moai-harness
Manage harness learning subsystem (status/apply/rollback/disable) OR create a harness via natural-language analysis (Context-First Discovery + name derivation…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-12 00:15
Agents & models
26,152 results
moai-jev-skill-suggestion
Guidance for a display-only skill-suggestion capability: how a caller should suggest a skill to the operator, how the emitted answer is read, and what must…
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the…
moai-ref-aside-browser
Safe-use reference for the optional Aside browser agent (the `aside` command-line tool and its MCP server), which works inside the operator's own logged-in…
moai-ref-jev-question-design
Question-design reference for the gated TypeSafe System One judgment capability. How to author typed questions that return useful, honest answers: compute the…
elevenlabs
Generate AI voices with the official ElevenLabs MCP server. Supports TTS (text → speech), voice cloning, dubbing in 32 languages, sound effects, and conversational agents (ConvAI). Ideal for card news voiceovers, short-form narration, podcasts, and audiobooks. 'Generate voice', 'Make me a narration',…
learning-project
I create a personalized learning project for you to study on your own. I diagnose your learning goals and current level, build a step-by-step roadmap, and automatically set up progress tracking and a dedicated learning CLAUDE.md. Use this for requests such as: - "Create a learning project to study claude code" - "English conversation…
notebooklm-slide-prompt
Receiving the body markdown of a lecture/talk/seminar as input, simultaneously (1) generating a slide deck prompt to paste directly into NotebookLM Studio and (2) a 5-Component image prompt per slide for Nano Banana (Gemini 3 Pro Image, a.k.a. Nano Banana Pro)…
minecraft-debug-mcp
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with `pnpm dev`, connecting to the local…
braindump
Long-term memory for agents — dense one-line facts appended to topic files, grepped back on later sessions. Use proactively whenever something surfaces that…
claims-triage
Triage an incoming insurance claim: check the coverage trigger against policy wording, band severity and complexity, screen for fraud indicators, set a…
delegate-to-ai
Decide what in your workload to hand to AI and what to keep yourself — like managing a fast, capable, but unreliable new hire — so you get leverage without…
file-access-preflight
Run the pre-flight checklist before an agent gets filesystem access — the scope boundary (which directories, read vs write), the secrets-exposure sweep, the…
idea-storm
Generate a big, wide spread of ideas for anything by running the prompt through many different lenses at once, then clustering and picking. Use when asked to…
poke-holes-in-this
Get only the weaknesses in something you made — no praise, no encouragement padding, just the holes and how to fix them. Use when asked to poke holes in this,…
prompt-library-builder
Build a personal library of reusable prompts for the things you ask AI again and again — so you stop rewriting the same request from scratch. Use when asked…
readonly-mcp-wrapper
Use when asked to expose a folder of notes or docs to Claude or another AI client, build an MCP server over Markdown or JSON files, let an agent read my…
subscription-auditor
Find the subscriptions you forgot you pay for — a tool-using agent audits statements and inboxes, prices the waste annually, and preps (never executes) the…
teach-me-in-layers
Learn a complex topic in progressive layers — a one-sentence version, then a paragraph, then the real depth — so you build a mental scaffold instead of…
reflexion
Implement reflexion loops for self-critique, learning from failures, and continuous agent improvement
agent-email-inbox
Use when setting up a secure email inbox for any AI agent — configuring inbound email via Resend, webhooks, tunneling for local development, and implementing…
brainstorm
Structured marketing brainstorming when direction is unclear. Use when the agent doesn't know which skill to run, the user is vague about what they need, there…
create-skill
Create new marketing skills for the mktg playbook. Use when the agent needs to add a new capability, someone says 'create a skill', 'new skill', 'add a…
dev-agent-spawn
Spawn Claude Code agents in new Ghostty terminal windows, tabs, or splits via AppleScript. Wraps in tmux for output capture and monitoring. Use when: opening a…