nav-pilot
Dispatch a Navigator task doc to Pilot as a labeled GitHub issue. Use when user says "dispatch TASK-XX to Pilot", "hand off to Pilot", "send to Pilot", or…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,666 results
oro-fun-sigidi
Write, review, or evolve text that agents consume to guide behaviour. Use for skills, AGENTS.md/CLAUDE.md, prompts, subagent definitions, workflow contracts,…
mine-claude-md
Mine recent Claude Code sessions for non-obvious, multi-file CLAUDE.md candidates, adversarially verify them, and propose paste-ready additions. Use when the…
herdr-workstreams
Materialize selected engineering workstreams as visible, persistent Herdr workspaces after a portfolio or handoff review. Use when the user asks to set up,…
wakatime-automation
Automate Wakatime tasks via Rube MCP (Composio). Always search tools first for current schemas.
parallel-orchestrate
Decompose a large, multi-part goal into independent slices and run them as parallel Cursor subagents via the Task tool (Multitask Mode), then merge their…
ai-level-check
"What AI Level Are You?": Read real local AI conversation logs and produce an evidence-backed, traceable report on AI usage capability. Scan the logs left on the hard drive by agents such as Claude Code, Codex, and Antigravity to see how this person gives instructions, what tools they call, how they correct things, and what results they produce, then determine an LV0–LV5 usage level, work system and organizational strength, AI…
nvidia-oo-agents
Build AI agents using NVIDIA Object-Oriented Agents framework with Python classes, typed methods, and LLM-driven generation
claude-code-design-guide
Comprehensive guide to understanding Claude Code's architecture, Agent Runtime, tool systems, and Context Engineering for AI agent development
oh-my-cli-autonomous-code-agent
Use oh-my-cli to run an autonomous code agent that can read/write files, execute shell commands, and manage multi-turn coding tasks with approval gates and…
text-to-speech
Convert text to speech audio. Picks from a catalog of OpenAI (gpt-audio) and Gemini voices. Supports style/prosody control — natural language directions for…
create-skill
Create new agent skills following the Agent Skills open standard (agentskills.io). Interviews the user relentlessly about intent, scope, and edge cases before…
batch
Research and plan a large-scale change, then execute it in parallel across 5-30 isolated worktree agents that each open a PR. Use when the user wants to make a…
building-restate-services
Design, build, run, and test Restate durable services, virtual objects, workflows, and AI agents across TypeScript, Python, Java, and Go. This skill should be…
budget-planning
event budget plan framework. concept-planner and logistics-manager agent event budget establishand managementto do when reference. 'event budget', 'cost…
gov-funding-plan
Full pipeline where an agent team collaborates to generate government funding proposal announcement analysis, technical/business section writing, budget…
product-copy-formulas
Product copy formula library. Referenced by the detail-page-writer and marketing-manager agents when writing purchase-driving copy. Use for 'product copy',…
users
Find out who you are talking to in RevOS — the person's user id, email, name and role in the organization — through the RevOS MCP server, and use it to answer…
codex-cli-agent
Codex CLI sub-agent for dispatching tasks to OpenAI-compatible models via the `codex` binary. Use for code-focused tasks routed to GPT-5 Codex or any…
hf-download
Download primitives for HuggingFace assets - files, folder snapshots, and model weights with exponential backoff on rate limits. Use when pulling models,…
local-llm-bridge
Local Gemma 4 12B sub-agent. Routes bounded tasks directly to the optimized llama-server at localhost:8089 — no routing proxy, no cloud API, 2–5s typical…
local-llm-setup
Cross-platform setup wizard for the local Gemma 4 12B inference stack. Automates llama-server installation (binary download or Metal/CUDA/Vulkan/ROCm compile),…
rlm-distill
Distills uncached files into the RLM Summary Ledger. You (the agent) ARE the distillation engine. Read each file deeply, write a high-quality 1-sentence…
using-exploration-cycle
Use when starting any conversation - establishes how to find and follow the business exploration workflow.