multi-repo-change
Skill0 starsChanged 2 months agoMITView on GitHub
Coordinate a feature spanning several Git repositories without hiding their independent histories, tests, branches, or pull requests.
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- elixir-docsSkill
- feature-planSkill
- independent-reviewSkill
- package-readinessSkill
- parallel-deliverySkill
- safe-refactorSkill
- security-reviewSkill
- stack-elixirSkill
- stack-nextjsSkill
- stack-phoenix-liveviewSkill
- stack-rustSkill
- stack-svelteSkill
- systematic-debuggingSkill
- technical-writingSkill
- ui-validationSkill
- unslopSkill
- worktree-integrationSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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
Use one task identity across repositories, but keep each repository independently auditable.
- Distinctive: line 14
Create independent worktrees/branches per repository and per writer.
- Distinctive: line 15
Do not create a synthetic mega-checkout whose state is not represented by Git.
- Distinctive: line 19
If one repository's implementation changes the shared contract, return to planning and revalidate dependents rather than patching around …
- Distinctive: line 21
Use contract impact to identify affected callers, generated output, examples, packages, and migration instructions.
- Distinctive: line 23
Never expose repository or organization identities in reusable examples for this public project.
≈ “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
Multi-repository change
Use one task identity across repositories, but keep each repository independently auditable.
Procedure
- Define the cross-repository contract first: API, protocol, schema, versioning, ordering, and compatibility assumptions.
- Record the base SHA for every repository.
- Create independent worktrees/branches per repository and per writer.
- Do not create a synthetic mega-checkout whose state is not represented by Git.
- Validate each repository independently before integration testing the compatible SHA set.
- Record the exact tuple of repository SHAs used for cross-repository validation.
- Open separate PRs unless the hosting/project policy has a stronger native mechanism.
- If one repository's implementation changes the shared contract, return to planning and revalidate dependents rather than patching around drift.
Use contract impact to identify affected callers, generated output, examples, packages, and migration instructions. Record the compatibility directions tested and those omitted, alongside the revision tuple. Use generic consumer fixtures when reusable evidence must remain public.
Never expose repository or organization identities in reusable examples for this public project.
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.