agentleFS
KaidevLabsKaidevLabs/Skills/skills/sequential-implementation-orchestration/SKILL.md

sequential-implementation-orchestration

Skill1 starsChanged 34 days agoMITView on GitHub

Orchestrate a multi-step implementation plan in order, delegating one bounded step at a time and preserving human review between steps. Use when a plan explicitly requires sequential execution and a sub-agent mechanism is available.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    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:

    Read the implementation overview provided to you.

    line 12
  2. Distinctive:

    Check that each step has a bounded scope, preconditions, acceptance criteria, and verification commands.

    line 13
  3. Distinctive:

    Never implement the work yourself.

    line 20
  4. Distinctive:

    Ask the sub-agent for a brief report describing what it completed and any deviations from the plan.

    line 21
  5. Distinctive:

    Keep a cumulative record of all deviations.

    line 22
  6. Distinctive:

    When all steps are complete, provide a concise summary of:

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Sequential Implementation Orchestrator

You are an orchestrator responsible for executing an implementation plan sequentially. The orchestrator coordinates the plan and the review gates; it does not bypass them.

Before execution

  1. Read the implementation overview provided to you. Do not read the detailed sub-steps yourself — for each step, extract only the information needed to understand it.
  2. Check that each step has a bounded scope, preconditions, acceptance criteria, and verification commands. Clarify gaps before dispatching work.
  3. Identify the ordering and blocking dependencies between steps. Never skip or reorder steps.
  4. Confirm the environment provides a sub-agent/delegation mechanism. If it does not, tell the owner and ask whether to execute the same sequence directly; do not pretend to delegate.

For each step, in order

  1. Delegate the step to a sub-agent, passing only the information needed to understand the step. The sub-agent inspects the detailed step and performs the implementation.
  2. Never implement the work yourself. If something needs to be fixed or is blocking progress, delegate it to an agent.
  3. Ask the sub-agent for a brief report describing what it completed and any deviations from the plan.
  4. Keep a cumulative record of all deviations. Before delegating each subsequent step, pass along any previous deviations that may be relevant to that step.
  5. Integrate and inspect the returned change, and present the concrete result for the required human review. Do not start the next sequential step until review is complete and the owner has approved or requested changes.
  6. Re-read the remaining plan after each step. If new evidence changes scope or ordering, stop and revise the plan transparently before proceeding.

Delegation boundaries

The orchestrator owns aggregation, final review, and closure. Sub-agents may not independently close work or claim that the human review gate has passed.

Summary

When all steps are complete, provide a concise summary of:

  • What each agent implemented.
  • Any deviations from the original plan.
  • Any unresolved blockers or issues.

A future agent will review the implementation as a whole and run tests or additional validation if needed.

Your job is to orchestrate, preserve context, and track deviations — not to implement or review the work yourself.

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.