agentleFS
Sign inStart free
buddy-compilerbuddy-compiler/buddy-mlir/.agents/skills/upstream-pr/SKILL.md

upstream-pr

Skill773 starsChanged 34 days agoApache-2.0View on GitHub

Prepare a Buddy-MLIR commit and pull request - scope, tests, docs, formatting, commit message, PR description with measurements - and handle review feedback. Use when committing, opening or updating a PR, or answering a reviewer.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. CIVITAS-John/vox-deorum★ 107same name
    2. Samin12/skills★ 8same 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 repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No unrelated refactoring, renames or reformatting.

    line 14
  2. Very specific:

    Update the docs the change touches (docs/*.md), including numbers that the change makes stale.

    line 24
  3. Very specific:

    Do not commit the llvm submodule pointer, build directories, local scripts, secrets or machine-specific paths.

    line 26
  4. Distinctive:

    Verify each point against the code.

    line 57
  5. Distinctive:

    When a fix could change performance (e.g.

    line 62

≈ “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

Upstream PR

Scope

  • One mechanism per PR. A PR that needs another unmerged PR waits for it, or says so at the top of its description.
  • Base the branch on the latest main; rebase when main moves and drop commits that were merged (squash merges rewrite them).
  • No unrelated refactoring, renames or reformatting.

Before committing

  1. Build and run the tests: ninja -C build check-buddy, plus the tests of the touched area (e.g. tests/Python/test_k3_w4_*.py, tests/Runtime/...). Add or extend a test for new behavior; a test of a contract must fail without the change (check it).
  2. Formatting on the changed files only: pre-commit run --files <changed files>.
  3. Update the docs the change touches (docs/*.md), including numbers that the change makes stale.
  4. Do not commit the llvm submodule pointer, build directories, local scripts, secrets or machine-specific paths. Stage files explicitly.

Commit message

[area] Imperative summary of the change

What was wrong or slow and why (the mechanism, with the evidence).
What the change does. Whether results are bit-identical or change, and
how that was checked. Measured effect.

Areas used in the history: [tools], [runtime], [frontend], [midend], [models], [docs], combinations like [frontend][runtime].

PR description

Follow .github/PULL_REQUEST_TEMPLATE.md:

  • Summary: the problem, the cause, the change (a table of files / changes for multi-part PRs), alternatives considered and why not.
  • Results: baseline vs PR (and the reference framework if relevant) per input size, how measured (board, command, runs), whether the output is identical.
  • Validation: tests run and their counts, accuracy checks for numerics changes.
  • Checklist from the template, ticked honestly.

Review feedback

  • Verify each point against the code; fix what is right, explain with evidence what is not.
  • Push fixes as new commits on the PR branch (do not force-push away the history the reviewer saw unless asked), re-run the tests, and summarize what changed in reply.
  • When a fix could change performance (e.g. alignment), measure it again.

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.

Check your setup, free