lean-build
Skill389 starsChanged 2 months agoNo licenceView on GitHub
Resource and verification rules for leading a long phased build run by many agent sessions (builders, verifiers, a lead) on one shared machine: phase gate scripts (job-scoped incremental runs, one flat full gate before commit, disk floor, lock, cleanup on a passing exit), scratch and disk hygiene, load caps, which jobs get a top-tier verifier and which model, fix-round limits, iOS Simulator versus real device, and a speed review of an existing plan. Use when leading or setting up a multi-session build team, writing a gate script that several sessions share, reviewing a written plan for speed or cost, or when gates are slow, the disk fills, load is high, verifier rounds repeat, or someone asks whether tests need the real phone. Not for: writing a new implementation plan (use plan), executing a plan in one session with subagents (use build), or diagnosing one flaky or failing test (use cc-debugging).
- Deletes or force-pushes
14 other projects use a version of this.
Adopted by
Most recently taken up by
- gameyfin/gameyfintheir own version, first seen Nov 16, 2026
- jjsizemore/jjskillstheir own version, first seen Nov 16, 2026
- r-irbe/proof-skillstheir own version, first seen Nov 15, 2026
- sudeepgupta90/my-ai-marketplacetheir own version, first seen Nov 8, 2026
- mjlueck-hash/cavemantheir own version, first seen Nov 8, 2026
- dhruvsaxena1998/skillstheir own version, first seen Nov 8, 2026
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- JuliusBrussee/caveman★ 120ksame name
- gameyfin/gameyfin★ 1.2ksame name
- r-irbe/proof-skills★ 3same name
- nomdedev/agent-manager-template★ 2same name
- xingtu1996/dsh-xingtu-skills★ 2same name
- dhruvsaxena1998/skills★ 1same name
- jjsizemore/jjskills★ 1same name
- mjlueck-hash/caveman★ 1same name
- MMACABRE/SKILLS★ 1same name
- Gopyr/gopyr-skills-hub★ 0same name
4 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 repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- aposd-designing-deep-modulesSkill
- aposd-reviewing-module-designSkill
- aposd-simplifying-complexitySkill
- aposd-verifying-correctnessSkill
- ca-architecture-boundariesSkill
- cc-control-flow-qualitySkill
- cc-debuggingSkill
- cc-defensive-programmingSkill
- cc-pseudocode-programmingSkill
- cc-quality-practicesSkill
- cc-refactoring-guidanceSkill
- cc-routine-and-class-designSkill
- clarifySkill
- code-clarity-and-docsSkill
- code-standardsSkill
- gof-design-patternsSkill
- performance-optimizationSkill
- planningSkill
- welc-legacy-codeSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
“Common” is measured: kept by at least 6 in 10 of the 12 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.
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.

