agentleFS
Sign inStart free
DylXBTDylXBT/claude-orchestrator-skills/orchestrator/SKILL.md

orchestrator

Skill114 starsChanged 5 months agoMITView on GitHub

Assemble the user's context brain, skills, connectors, and pipelines into one system they actually run end-to-end — and document it so a teammate could run it too. The capstone meta-skill. Works for any role.

80 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use worker, reviewer and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • stotihvSkill

    worker

    Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestrator.

    Also in 3 projects that use this

  • MicrosoftSkill

    reviewer

    ASP.NET Core ハンドブックの記事をレビューする。Use when: 記事をレビューする、ドキュメントを校正する、コードレビューする、PRをレビューする。技術ドキュメントのレビュー、品質チェック、校正。

    Also in 4 projects that use this

  • am-willSkill

    planner

    Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.

    Also in 4 projects that use this

  • yakatotechSkill

    advisor

    Provide improvement suggestions and advice on work content. Use for document review, efficiency suggestions, and best practices

    Also in 3 projects that use this

  • AWSSkill

    planning

    Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.

    Also in 3 projects that use this

  • OpenAISkill

    observability

    Vercel Observability expert guidance — Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards. Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 66 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask what the user already has (and help them build any gaps with the matching skill):

    line 14
  2. Distinctive:

    Write a short runbook: how to trigger it, what each part does, and how to recover when something's off.

    line 44
  3. Distinctive:

    If you can't document it, it isn't finished.

    line 50

“Common” is measured: kept by at least 6 in 10 of the 66 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Orchestrator

The payoff of the other skills is a system, not a pile of parts. This skill wires a user's context brain, skills, connectors, and pipelines into one workflow they run for real — and writes it down so it survives them being on holiday.

Role-agnostic. The orchestrator is whatever recurring, high-value workflow matters most in the user's world.

Step 1 — Inventory

Ask what the user already has (and help them build any gaps with the matching skill):

  • A context brain? (context-brain)
  • Any skills for recurring tasks? (skill-author)
  • Connectors to their live tools? (connector-setup)
  • A pipeline for their multi-step work? (pipeline-builder)

Then ask the key question: what's the one workflow worth orchestrating first? Pick a real, recurring, high-value one — not a toy.

Step 2 — Assemble the flow

Map that workflow as a single flow that connects the parts:

TRIGGER  → which brief/event starts it
CONTEXT  → the brain it reasons from
SOURCES  → the connectors it reads live
STEPS    → the pipeline/skills that do the work
OUTPUT   → the deliverables + the report
LEARN    → what folds back into the brain

The goal is no manual glue — the user drops in a brief and the system runs.

Step 3 — Run it end-to-end

Push one real instance through, brief to output, with no copy-paste in the middle. Where it breaks is where a part is missing or a hand-off is unclear — fix that part, not the symptom.

Step 4 — Document it (the real test)

Write a short runbook: how to trigger it, what each part does, and how to recover when something's off. The test of an orchestrator is that a teammate could run it without the person who built it.

Rules

  • Orchestrate one real workflow well before adding a second.
  • The best system is boring in the best way — one you'll still be running in three months.
  • If you can't document it, it isn't finished.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free