Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
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 this skill when decomposing complex work into verifiable tasks and dependencies before or during implementation. Activates on mentions of write a plan, create a plan, break this down, task decomposition, implementation plan, what are the steps, plan the work, spec this out, or decompose this feature.
Project status dashboard — open issues, recent commits, active branches/worktrees, memory state, and scratchpad. Use when the user asks for a status report, project overview, "what's going on", "where are we", or wants to catch up on project state without the full /catchup reconstruction
Search watched registries for community legal skills, showing matches with descriptions and offering to show the full SKILL.md before install. Use when the user says "browse", "search skills", "find a skill for", "what's out there for", or wants to add a new registry to the watchlist.
Use when you need to act as an Elite Software Architect (Maestro) to manage complex repositories. It enforces a "Why over How" philosophy, maintains a persistent project memory (Brain), and orchestrates specialized sub-skills through a Plan-Act-Verify lifecycle.
Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small judgeable pieces, run a builder and a separate harsh critic on each, compare blind against the bar, and loop until it wins. Works for builds, writing, code, research, or design. Triggers on "/gauntlet-loop", "gauntlet loop", "gauntlet this", "make a gauntlet prompt", "loop until it beats X".
Discover which AE (Agentic Engine) knowledge bases accessible to the current user are worth searching, and decide whether to search at all, through read-only operations. Use when the user explicitly asks to search knowledge bases, internal documentation, or company materials. Also use when a task requires internal facts or business context, or when ae-analysis sees an enabled KB auto-discovery company switch before choosing its query route. Use internal context to explain data analysis results, anomalies, or trends and form evidence-backed conclusions. Do not use if the user explicitly asks not to access knowledge bases. This skill covers discovery and candidate selection; run the actual `+index` / `+grep` / `+read` / `+ask` retrieval with the `ae-kb` skill.
Detects when Luminance, Kira, or a similar bulk-review tool is in use, hands off the high-volume clause extraction to it, and QAs its output per the trust level in ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md. Use when user says "send to Luminance", "bulk review", "AI extraction", or when diligence-issue-extraction hits a high-volume category.
Install a community skill from a watched registry. Reads the allowlist first, fetches, shows the RAW SKILL.md (not just a summary), runs structural trust checks, runs skills-qa, and only writes files after explicit user approval. Use when the user says "install [skill]", picks install from browse, or provides a direct skill URL.
Use when the user wants to update, refresh, or reinstall the CopilotKit agent skills (the SKILL.md files that teach this agent about CopilotKit). Not for updating the CopilotKit codebase or project — this is specifically about refreshing the skills/knowledge this agent has loaded. Triggers on "update copilotkit skills", "update skills", "refresh skills", "skills are stale", "skills are outdated", "get latest skills", "my copilotkit knowledge is wrong", "copilotkit APIs changed", "skills seem old", "wrong API names", "reinstall skills", "skills not working right", "update your copilotkit knowledge".
ListenHub CLI skills router. Routes to the correct skill based on user intent. Triggers on: "make a podcast", "explainer video", "read aloud", "TTS", "generate image", "generate video", "做播客", "解说视频", "朗读", "生成图片", "生成视频", "幻灯片", "slides", "音乐", "music", "generate music", "翻唱", "cover song", "pixverse", "口型", "lipsync", "对口型", "parse URL", "解析链接", "提取内容".
Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
Help a clinic supervisor author a practice-area guide that configures how student-facing skills behave — intake questions, pedagogy posture (assist / guide / teach), review gates, cross-plugin checks, and local rules. Use when a supervising attorney wants to build or revise a per-practice-area guide, tune how the clinic skills behave for their clinic type, or set their teaching philosophy as plugin configuration.
This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff files, filesystem memory, or cleanup policies for context stored outside the prompt.
Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.
Disable a community skill installed through the hub without removing its files. Use when the user wants to temporarily quiet a community skill ("disable [skill]"), stop its hooks from firing while keeping its config, or re-enable a previously disabled skill.
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (older than 90 days), enriches context during conversations, and enforces privacy/anonymization rules before external API calls. Use when starting any C-suite advisor session, when context looks stale or missing, or before sending company data to an external service.
Run offline Python (`pydantic_evals`) or Node.js (`logfire/evals`) evaluations and review them in Logfire. Also redirect existing Braintrust `Eval()` suites. Use for eval setup, test datasets, AI scoring, agent checks, LLM judges, Braintrust migration, or Logfire Datasets & Experiments. Not for live traffic or infrastructure monitoring.
Mine the user's own agent session logs per model and per harness, count failure modes, and propose the top three as hazard rules. Use when the user asks to audit, review or mine agent history, session logs or transcripts for mistakes, failure modes or corrections, or asks why an agent keeps doing X.
Convene a structured LLM Council — five thinking-lens advisors (Red Team, First Principles, Expansionist, Outsider, Executor) plus anonymised peer review, forced debate on consensus, dual-chairman synthesis with dissent preservation, and optional Codex-powered Decision Science pass — to pressure-test high-stakes decisions. Adaptive modes (Quick/Standard/Deep) keep cost bounded; a persistent journal enables learning across runs. Mandatory triggers: /claude-council, "convene the council", "run this by the council", "I need the council", "council this", "pressure-test this", "stress-test this", "war room this", "debate this". Strong triggers: "I'm torn between X and Y", "this is a big decision", "help me think this through from multiple angles", "I need outside perspectives", "should I X or Y" (with real stakes — if binary with obvious answer, triage rejects per Step 1 rule 4). Do NOT invoke for factual questions, coding help, debugging, quick yes/no decisions, emotional support, or questions with one right answer — answer those directly. Optional suffixes: "with codex" enables Decision Science pass; "deep" forces Deep mode; "quick" forces Quick mode. Secondary invocation: /claude-council outcome <sha1> <note> records decision outcome. /claude-council meta runs journal meta-analysis.
Inspect and debug Honcho workspaces via the `honcho` CLI. Use when investigating peer representations, memory state, session context, or dialectic quality — any task that requires introspection of a Honcho deployment, including verifying that a recall/record memory loop is actually working.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', 'adversarial plan', 'hostile planning', 'cross-critique plan', '하이퍼플랜', '적대적 계획', '교차 비평'.
Suggest community skills based on recent activity in other plugins. Checks whether the community has built something relevant to a task and mentions it once, non-intrusively. Use when the user says "is there a community skill for this", "what else is out there", or asks for skill recommendations; also runs passively as part of other plugins' workflows.
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when the user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to set up Claude Code for a project for the first time, or wants to know which Claude Code features they should use.
Run parallel feature work safely with Git worktrees. Standardizes branch isolation, port allocation, environment sync, and cleanup so each worktree behaves like an independent local app. Optimized for multi-agent workflows where each agent or terminal session owns one worktree. Use when running multiple feature branches simultaneously, isolating experimental work, or coordinating multi-agent development across the same repo.
Uninstall a community skill that was installed via the hub. Confirms before deleting files, refuses to touch first-party plugin skills, and logs every action. Use when the user wants to fully remove a community skill ("uninstall [skill]", "remove this skill") rather than just disable it.
Guides the agent through connecting an MCP client to the hosted, unofficial Capacitor MCP server by Capawesome, which serves the official Capacitor documentation for v8, v7, v6 and next, the official and community plugin list, and the Capacitor posts from the Ionic blog. Covers client detection, setup for Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Zed and stdio-only clients, documentation version selection, verification, and troubleshooting. Do not use for installing or configuring Capacitor plugins, upgrading or migrating apps and plugins to a newer version, Ionic Framework UI components, Capawesome Cloud, or MCP servers other than the Capacitor one.
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
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.