Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Get an INDEPENDENT second opinion from the OpenAI Codex CLI — a separate reviewer runtime run over the real diff, not Claude reviewing its own work. Verifies Codex is available, resolves the scope (branch, a commit, or uncommitted), writes a focused instruction file grounded in the actual change set, runs `codex review` with disk-read sandbox so it can verify findings against source, then summarizes them by priority. Keeps secrets and credential values out of the instruction file, treats findings as candidates to verify locally before any fix, and reports an explicit clean result rather than fabricating one. Use only when the user explicitly asks for a Codex review or cross-review.
Route work across Arthur's private Mac, Windows/WSL, and Android agent environments. Use when choosing between ChatGPT Remote, raw SSH, app SSH projects, Computer Use, Logitech Flow, or SkillPort synchronization, or when diagnosing cross-device behavior; not for detailed monitor cabling.
Stress-test a design, idea, or approach by interviewing the user one question at a time. Each question comes with a recommended answer AND a one-line self-critique of that recommendation. After each user answer, briefly stress-test the answer against prior decisions before moving on. Use when the user wants a sharp grill on a design or decision tree without persistence overhead. Lighter than `/chief-grill` (which adds codebase verification and a session log).
Audit, prune, and improve agent guidance markdown files in repositories. Use when the user asks to check, audit, update, improve, or fix AGENTS.md, CLAUDE.md, or related guidance files. Adds missing commands and gotchas, removes stale entries, deduplicates, and keeps the file small and relevant. Scan for guidance files, evaluate quality against templates, output a quality report, then make targeted updates.
Research workspace context, APIs, implementation options, or external evidence before planning. The terminal artifact is always a spec at specs/<slug>.md; a plans/research/<slug>.md memo is optional supporting evidence when substantial investigation was needed. Accepts an optional goal path for provenance; see loam::setting-goals.
Create and manage Claude Code skills following Anthropic best practices and the agentskills.io specification. Use when creating new skills, understanding trigger patterns, debugging skill activation, or implementing progressive disclosure. Covers SKILL.md structure, YAML frontmatter schema, trigger types, enforcement levels, hook mechanisms, and progressive disclosure.
Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse, "delve"/"tapestry"/"testament", hedging stacks, tidy five-paragraph shapes), engineers burstiness and calibrated uncertainty, and preserves technical accuracy. Supports intensity levels: subtle, balanced (default), full, voice-match, anti-detector. Use when user says "humanize this", "make this sound human", "de-slop this", "rewrite without AI tone", "match my voice", "less robotic", or invokes /unslop. Also auto-triggers when text-quality is requested.
Use when a user wants to draft, revise, save, approve, or explicitly explore requirements for a rough, ambiguous, contradictory, creative, non-technical, or underspecified coding goal before implementation planning or coding, including explicit chat-only/no-file requirements exploration.
This skill installs and configures the **Tablestore Mem0** plugin for OpenClaw. Tablestore Mem0 uses Alibaba Cloud Tablestore as the vector store backend for mem0, providing persistent long-term memory for AI agents. Use this skill when the user wants OpenClaw to persist or manage long-term memory using Alibaba Cloud Tablestore as the backend. Triggers: "set up tablestore memory", "install tablestore mem0 plugin", "configure long-term memory with tablestore", "remember this".
Designs, evaluates, audits, and implements WebMCP tools: client-side tools a web page exposes to in-browser AI agents on document.modelContext, via registerTool, declarative form attributes (toolname, tooldescription), React useWebMCP, or Angular provideExperimentalWebMcpTools. Use when a developer wants to make a website or web app agent-ready, analyze a site or URL for WebMCP user journeys, add or review tools for in-browser agents, write tool schemas, descriptions, annotations, or evals.json, audit existing WebMCP tools, or fix Lighthouse "Agentic browsing" and DevTools WebMCP findings. Not for backend MCP servers over stdio or SSE, or for standalone scraping scripts.
Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.
Eva New User 2.4.2 standalone beginner tutorial. Use when the user explicitly says /eva-new-user, Eva New User, “I’m a new user,” “start the beginner tutorial,” “teach me how to use Eva,” or chooses the beginner tutorial after the bare /eva welcome message. Before starting, dynamically scan the Eva sub-skills installed in the current environment, then complete a minimal loop of “demonstrate, follow along, start independently” around the user’s current goal. The user may say “skip” at any time, specify a feature to learn early, or exit the tutorial and handle a real task directly.
Guide a first-time Forge builder through building Forge Guru, a Rovo Agent that answers Forge questions. Use for Forge onboarding, a first Forge or Rovo app, or resuming this tutorial. Route unrelated existing-app changes, debugging, reviews, and connector work to the specialist skills.
Apply the Karpathy understanding-first principle — verify what AI built, own your understanding, map the jagged capability landscape of LLMs. Use this skill when the user has used AI to build something and needs to verify it, wants to audit their own understanding, needs to know where LLMs are reliable vs unreliable, or says "verify this", "do I actually understand this", "what can I trust the AI on", "jagged capabilities", "understanding not outsourcing". Based on 46k-like quote post.
Amend an existing plan file — add tasks, modify pending or delegated tasks, and mark completed tasks that are invalidated by the change as [>] (needs re-run). Walks through analysis, cascading impact, and user confirmation before touching the file. When memory (wiki substrate) exists, it may also preserve durable amendment findings there. Reports goal impact and routes intent, boundaries, or validation changes to loam::setting-goals.
Use when agents must debate, conference, deliberate, or reach consensus on a goal — competing positions argue and converge on one deliverable, adversarial review with synthesis, multi-stakeholder deliberation, structured disagreement with a forcing-field deliverable. Triggers: 'have agents debate X', 'reach consensus on Y', 'argue distinct positions and converge'. Not for saved team configs, agents/<slug> artifacts, implementation, or open-ended research.
This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal task briefs that define terms and an exact success predicate linguistically, enumerate non-counting outcomes, set persistence rules with explicit stop and return conditions and effort floors, manage a diverse portfolio of parallel approaches with an approach registry and blocked-route bookkeeping, and gate the return on adversarial audit. Route agent topology and coordination protocols to multi-agent-patterns, runtime control surfaces and loop governance to harness-engineering, evaluator and quality-gate construction to evaluation, judge design to advanced-evaluation, and compaction or memory mechanics to context-compression and memory-systems.
Universal MCP client for connecting to any MCP server with progressive disclosure. Wraps MCP servers as skills to avoid context window bloat from tool definitions. Use when interacting with external MCP servers (Zapier, Sequential Thinking, GitHub, filesystem, etc.), listing available tools, or executing MCP tool calls. Triggers on requests like "connect to Zapier", "use MCP server", "list MCP tools", "call Zapier action", "use sequential thinking", or any MCP server interaction
Search conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the user asks to "search memory", "what did we discuss", "remember when", "find previous conversation", "check history", or before starting work to recall prior decisions.
Use after /audit resolved the RV ledger and wrote the reconciliation brief — you are the sole explicit writer of reconciled truth. Consume the RV + brief, write changes through two surfaces (direct edit for per-slice artefacts, REV for governance/spec), and hand off a resolved outcome to /close. Routed to from /audit.
Protocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via their host's skill loader. The orchestrator may also invoke this skill to understand the brief shape its dispatched subagents expect + what they're required to emit -- useful when writing briefs or debugging a subagent's behavior
Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.
Assess agentic AI applications against the OWASP Top 10 for Agentic Applications 2026. Use when reviewing autonomous AI agents, multi-agent systems, or agentic workflows for security risks including goal hijacking, tool misuse, privilege abuse, and rogue agent behavior.
Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context. Use when the user asks to check, audit, review, update, improve, or fix their AGENTS.md or CLAUDE.md, mentions "project rules maintenance" or "agent context optimization", or when the codebase has changed enough that the rules file may be stale. Scans the repository for every rules file, grades each against a quality rubric, outputs a quality report, and applies targeted edits only after user approval.
Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions to /launch as a mission brief. Wayfinding, not building: it produces decisions, never deliverables.
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.