cmux
cmux terminal orchestration — split panes, spawn Claude Code instances, send commands, poll output, report sidebar progress, automate the built-in browser, and…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-11 00:16
Agents & models
26,086 results
speaker-labeling
Use when several people speak in a video and you need to distinguish who is speaking or give speakers names: re-transcribe without speaker separation using voiceprints to separate speakers, then find evidence from the transcript and source information to assign each a real name, and write it back to the transcript's speakers. Only change speakers, not the body text. Not needed when only one person speaks, or the user only wants typos corrected.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
claude-local
Install the bundled agent conventions into a project's CLAUDE.local.md, plus an AGENTS.md entry point. Explicit invocation only.
write-great-skill
Workflow and eval bar for agent skills: draft with evals, polish, compress, verify, ship, with token-lean eval runs. Use whenever creating, editing or…
computer-use
Use Orca's computer-use CLI to inspect and operate local desktop app windows through accessibility trees, screenshots, and safe UI actions. Use for desktop app…
linear-tickets
Use Orca's Linear CLI through `orca linear ...` commands to read linked ticket context with `orca linear issue --current --full --json`, post completion…
orca-linear
Use Orca's Linear CLI through `orca linear ...` commands to read linked ticket context with `orca linear issue --current --full --json`, post completion…
orchestration
Use Orca orchestration for structured multi-agent coordination: threaded messages, blocking ask/reply flows, task dispatch, worker_done/escalation waits, task…
generate-key
Generate a test API key for Lab Nocturne. Triggered by /generate-key or naturally (e.g. 'get me an API key'). This is an alias for the image-key skill.
stats
View storage usage and quota statistics for Lab Nocturne. Triggered by /stats or naturally (e.g. 'how much storage am I using').
VLM
Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze images, describe visual content, or…
bff-spring
Spring Boot BFF implementation. Client detection, response tailoring, service composition. Trigger: apigen-bff, BaseBffController, ClientType, TailorForClient,…
langchain
Build LLM applications with chains, agents, and RAG using LangChain and LangGraph. Trigger: langchain, llm app, agent, rag, chains, langgraph
mlflow
ML experiment tracking, model registry, and deployment with MLflow. Trigger: mlflow, experiment tracking, model registry, mlops, model versioning
prompt-creation
Context prompts for AI assistants with schema validation. Trigger: When creating context prompts for AI assistants or documenting project config.
subagent-orchestration
Fresh subagents per task with two-stage reviews. Trigger: When coordinating parallel agents for complex workflows.
vectorize-search
Vectorize semantic search patterns for agent memory. Use when implementing embedding generation, semantic search, memory retrieval, or working with the…
pi-bellwether
Manage Herdr agents and panes from Pi with Bellwether 🐏🔔. Use when listing Herdr agents, reading pane output, sending/submitting text to another agent,…
session-search
Search and verify Joel's Pi, Claude, Codex, Cursor, Grok, and OpenCode session history. Use when asked to recover prior context, find exact transcript…
skill-generator
Meta-skill for generating new skills with proper format and structure. Use when creating new skills for the swarm system or when agents need to generate skill…
listenhub-voice
End-to-end audio generation with ListenHub-Voice-1.0 (text / image → audio). Supports sound effects, multi-voice dialogue, reference-audio cloning, and…
align
Turn a task prompt into a prompt-align brief page — reading, scope, done-means, and autonomy as editable sentences with ghost alternatives and AI steering —…