parallelize-independent-work
Skill1 starsChanged 2 months agoMITView on GitHub
Delegate independently verifiable work when subagents can improve completion time or review quality.
In this repository16 other files it gives its agents.
- adversarial-refinement-loopSkill
- atomic-commitsSkill
- audio-verificationSkill
- build-without-fearSkill
- comfyui-assetsSkill
- diagnosing-bugsSkill
- finish-the-listSkill
- frontend-designSkill
- headless-terminal-workflowSkill
- prefer-second-monitorSkill
- require-external-communication-approvalSkill
- state-of-the-art-firstSkill
- try-it-firstSkill
- visual-verificationSkill
- web-design-guidelinesSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 8
When a task contains concrete outcomes that can progress independently, use subagents if available and authorized and the expected benefit …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Delegate independent outcomes
When a task contains concrete outcomes that can progress independently, use subagents if available and authorized and the expected benefit exceeds the coordination cost. Useful lanes include a bounded investigation, an isolated implementation, or review of a stable artifact. Keep simple or tightly coupled work local. Reconsider the split when new independent requirements arrive.
Give each agent a clear outcome and stopping condition, exact scope, edit ownership or a read-only boundary, and relevant verification expectations. Delegate early when that enables useful overlap. Do not duplicate another lane or invent work to fill slots. Model selection follows the user and host.
Assume the workspace is shared unless told otherwise. Reserve one writer per file and one owner for exclusive resources such as a browser fixture, device, or deployment. Subagents inherit the task's authorization, not additional rights.
The coordinator reviews returned findings and diffs, integrates dependent work, and verifies the combined result after the tree is stable. Collect all active results before completion or explicitly stop obsolete lanes. Report the integrated outcome and evidence rather than an activity tally.
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.