agentleFS
jscott3201jscott3201/yet-more-skills/skills/orchestrate/SKILL.md

orchestrate

Skill4 starsChanged 2 months agoApache-2.0View on GitHub

Coordinate an explicitly requested end-to-end implementation and review workflow. Use available agents only when useful; not for explanation, diagnosis-only requests, or routine direct edits.

161 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use define-requirements, orchestrate-plan 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.
  • sson0-erSkill

    define-requirements

    Work with the user, one question at a time, to complete the requirements document (docs/claudex/<slug>/01-requirements.md). Run by the orchestrator (parent). Stays out of design and implementation.

    Also in 3 projects that use this

  • EternallLightSkill

    orchestrate-plan

    Use when executing a locked, reviewed PLAN.md by delegating the implementation to visible worker agents in Orca, herdr, or cmux ONE PHASE at a time — splitting the plan into context-window-sized phases, giving every phase a pristine worker context, and (when the plan touches INDEPENDENT repos) running one worker per repo IN PARALLEL. Triggers on "run the plan with a worker", "execute the plan in the other pane", "split the plan into phases and build it with workers", "build the backend and frontend in parallel panes". Not for edits you can finish inline; outside Orca, herdr, or cmux use tgc-skills:orchestrate.

    Also in 3 projects that use this

  • sson0-erSkill

    record-evidence

    How to record external facts (docs, command output, codebase findings) as evidence and design choices as decisions. Used by the researcher, designer and reviewer agents.

    Also in 3 projects that use this

  • PinkneyJiangSkill

    improve-architecture

    扫描代码库中的架构摩擦点,识别浅模块并挖掘深模块演进机会。生成可视化交互式 HTML 诊断报告,并在用户确认后闭环实施深度重构。

    Also in 4 projects that use this

  • kjnezSkill

    ticket

    Work on a JIRA/Linear ticket end-to-end: read ticket details, explore codebase, create a branch, implement with TDD, run quality checks, update ticket status, and create a PR. Use when the user provides a ticket ID to implement. Triggers on requests like "/ticket PROJ-123", "work on this ticket", "implement PROJ-123".

    Also in 4 projects that use this

  • xfstudioSkill

    reverse-engineer

    Expert reverse engineer specializing in binary analysis,

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 144 edited versions we read keep these.

  • 2

    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:

    Avoid simultaneous writers to the same logical state.

    line 19
  2. Distinctive:

    Commit, push, open a PR, merge, publish, or deploy only when the request and active policy cover that action.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 144 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

Coordinate a Bounded Change

Guide one coherent requested outcome from source inspection through implementation, validation, and a useful handoff. Respect repository policy and the user's authority boundaries. No named agent, memory server, ledger, or remote PR is required by this skill.

Choose the smallest effective workflow

Confirm the goal and inspect the affected source, instructions, and existing checks. Reuse context already established. For a small task, implement directly when authorized. For substantial work, form a compact outcome and acceptance brief; use specialist skills only for the boundaries actually involved.

Delegate only when independent work or context isolation repays setup, duplicated instructions, review, and integration. A small known-path lookup usually stays local. Give each worker one question or outcome, relevant paths, authority, exclusions, and the expected evidence; do not clone the entire conversation or ask every worker to survey the repository. Use configured roles and models, not hard-coded names or unauthorized cheaper-model switches.

Request conclusions with source pointers, actual checks, and unresolved issues rather than full transcripts. Verify consequential claims without repeating all discovery. Stop redundant exploration when its question is answered; preserve useful partial work. Judge total work across parent and workers, not just the coordinator's visible context. Without subagents, do the same work locally.

Avoid simultaneous writers to the same logical state. For intentional parallel implementation, agree on independent lanes and who integrates shared changes. Do not run competing implementations or contending performance measurements by default.

Implement and check

Preserve unrelated work. Test observable behavior at the appropriate seam, run focused checks and required gates, and inspect the resulting diff. Distinguish introduced failures from pre-existing or environmental failures; report both honestly. Missing optional tooling does not excuse skipping a required check or claiming it passed.

Use proportionate review. A second lens is useful for independent risks such as lifecycle/data flow or public contracts; it is not an automatic two-agent ceremony. Deduplicate findings, fix demonstrated defects within scope, and recheck the correction. Change the approach when feedback stops producing progress or exposes a material design gap, not because a fixed number of review rounds elapsed.

Close at the authorized boundary

Commit, push, open a PR, merge, publish, or deploy only when the request and active policy cover that action. Reuse valid authorization; do not re-ask unchanged questions. Never treat a review result as permission to merge.

Report the outcome, changed areas, actual checks, remaining gaps, and next useful action. Continue already-authorized work unless the user set a stop point. Leave a handoff when changing sessions or ownership, not after every minor step.

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.