get-goal-prompt
Generate a /goal command to execute an ideation project's specs autonomously. Reads the contract, builds a goal prompt with phase ordering and spec paths,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
Agents & models
25,740 results
chart
Use when an effort is too big for one agent session and the way from here to the destination isn't visible yet — the route itself is the unknown, not the…
skill-diet
Keep agent skills lean and correct. Use before editing an existing skill, such as adding a lesson; when a code change touches names or behavior a skill…
handoff
Compact the current conversation into a handoff document for another agent to pick up.
setup-matt-pocock-skills
Set in AGENTS.md/CLAUDE.md the `## Agent skills` block and `docs/agents/`, so engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain docs layout. On first use…
triage
Triage issues through a state machine driven by triage roles. Use when the user wants to create an issue, triage an issue, review an incoming bug or feature request, prepare an issue for an AFK agent, or manage the workflow. (Triage issues through a state machine driven by triage roles.…
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when the user wants to create, write, or build a new skill. (Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when…
cmux-terminal-multiplexer
AI-native terminal multiplexer with programmable socket API, full Playwright-equivalent browser automation, and agent team coordination — built for Claude Code…
grill-me
User-invoked entry that runs a /plan-grilling session — a relentless interview to sharpen a plan or design. Use when the user wants to stress-test a plan,…
plan-grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
skill-description-audit
Skill Description Audit. User-level skill; source: agent-skills. Cross-validation of an Agent Skill's SKILL.md description vs body: frontmatter spec compliance…
skill-eval
Behaviorally evaluate a skill: define 3-5 representative tasks, run each N>=3 times with and without the skill loaded in fresh agents, compare pass rates, and…
zellij-session-snapshot
Snapshot a zellij session's tabs together with the Claude Code (cc) session running in each tab, then restore every tab AND resume its exact Claude…
werewolf-judge
Werewolf judge skill (process execution version). Only responsible for state machine advancement, protocol validation, and public announcements; not responsible for player role-playing strategy.
skill-manager
Install a one-click Mac app for turning Claude Code skills on and off. It lists every skill in ~/.claude/skills with its description size and writes the…
bootstrap-agents-md
Bootstrap a repository's AI coding agent operating system — AGENTS.md, CLAUDE.md, CONTEXT.md (domain language), docs/agents (architecture, code-style,…
nemo-gym-pivot-datasets
Use when creating, validating, or documenting Nemo Gym pivot datasets from rollout, trajectory, chat-completion, Responses API, or tool-call artifacts. Covers…
grpo-rl-training
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
nvidia-broadcast
Use when controlling NVIDIA Broadcast through MCP to apply effects, process local media, select devices, or change camera resolution, or when Broadcast is…
yuminhong-perspective
A mental model from the perspective of Yu Minhong's philosophy of rebirth through adversity and self-deprecating motivation. Use when the user explicitly requests this person's perspective, mentions "yuminhong-perspective", or wants to apply his core methods to analyze a problem; do not trigger automatically for general questions.
guardrails-developer-create-guardrails
Helps developers create a NeMo Guardrails configuration for an LLM application. Use when users want to build, scaffold, configure, test, or iterate on input,…
nooa-agent-authoring
Author agents with NVIDIA-labs Object Oriented Agents (NOOA). Use when writing or modifying an Agent subclass, agentic methods (ellipsis bodies), docstring…
nooa-channels
Reactive input for NVIDIA OO agents — Channel/QueueManager for queued and event-mode input, race() turn dispatch, spawn() background jobs with JobHandle, and…
nooa-tools-and-skills
Give a NVIDIA OO agent capabilities — methods as tools, built-in tools (ShellTools, TodoManager), MCP servers, agent skills (Skill/TextSkill/SkillRegistry),…