Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Dynamic academic writing skill generator. Combines optional static writing skills with target-journal, field-top, or user-provided reference corpora, then revises a manuscript with a reviewable temporary skill. Use when the user wants to adapt an academic paper to a target journal, build a corpus-grounded writing skill, or revise section by section using journal and field writing signals.
Audit and reduce Codex desktop and CLI local-state bloat without deleting history or editing private app state. Use when Codex feels slow, logs or sessions consume substantial disk space, stale task worktrees accumulate, configuration contains dead project paths, or the user wants a repeatable maintenance report. Default to a read-only audit; perform archival or rotation only when the user explicitly requests cleanup.
Operating-instructions dispatcher for the openclaw-coder autonomous-programmer workspace. Routes every user message by surface — thread → working session, channel/DM → channel handling — and carries the global rules. The workspace AGENTS.md loads this skill first on every user message.
OpenClaw session cleanup assistant. Use when the user mentions cleaning up OpenClaw sessions, deleting old cron sessions, compacting or rebuilding sessions.json, or troubleshooting session file bloat. Once triggered, first check the number of session files under ~/.openclaw/agents/main/sessions/ and the size of sessions.json, then perform cleanup as instructed.
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.
Full Prism: multi-pass structural analysis with mandatory adversarial self-correction. Designs custom analytical passes, executes them with chaining, then attacks its own findings before synthesizing. Use for maximum depth on important code or artifacts.
Give sparse, evidence-based progress updates for long-running agent tasks and projects. Use when work will take more than 15 minutes, spans multiple milestones, involves delegated agents, or when the user asks for progress bars, status cadence, fewer updates, or a global cross-agent progress rule. Not for short answers or tasks with no meaningful intermediate state.
Rewrite a vague request into a precise EARS-format specification (event/state/optional/unwanted-behavior clauses, domain theories, concrete examples, enhanced prompt). Use when a feature request has no measurable outcome or trigger conditions (「ダッシュボード作って」「リマインダーアプリ」), when a prompt for AI-generated code/docs needs tightening before implementation, or when asked to 「プロンプト最適化」「要件を精緻化」「仕様に落として」. Do NOT use for: defining done-criteria / stop conditions for an autonomous run (goal-prompt-crafter), or tasks whose scope is already one clear sentence.
Discover and apply curated prompts from the prompts.chat collection to optimize AI interactions. Use when refining prompt engineering, finding domain-specific prompt templates, improving response quality, or building prompt-based workflows. Triggers on: prompt optimization, prompt templates, prompt engineering, prompt library, curated prompts, prompt discovery, and AI prompt patterns.
This skill should be used when publishing a new or updated skill to the claude-skills-site Astro website. Use this skill for both adding new skills AND updating existing ones on the site. Triggers on "/publish-skill skillname", "add skill to site", "publish skillname to skills site", "update skill on site", "edit skill on site", "sync skill to site", "republish skill". Reads SKILL.md from the skills repo, generates MDX frontmatter and body, picks the right bundle, updates bundle skills array, and commits/pushes both repos. For existing skills, pass --update to preserve apothecary_name, hero_image, and activity data while regenerating the rest. A hero image is generated by default (pass --no-image to skip).
Optimizes QE agent performance through transfer learning, hyperparameter tuning, and pattern distillation across test domains. Use when improving agent accuracy, applying learned patterns to new projects, tuning quality thresholds, or implementing continuous improvement loops for AI-powered testing.
Use when the user says 'set up respira', 'respira not connecting', 'check my respira connection', or 'fix respira'. Walks through first-time setup and diagnoses connection failures: timeouts, 401s, 403s, and plugin or server version mismatches.
Preserve useful project knowledge through StrictDoc, Magic Context, and available memory tools, including overlapping storage where useful. Maintain readable current norms in StrictDoc; update them when a genuine decision change is clear and briefly inform the user, without routinely churning the canon. Ordinary memories and explanatory docs can evolve more freely. Favor concise phrases, lists, tables, and occasional PS explanations; choose storage, detail, and timing with judgment.
Run the standard post-change validation flow after a fix, refactor, or new feature. Use when implementation work is done and you should validate the latest changes by invoking the repo's review skills, starting with review-changes and then repo-doc-maintainer, before giving the final close-out.
Write and improve agent skills (SKILL.md files). Use when creating new skills, refactoring existing ones, debugging why an agent ignores instructions, or improving compliance. Covers prompt structure, TDD for skills, description optimization, and rationalization bulletproofing.
Use when a question, decision, plan, tradeoff, or claim needs a rigorous verdict and one perspective is not enough. Spawns a panel of 3 to 5 subagent jurors that form independent blind opinions, deliberate anonymously under an anti-anchoring and anti-sycophancy protocol, and return one committed verdict with confidence, preserved dissent, and a concrete next action. Domain-agnostic across engineering, architecture, data, product, hiring, strategy, vendor choice, build-vs-buy, and research design. Trigger phrases include "convene a jury", "have agents debate and decide", "get a panel to decide", "multi-agent decision", "stress-test this and decide", "monte um juri", "tribunal de agentes", "painel para decidir". Do NOT use to only critique without deciding (use the-fool for that), to build a plan or write the solution itself, or for simple factual lookups.
Orchestrates comprehensive cognitive thinking patterns for complex problem-solving. Analyzes tasks to select optimal pattern(s) from foundational, reasoning, creative, metacognitive, specialized, and neurodivergent categories. Chains multiple patterns when needed and validates outputs before responding.
Operate Trau (display name Cobble) — the autonomous, ticket-driven development loop (trau.sh) — from a shell or MCP client: file, search and queue tickets, arm or pause the queue drain, watch and steer live runs, switch a run's provider, answer a PR or QA hold, settle an ADR conflict, read evidence, spend and conformance results, diagnose, resume or discard failed or quarantined runs, hand a run a secret, work a ticket's operator checklist, set config, manage QA sign-in accounts, tracker and forge connections, hosted collaborators and the local web hub. Use whenever the user mentions trau or Cobble, the trau hub, queue, drain, babysitting a drain, steering a run, a quarantined, parked, awaiting-qa or needs-human ticket, `trau doctor`, `trau forensics`, `trau update`, `trau connect`, QA accounts or proofs — or asks to start, stop, monitor, or debug autonomous ticket runs in a repo trau manages, even phrased as "queue this ticket", "what is the loop doing", "why won't the drain arm", or "why didn't COD-123 merge". Do not use for writing trau's own source code, or for general git/PR workflow questions unrelated to trau runs.
Design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.
Converts markdown plans into beads (tasks with dependencies) and polishes them until implementation-ready. The bridge between planning and agent swarm execution. Use when converting a plan to beads, polishing bead descriptions, adding test coverage beads, reviewing bead dependencies, or preparing tasks for agent swarm execution.
Use when the user asks to "create a metric", "write a metric", "design a metric", "build a metric for", "evaluate agent performance", "measure call quality", "track a KPI", "add a workflow metric", "improve my metric", "fix a metric", "debug metric results", "set up quality scoring", or "what metrics do I need". Also relevant when discussing LLM judge prompts, custom code metrics, evaluation triggers, VALID_SKIP patterns, section extraction, or metric best practices for Cekura voice AI agents. Covers both creating new metrics and reviewing, iterating on, or troubleshooting existing ones.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X", "explain X", "compare X and Y", "research X", or before content generation tasks. Provides systematic multi-angle research methodology instead of single superficial searches. Use this proactively when the user's question needs online information
The claude arm of `/dispatch` — spawn a worker via the `Agent` tool using the dispatch-worker subagent type with worktree isolation. Base is explicit — `dispatch arm-spawn --base B` writes the base file, then cd into the spawn dir before the Agent spawn so the WorktreeCreate hook forks at B. Worker self-commits via the gated `worker_commit` MCP tool; the orchestrator then does whatever `doctrine dispatch next` prescribes, one action at a time. Reached only from the `/dispatch` router on a claude↔env-marker agreement; do not invoke directly.
Review skills in any project using a dual-axis method: (1) deterministic code-based checks (structure, scripts, tests, execution safety) and (2) LLM deep review findings. Use when you need reproducible quality scoring for `skills/*/SKILL.md`, want to gate merges with a score threshold (for example 90+), or need concrete improvement items for low-scoring skills. Works across projects via --project-root
Execute implementation tasks from design documents using markdown checkboxes. Use when (1) implementing features from feature-analyzer output, (2) resuming interrupted work, (3) batch executing tasks. Triggers on 'start implementation', 'run tasks', 'resume'.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Use when someone has a business goal rather than a single query — "how can I use Linkup?", "enrich my leads", "build a competitor tracker", "research before my meeting", "vet this vendor" — and whenever designing or coding a Linkup-powered product, agent, or pipeline. Turns a goal into a multi-step Linkup workflow (which endpoint, which calls, what feeds the next step, where another tool takes over), grounded in bundled workflow patterns and 18 ready-made recipes that double as integration blueprints.
Understand a project through its existing memory when starting or resuming work, or when past decisions matter. Use StrictDoc docs/, Magic Context, claude-mem, and project evidence as complementary, overlapping sources. Identify current authoritative norms separately from history, recover relevant context, and surface meaningful contradictions. Choose the depth and retrieval path that suit the task.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Establish useful memory for a project that already has development history, or improve an incomplete memory setup. Survey the project and its existing evidence, then initialize or enrich human-readable StrictDoc docs/ with current norms and historical context. Use Magic Context and other available memory alongside it where useful. No previous workflow, legacy folder convention, or pre-existing StrictDoc skeleton is assumed.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
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.