agentleFS
Sign inStart free
VoTruongDanhVoTruongDanh/Skills-Agent/.claude/skills/orchestrate/SKILL.md

orchestrate

Skill4 starsChanged 33 days agoMITView on GitHub

Coordinate multi-step plans across multiple roles, files, systems, or parallel workstreams. Use when the user has a complex request spanning multiple domains or needing decomposition. Triggers: orchestrate, coordinate, multi-step, full-stack, tổng hợp, làm nhiều bước.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 135 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    START: Read .ai-memory.md from project root.

    line 10
  2. Very specific:

    END: Update .ai-memory.md using Memory Compaction Rules with: workstreams, assignments, dependencies, execution order, and blockers/risks.

    line 11
  3. Distinctive:

    If any answer is unclear, ASK before proceeding.

    line 32
  4. Distinctive:

    Keep plans realistic for the current project.

    line 67
  5. Distinctive:

    Always read and update the memory file.

    line 71
  6. Very specific:

    All code snippets and example files referenced or produced by this skill must be UTF-8 encoded.

    line 80

“Common” is measured: kept by at least 6 in 10 of the 135 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

Memory Protocol

START: Read .ai-memory.md from project root. Check project architecture, team structure, past orchestration plans, ongoing tasks, and blockers. END: Update .ai-memory.md using Memory Compaction Rules with: workstreams, assignments, dependencies, execution order, and blockers/risks.

Goal

Break a complex request into a coordinated execution plan with clear agent assignments.

Agent Routing

  • Primary coordinator → read .kiro/skills/agents/agents/orchestrator.md and apply its knowledge
  • For planning phases → read .kiro/skills/agents/agents/project-planner.md and apply its knowledge
  • For each workstream, read the most relevant agent file:
    • Frontend tasks → read .kiro/skills/agents/agents/frontend-specialist.md
    • Backend tasks → read .kiro/skills/agents/agents/backend-specialist.md
    • Database tasks → read .kiro/skills/agents/agents/database-architect.md
    • Testing → read .kiro/skills/agents/agents/test-engineer.md
    • Security review → read .kiro/skills/agents/agents/security-auditor.md
    • Deployment → read .kiro/skills/agents/agents/devops-engineer.md

Socratic Gate

Before orchestrating, verify:

  1. What is the full objective? (end-to-end scope)
  2. How many domains are involved? (frontend, backend, DB, infra?)
  3. Are there hard dependencies or deadlines? If any answer is unclear, ASK before proceeding.

Workflow

  1. Read Memory — Load .ai-memory.md for project context and history.
  2. Decompose the objective into workstreams.
  3. Assign each workstream to the appropriate agent/role.
  4. Identify dependencies, blockers, and the critical path.
  5. Define parallelizable tasks and merge points.
  6. Produce an execution order with clear handoffs.
  7. Quality Gate — Read .kiro/skills/_scripts/checklist.md and verify each workstream output before merge.
  8. Update Memory — Save orchestration plan to .ai-memory.md.

Output format

  • Objective
  • Workstreams (with assigned agents)
  • Dependencies and critical path
  • Execution order (sequential + parallel)
  • Risks and mitigations
  • Done criteria for each workstream

Checklist

  • Objective clearly defined
  • Workstreams decomposed
  • Agents assigned to each workstream
  • Dependencies mapped
  • Critical path identified
  • Parallel tasks defined
  • Handoff points clear
  • Done criteria set
  • Memory file updated
  • Clean code chuẩn (Standard clean code applied)
  • Cập nhật đầy đủ tất cả các file liên quan (All related files fully updated)

Rules

  • Keep plans realistic for the current project.
  • Surface unknowns early.
  • Favor visible checkpoints over long hidden work.
  • Control scope: each workstream must state minimal files to touch; ASK before allowing wide-impact changes.
  • Always read and update the memory file.

Related Skills

  • /plan → read .kiro/skills/plan/SKILL.md — Detailed planning for individual workstreams
  • /create → read .kiro/skills/create/SKILL.md — Execute creation tasks
  • /deploy → read .kiro/skills/deploy/SKILL.md — Deploy completed work
  • /test → read .kiro/skills/test/SKILL.md — Validate each workstream

Encoding

All code snippets and example files referenced or produced by this skill must be UTF-8 encoded. When applicable, include encoding: "UTF-8" in SKILL.md front-matter and ensure saved files use UTF-8 (no BOM).

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.

Reviews can't be read right now.

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