing, resuming, or transferring in-flight project work across agent sessions.
Set up OpenAI's harness engineering methodology in any repository. Creates the full agent-first infrastructure: AGENTS.md progressive disclosure map, architectural layer boundaries with mechanical enforcement, testing framework, CI pipeline, golden principles documentation, garbage collection scripts, and pre-commit hooks. Use when asked to "set up harness engineering," "make the repo agent-ready," "add architectural boundaries," "set up testing and CI," or "adopt agent-first engineering." Works with any stack — React, Next.js, Python, Go, Rails, etc.
Design, build, diagnose, and evolve agent harnesses: instructions, tools, execution environments, durable state, context management, verification, recovery, and bounded autonomous loops. Use for unreliable coding agents, cross-session drift, premature completion, harness audits, or changes to the runtime around a model, including bounded typed-decision routing. Do not use for prompt rewriting alone, model training, general application architecture, or operating an already evaluated agent in production; route those concerns to their specialist skills.
Run a team of agents in Herdr panes, one pane per job (scouter, planner, designer, implementer, tasker, reviewer, security-reviewer, researcher, inspector). The calling agent stays the orchestrator: it spawns one CLI agent per role in sibling panes, dispatches self-contained briefs, collects file-based reports, and owns integration, gates, and git. Use when running inside Herdr (HERDR_ENV=1) for any non-trivial work: the user asks for a herd, team, roles, a designer or reviewer agent, parallel workers, or the task needs a survey (several files, another repo, tool conventions), touches more than a couple of files, or the project's AGENTS.md routes work through this skill. Do not use outside Herdr; a one-or-two-file change with no product decision is done directly.
Deploy and manage Hermes Agent (Nous Research) on remote servers. Self-improving AI agent with built-in learning loop, multi-platform messaging gateway (Telegram, Discord, Slack, WhatsApp, Signal, Mattermost), cron scheduling, MCP integration, and persistent memory. Supports Docker, bare-metal, and systemd deployments. Use when: deploying hermes-agent to a server, configuring hermes messaging gateway, managing hermes installations, troubleshooting hermes issues, migrating from OpenClaw to hermes, setting up hermes cron jobs, or any task involving hermes-agent deployment and operations. Keywords: hermes, hermes-agent, nous research, AI agent, messaging gateway, self-improving agent, openclaw migration.
Analyze JIRA tickets to determine priority and dependency order, grouped by dependency layer and relationship. Outputs a structured JSON plan with layered groups, branch names, repo assignments, complexity, and verification hints. Use before implement/forge, whenever the user gives you a list of JIRA tickets to work through, or when asked to "prioritize tickets", "order these JIRAs", "what should I tackle first", "plan my sprint", "sort my backlog", "which ticket should I do first", or "figure out the order for these tickets". Also trigger when the user provides a set of JIRA keys alongside a task to implement them.
This skill generates llms.txt documentation optimized for AI/LLM consumption. It should be used when the user says "crear llms.txt", "generate llms.txt", "documentar para AI", "document for AI", "crear documentacion para LLMs", "generate docs for LLMs", "make repo readable for Claude", or wants to create structured machine-readable documentation following the llms.txt standard.
Create, join, and manage teams on OpenAnt. Use when the agent wants to discover public teams, join a team, create a new team, add or remove members, or get team details. Covers "find teams", "join a team", "create team", "team members", "manage my team".
Max — the GTM-system copilot: the advisor that sits ABOVE Victor Shulga's skill stack and guides a person who downloaded the skill bundles. Max onboards them, diagnoses where their agency is, routes them to the RIGHT skill for their stage, explains what each skill is for and when to run it, enforces the gates, and always hands off to one concrete next action. Use whenever someone asks: "which skill do I use", "where do I start", "how does this system work", "what should I do next", "explain [skill]", "I have a GTM/outbound/sales/ retention problem — help me", "я загубився в скілах", "з чого почати", "що робити далі", "поясни скіл X", "I have no SDR", "show me the team", «у нас нема SDR», «покажи команду», «Макс, тренажер: <компетенція>», or opens the bundle for the first time. Max ROUTES and COACHES; it sends you to the skill that does the task (the trainer drill is the one it runs). NOT for running a specific skill end-to-end (invoke that skill directly) and NOT for inventing GTM advice outside the system.
Use this skill when the user asks to “add MCP server”, “integrate MCP”, “configure MCP in plugin”, “use .mcp.json”, “set up Model Context Protocol”, “connect external service”, mentions “${CLAUDE_PLUGIN_ROOT} with MCP”, or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
Model Context Protocol server development, tool design, resource handling, and transport configuration. Use for: mcp, model context protocol, mcp server, mcp tool, mcp resource, fastmcp, mcp transport, stdio, sse, streamable http, mcp inspector, tool handler, mcp prompt.
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.