Orchestrate
Team-lead orchestrator: whichever frontier-class Claude model leads your session plans, routes, and verifies while cheaper Claude or Codex workers execute. Use for: orchestrate, delegate, conductor mode, save tokens, multi-agent.
Install
npx skills add thatmike1/claude-skills --skill orchestrategit clone --depth 1 https://github.com/thatmike1/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/orchestrate ~/.claude/skills/orchestratePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Orchestrate You are the conductor: the one model on the podium, and the conductor does not play an instrument. Your judgment is the expensive part — planning, routing, reviewing. The typing is cheap. Delegate it. **Any frontier-class model holds the podium identically.** Every rule below keys off capability *class*, never model identity. An Opus session that invoked this skill, or a Fable session that fell back to Opus mid-run, is the conductor with an unchanged decision tree. **Also fire on:** farm this out, team lead mode, use cheaper models, save credits, route tasks to the right model, run agents in parallel, big task on a budget — when delegation is requested or authorized by the project. ## The First Law **Economics chooses among the models that clear the quality bar. It never lowers the bar.** When unsure whether a cheaper tier can do a task well, go one tier up. If budget or rate limits cannot support the tier a task demands, stop and tell the user — never silently ship degraded work. ## T3 dispatch Inside T3, follow [references/t3-workers.md](references/t3-workers.md) before probing a CLI. It defines discovery, model options, visible child tasks and fresh review rounds. The ticket, write-set, ledger and verification contracts below apply to those tasks too. ## Step 0 — Probe the stage (once per session, then cache — re-probe on model change)
Details
- Skill name
orchestrate- Repository
- thatmike1/claude-skills
- Path
orchestrate/SKILL.md- Repo updated
- 18 November 2026
FAQ
What does the Orchestrate skill do?
Team-lead orchestrator: whichever frontier-class Claude model leads your session plans, routes, and verifies while cheaper Claude or Codex workers execute. Use for: orchestrate, delegate, conductor mode, save tokens, multi-agent.
How do I install the Orchestrate skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add thatmike1/claude-skills --skill orchestrate. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Orchestrate popular?
It lives in thatmike1/claude-skills, which has 10 GitHub stars and 1 forks.
Related skills
Afk Prompt
10thatmike1/claude-skills
Write a copy-paste prompt that hands one or more tasks (usually beads issues) to a fresh Claude instance to run autonomously while the user is away — no questions, no waiting for input. Includes picking which tasks are safe to run unattended. Use when the user says they're going AFK (shower, lunch, errand, overnight), asks "which tasks can just run without me", or wants an autonomous/batch prompt. For attended sessions the user will steer, use the live-prompt skill instead.
AI CV Scanner
10thatmike1/claude-skills
Mine Claude Code conversation history to answer questions about your AI experience. Scans session indexes, spawns parallel subagents to deep-dive relevant conversations, and drafts evidence-based answers. Use when user mentions CV, AI experience, questionnaire, scan my conversations, or needs to document their AI usage.
Arena
10thatmike1/claude-skills
Give several T3 child candidates the same prompt, rank them against a rubric written before they run, pick a base and graft the best of the rest into it. Run with /arena when one attempt at a non-trivial artifact would lock in the wrong shape.
Peek
10thatmike1/claude-skills
Read another agent session's transcript straight from its log on disk, with zero footprint on the observed session, and list which sessions are running right now. Covers Claude Code, Codex and the Antigravity CLI (agy/Gemini), and the T3 Code threads wrapped around any of them. Use before sending a message to another session, when observing or coaching a session that must stay untouched, when asked which T3 threads are still open or unsettled, or when asked to peek at, read, or follow what another session is doing.
Live Prompt
10thatmike1/claude-skills
Write a copy-paste prompt that hands a task (usually a beads issue) to a fresh Claude instance the user will actively work with, in either collaborative (discuss-approach-first) or off-the-leash (implement-end-to-end) mode. Use when the user says "give me a prompt", "prompt for <task-id>", or wants to start a fresh instance on a task. For unattended runs (user going AFK), use the afk-prompt skill instead.
Scan
10thatmike1/claude-skills
Scan Claude Code conversations for a date range / project and answer a specific question about them. Use when user says scan my chats, scan conversations, find a message where I said X, what did I do in <project> today, search my Claude history, recap a specific project, or asks a question about past Claude Code sessions.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.