coordinate-work
Skill7 starsChanged 4 days agoMITView on GitHub
Delegate, parallelize, split work, coordinate contributors, integrate handoffs. Organize requested assignments; does not authorize delegation by itself.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- microsoft/amplifier-unifiedtheir own version, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- microsoft/amplifier-unified★ 5same name
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 repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- audit-and-resolveSkill
- context-pagingSkill
- design-skillSkill
- design-time-triggered-skillSkill
- design-validationSkill
- diagnose-and-repairSkill
- indefinite-loopSkill
- install-dev-skillsSkill
- operate-workflowSkill
- polish-docsSkill
- run-experimentSkill
- contract-disciplineSkill
- documentation-styleSkill
- evidence-disciplineSkill
- git-disciplineSkill
- scratch-spaceSkill
- testing-doctrineSkill
- context-compaction-procedureSkill
- maintain-scratchSkill
- refine-skillSkill
- security-hygiene-checkSkill
The file
Files
Coordinate work
Partition by ownership and interfaces. Keep tightly coupled work together; parallelism is a choice, not the goal.
For ongoing work, read and update scratch records in agents/scratch/: assignment ownership, dependencies, separate contributor records, and integration status.
- Establish the shared outcome, acceptance criteria, source baseline, and dependency order. Assign integration ownership.
- Give each assignment a bounded objective, owned files or artifacts, interface expectations, available inputs, and required return evidence. Make each handoff self-contained.
- Prepare authorized execution environments before dispatch. Separate writable outputs, preserve required uncommitted inputs, and allocate shared resources. Parallelize only noninterfering assignments.
- Reconcile returned deltas against their source baseline. Check interface changes, evidence, and unresolved decisions; reassign or clarify the affected work when assumptions break.
- Combine authorized changes at meaningful dependency milestones and validate end-to-end interfaces. Report what is reviewed, integrated, verified, and still pending.
Planning does not authorize delegation or integration. When contributors or isolation are unavailable, execute the same assignments sequentially and state the limitation. Passing isolated checks does not establish combined behavior.
Illustrative handoff: “Own the CSV parser. Return records matching the agreed schema, malformed-input behavior, and verification results. The importer owns persistence; integration must exercise parser output against the real importer.”
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.

