agentleFS
MicrosoftKnown publishermicrosoft/amplifier-foundation/skills/per-repo-conventions/SKILL.md

per-repo-conventions

Skill17 starsChanged 3 months agoMITView on GitHub

Use when starting work in any repository, and again at each work-phase transition (design, coding, debugging, verification, opening a PR). Loads the canonical per-repo-conventions guidance from foundation:docs/PER_REPO_CONVENTIONS.md — the discovery pattern for AGENTS.md, PR templates, CONTRIBUTING.md, and contextual files (VISION.md, PRINCIPLES.md, SMOKE_TESTS.md, KNOWN_ISSUES.md), plus the re-read cadence, the verification gradient, the steering pattern for repos with a governing contract, and the pre-publication leak defense for repos that publish publicly.

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
  1. Distinctive:

    Before writing code, debugging, verifying, or opening a PR in any repository, discover and honor that repo's local conventions.

    line 16

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Per-Repo Conventions

Before writing code, debugging, verifying, or opening a PR in any repository, discover and honor that repo's local conventions. You are a guest — read the house rules before changing the furniture.

Read foundation:docs/PER_REPO_CONVENTIONS.md and follow it. Re-read the relevant parts at each major shift in what you are doing (design → implementation, investigation → fix, coding → verification → PR): earlier reads fall out of context, and each file reads differently through the lens of the current objective.

That document is the single source of truth. It covers discovery order (repo root + subdirectory walk, most-specific-wins), the always-loaded files (AGENTS.md, .github/PULL_REQUEST_TEMPLATE.md, CONTRIBUTING.md, README.md), the contextual files (VISION.md, PRINCIPLES.md, SMOKE_TESTS.md, KNOWN_ISSUES.md), when to read and re-read them, the verification gradient, how a repo with a governing contract steers against it, how a repo that publishes publicly defends against leaks before the push, and author guidance.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.