orchestrate
Skill36 starsChanged 21 days agoMITView on GitHub
Use this skill when coordinating independent agents with explicit ownership, dependencies, integration, and verification. Activates on mentions of swarm, parallel agents, multi-agent, orchestrate, fan-out, wave dispatch, research army, unleash, dispatch agents, or parallel work.
161 other projects use a version of this.
Adopted by
Most recently taken up by
- alexratmanpl/business-agent-skillstheir own version, first seen Nov 8, 2026
- gtonkov/claude-codetheir own version, first seen Nov 8, 2026
- edilsonvilarinho/usage-monitortheir own version, first seen Nov 8, 2026
- nathanonn/agent-skillstheir own version, first seen Nov 8, 2026
- peterpme/skillstheir own version, first seen Nov 8, 2026
- GDriem/agent-skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use define-requirements, orchestrate-plan and 9 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-erSkilldefine-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
EternallLightSkillorchestrate-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-erSkillrecord-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
PinkneyJiangSkillimprove-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
kjnezSkillticket
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
xfstudioSkillreverse-engineer
Expert reverse engineer specializing in binary analysis,
Also in 3 projects that use this
Other versions161 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 161
- Significant-Gravitas/AutoGPT★ 188ksame name
- rohitg00/pro-workflow★ 2.9ksame name
- apmantza/pi-lens★ 521same name
- boshu2/agentops★ 453same name
- quantumaikr/quant.cpp★ 403same name
- Noizefield/audio-plugin-coder★ 334same name
- kagenti/kagenti★ 303same name
- varun29ankuS/shodh-memory★ 294same name
- provencher/codex-skills★ 271same name
- first-fluke/fullstack-starter★ 226same name
151 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- brainstormSkill
- codex-imagegenSkill
- cross-model-reviewSkill
- demo-reelSkill
- deslopSkill
- dreamSkill
- gitSkill
- hyper-pr-reviewSkill
- implementSkill
- planSkill
- researchSkill
- super-good-prSkill
- tui-designSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 144 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 41
Before dispatch, define how partial progress becomes integrated progress: the artifact each consumer expects and when it is ready.
- Very specific: line 99
Read references/dispatch-briefs.md when composing worker, research, verification, or watcher instructions.
“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.
Files
Multi-Agent Orchestration
The coordinator owns integration and the final claim of completion.
The user's instructions take precedence over this skill; delegation, tools, and external actions remain subject to current host instructions and authorization, and this skill grants a worker no authority the coordinator lacks.
Check Capabilities Before Dispatch
Inspect the actual tools and current schemas instead of inferring capabilities from a product name. An external CLI reviewer is still delegation, not an escape hatch.
Choose the Shape by Dependency
| Work shape | Coordination pattern |
| Independent research questions | Parallel investigators, evidence-based synthesis |
| Disjoint features, stable interfaces | Parallel builders, designated integration owner |
| One change repeated across modules | Scoped transform or partitioned workers, combined checks |
| Dependent edits or shared mutable state | One owner for the dependency, parallel work around it |
| Consequential review | Independent read-only reviewers with distinct risk lenses |
| Small, tightly coupled change | Direct execution |
Fan out by default: anything that splits across independent surfaces runs in parallel, and the coordinator keeps working while workers run. The limits are resources, not agent count: one owner per shared mutable surface, one committer per index, and a sequential chain stays sequential. Check the critical path, since a branch waiting on one shared interface gains nothing from more agents. Do not cap a fleet to look frugal or serialize work to look careful; name the contended resource or don't restrict. A worker that double-checks a small change rarely pays; the verification triggers below say when it does.
Establish Ownership and Integration
Map shared resources as well as files: generated artifacts, schemas, lockfiles, fixtures, ports, build outputs, and caches collide across otherwise disjoint modules.
| Isolation | Appropriate use | Required coordination |
| Shared tree, disjoint paths | Small changes with clear ownership | One owner for contended files and the Git index |
| Separate worktrees | Independent branches or build state | Known base, branch, merge order, and integration owner |
| Read-only revision | Review or research | Fixed revision or diff plus permitted scratch outputs |
Worktrees isolate tracked files and the index, not ports or databases. Never overwrite a human's or sibling's edits to clear a conflict. In a shared tree, workers report patches while one coordinator stages and commits. Investigate a lock's actual owner before removing it; an inconclusive process listing does not establish that a lock is safe to remove.
Before dispatch, define how partial progress becomes integrated progress: the artifact each consumer expects and when it is ready.
Write Briefs
Give each worker the original request plus facts absent from their checkout, such as user corrections and untracked decisions.
| Brief element | Purpose |
| Outcome and scope | Result needed, owned surfaces, exclusions |
| Current evidence | Code, versions, interfaces, verified premises |
| Dependencies | What is ready, what is promised, who owns it |
| Authority | Permitted mutations, commit rights, external actions |
| Verification | Checks and acceptance conditions |
| Return | Changed artifacts or findings, evidence, limits, justified deviations, calls made where the brief was silent |
Let workers challenge a premise. A first independent review gets the raw change without coaching; a follow-up verification gets the finding and the fix claim so it can test closure. Templates are in references/dispatch-briefs.md.
Supervise
Harvest dependency-ready results as they arrive. Silence alone does not prove an agent is stuck; check its artifacts before interrupting. Polling must respect the host's limits. When requirements change, tell the affected workers.
A watcher needs a completion condition, failure detection, an expiry, and a stale-state check, with its signal tested on a known state. Cancel only processes this run owns. A watch loop checks for new user messages between polls and yields to them.
Harvest, Integrate, Verify
A worker's summary is a claim; inspect the actual diffs. Integrate at a stable checkpoint and run checks covering the combined behavior.
Independent verification is required when consequence or run length justifies it (shared or production state, an unattended run past a checkpoint, an acceptance check the implementer cannot alter) or when the project contract requires it. The implementer cannot certify an independent PASS. Tie each verdict to a revision or recorded snapshot.
| Verdict | Meaning |
| PASS | Declared scope completed, no unresolved blocking findings |
| FAIL | A supported defect violates the requested outcome or contract |
| INCOMPLETE | Review or a required check did not finish; list uncovered scope |
An interrupted review cannot grant a full PASS. Agreement does not establish severity; impact does. Do not reuse a PASS for changed runtime code.
Finish With an Honest State
Report integrated outcomes, the checks run and their revision, unresolved limits, and any blocked gate with the action it needs. Capture durable coordination failures in project memory: the contended resource, mechanism, fix, and conditions.
Evidence
Reviewed 2026-09-04 and 2026-10-27; sources and their limits are in references/evidence.md.
Anti-Patterns
| Anti-pattern | Better move |
| Choose a fleet size before finding independent work | Name useful lanes and their integration path |
| Serialize parallelizable work to look careful | Fan out; limit by shared resources, not agent count |
| Assume different files imply isolation | Inspect shared runtime resources and generated outputs |
| Let all shared-tree workers commit concurrently | Assign ownership of the index and commit operation |
| Vote-count findings | Verify mechanism and impact |
| Reduce review automatically over time | Match checks to current risk and changed evidence |
References
Read references/dispatch-briefs.md when composing worker, research, verification, or watcher instructions.
What This Skill is NOT
- Permission to ignore host delegation rules or user ownership.
- A fixed pipeline, agent quota, or requirement to use multiple agents.
- A substitute for integrated verification or the coordinator's judgment.
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
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.

