make-bot-ui
Use when building a custom UI (page, dashboard, buttons) that should wake the agent in its Rex pane, or when exposing that UI on Tailscale.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
Agents & models
25,719 results
poteto-mode
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or…
principle-guard-the-context-window
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not…
principle-never-block-on-the-human
Apply when tempted to ask 'should I do X?' on reversible work.
principle-prove-it-works
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy,…
principle-separate-before-serializing-shared-state
Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one…
rex-subagents
How pstack runs subagents in Rex. Every subagent is a Claude Code or Codex agent in a Rex pane to the right of the main agent, and a watcher wakes the main…
swarm
Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
amazon-ads
Guide for using the Marketplace Ad Pros MCP server to manage and analyze Amazon Advertising accounts. Use when working with Amazon Ads campaigns, performance…
autoresearch-prompt
Autonomous prompt optimization via eval-driven experiment loop (Karpathy autoresearch pattern). Use when user says autoresearch, prompt optimization, optimize…
harness-trace
Execution trace capture and token baselining. Use when user says trace, extract trace, count tokens, token baseline, or /harness-trace. Not for harness…
code-subagents
Implementation subagent dispatch patterns. Use when independent implementation work is available and subagents can execute it. Covers parallel dispatch,…
citadel
Route Citadel Organization Vault work to the right satellite skill. Use when a user asks about Citadel search, ingest, MCP setup, CLI commands, onboarding,…
audio-to-srt
Automatically generate clean SRT subtitle files from audio/video files. When the user wants to "turn audio into subtitles", "make an SRT", "speech to text + timecodes", or "add subtitles to a video", this skill must be used. By default it uses Groq Whisper-large-v3-turbo (cloud, word-level timecodes), with local Whisper medium as fallback. Claude…
improve-skills
Improves existing Agent Skills from real interactions by making small, reusable, evidence-backed updates. Use after a skill-driven task or reusable user…
skill-extractor
Extract experience from the current session and automatically generate a reusable Claude Code Skill. Use when user wants to extract skill, summarize into skill, solidify experience, generate skill, extract skill, create skill from context, save as skill,…
user-value-chain-glossary
Defines every member of MCPJam's user-value chain vocabulary — the six stages, the five stage states, the twenty-nine stage reasons, the seven failure…
prompt-optimizer
Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for any LLM model inside a chat interface — NOT…
andrej-karpathy-perspective
Karpathy's thinking framework (5 mental models + 8 heuristics) analyzes AI/learning/engineering/education/agent loop/Software 3.0. Triggers: Karpathy perspective, from-scratch, human-AI collaboration, AI-native school.
audit-agent-consolidation
Analyze agents for consolidation opportunities. Groups agents by configuration, tracks references, and manages refactoring.
audit-automation-gaps
Audit a repo's Claude Code automation landscape (hooks, MCP servers, skills, subagents, scheduled tasks) against the enforcement hierarchy, producing…
audit-derivability
Audit whether a documentation file earns its existence — could a fresh agent re-derive its conclusions by exploring the code, config, metadata, and structure…
audit-encapsulation
Audit and remediate skill-encapsulation violations — external citations reaching into private surfaces inside `.claude/skills/<X>/` beyond the slash…
audit-hooks
Audit Claude Code hooks for quality, compliance, and maintainability. Use after creating hooks, before releases, or for periodic quality checks.