agentleFS
karim-bhalwanikarim-bhalwani/agent-skills-collection/skills/orchestrator/SKILL.md

orchestrator

Skill0 starsChanged 10 months agoMITView on GitHub

Specialized in managing project-wide constraints, context tiers, and coordination between specialized skills. Use when interpreting project rules, coordinating complex workflows, managing context and dependencies, or overseeing multi-skill project execution.

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

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 66 edited versions we read keep these.

  • 8

    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:

    Tier 1 (Constant): Ensure tech stack, OS platform, and critical security rules are always top-of-mind.

    line 24
  2. Distinctive:

    When preparing a task, the Orchestrator should output:

    line 41
  3. Distinctive:

    When first joining a project.

    line 49
  4. Distinctive:

    NO implementation: Only governs and validates.

    line 56
  5. Distinctive:

    DO NOT invent context: If rules aren't documented, explicitly state the gap.

    line 58
  6. Distinctive:

    Success Criteria: All team members agree on the handoff sequence and context requirements

    line 64
  7. Distinctive:

    Ignoring New Patterns: Not updating constraints when the codebase evolves.

    line 73
  8. Distinctive:

    Conflict Blindness: Not catching when a new requirement contradicts existing documented rules.

    line 74

“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 Skill - Project Governance & Context Management

Overview

The Orchestrator skill acts as the project's "Knowledge Keeper." It ensures that every action taken by other skills aligns with the project's technology stack, architecture styles, and critical rules.

Core Responsibilities

1. Tiered Context Management

  • Tier 1 (Constant): Ensure tech stack, OS platform, and critical security rules are always top-of-mind.
  • Tier 2 (Task-Specific): Load domain context (e.g., API patterns for web tasks, schemas for data tasks) only when needed to save tokens.
  • Tier 3 (Historical): Reference decisions.md to understand why certain patterns were established.

2. Constraint Validation

  • Authority: Maintain the "Approved Libraries" list.
  • Guardrail: Block any implementation that violates project-wide "Non-Negotiables" (e.g., "No raw SQL", "Mandatory Pydantic validation").
  • Escalation: Identify when a specialist's request conflicts with existing documentation.

3. Skill Coordination

  • Analyze a task and determine the sequence of skills required (e.g., navigator -> architect -> implementer -> guardian).
  • Manage handoffs between skills, ensuring the output of one serves as a clean input for the next.

Output Format: Tiered Context Block

When preparing a task, the Orchestrator should output:

  • Project Pillars: Core tech and architecture.
  • Hard Constraints: Non-negotiable rules for this specific task.
  • Handoff Map: Sequence of skills to be invoked.

When to Use

  • When first joining a project.
  • To clarify "how we do things here."
  • To validate if a new library or pattern is allowed.
  • To plan the multi-step execution of a complex feature.

Constraints

  • NO implementation. Only governs and validates.
  • NO writing source code.
  • DO NOT invent context. If rules aren't documented, explicitly state the gap.

Outputs & Deliverables

  • Primary Output: Tiered context block (Tier 1/2/3), handoff map, and skill routing recommendations
  • Secondary Output: Constraint validation report identifying conflicts or gaps
  • Success Criteria: All team members agree on the handoff sequence and context requirements
  • Quality Gate: Approved by project owner or lead before skill delegation begins

Common Pitfalls

  • Inventing Constraints: "I assume we use TypeScript" when it's undocumented. If rules aren't documented, explicitly state the gap.
  • Over-Constraining: Blocking everything with "team standards" that don't exist yet. Only enforce documented rules.
  • Poor Handoff Maps: Routing tasks to the wrong skill because you didn't understand the requirement. Always think through skill dependencies.
  • Missing Context Tiers: Throwing everything at an agent at once instead of tiering (Tier 1: always, Tier 2: on demand, Tier 3: history).
  • Ignoring New Patterns: Not updating constraints when the codebase evolves. Review and refresh quarterly.
  • Conflict Blindness: Not catching when a new requirement contradicts existing documented rules. Always cross-reference.

Integration Points

PhaseInput FromOutput ToContext
Project OnboardingProject README, existing rulesContext setupCreate initial Tiered Context Block
Task RoutingTask request + project contextSkill coordinationMap required skill sequence
Constraint ValidationNew implementation requestsApproval/FeedbackVerify against documented standards
Context RefreshEvolution of codebaseUpdated project-context.mdKeep context current as project matures
Conflict ResolutionConflicting requirementsEscalationDocument discrepancies between old/new rules

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.