parallel-builder
Skill0 starsChanged 49 days agoMITView on GitHub
Build multiple files/pages in parallel using subagents. Handles task division, shared file coordination, and build verification. Conflict-free by design.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- michaelboeding/skillstheir own version, first seen Jan 5, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- michaelboeding/skills★ 30same 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 repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- audit-fullSkill
- frontend-designSkill
- merge-prSkill
- pushSkill
- review-code-fixSkill
- review-docsSkill
- review-fullSkill
- review-ux-fixSkill
- shipSkill
- skill-creatorSkill
- update-docsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 27
Before spawning agents, identify files that appear in multiple batches:
- Distinctive: line 59
After all subagents complete:
≈ “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
/parallel-builder
Orchestrate building many files at once without merge conflicts.
When to use
- Building 3+ independent components/pages
- Migrating many files to a new pattern
- Generating boilerplate across a feature
How it works
- Divide: split work into independent batches (no shared file edits within a batch)
- Register shared files: identify files that multiple batches might touch
- Spawn subagents: one per batch, working on independent files
- Coordinate: main agent handles shared files after all subagents complete
- Verify: build + typecheck to catch integration issues
Shared File Registry
Before spawning agents, identify files that appear in multiple batches:
Shared files (main agent handles these AFTER subagents finish):
- Router config (e.g., routes.tsx, app.module.ts)
- Barrel exports (e.g., index.ts)
- Shared types (e.g., types.ts)<!-- CONFIGURE: List your project's typical shared/coordination files -->Rule: subagents never edit shared files. Only the main agent does, after all parallel work completes.
Batch Size Guidelines
| Files to build | Strategy |
| 1-2 | Just do it sequentially: no need for parallel |
| 3-5 | 2-3 subagents |
| 6-10 | 3-4 subagents |
| 10+ | 4-5 subagents max (diminishing returns) |
Pre-flight Checklist
Before spawning:
- All target directories exist
- Shared files identified and excluded from subagent scope
- Each batch's files are truly independent
- Build passes before starting (clean baseline)
Post-flight Checklist
After all subagents complete:
- Update shared files (routes, exports, types)
- Run build + typecheck
- Verify no duplicate exports or circular imports
- Spot-check a sample of generated files
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.