agentleFS
refpathrefpath/chatgpt-team/.agents/skills/stack-elixir/SKILL.md

stack-elixir

Skill0 starsChanged 2 months agoMITView on GitHub

Apply conservative Elixir engineering practices using the repository's own Mix configuration, formatter, tests, and static-analysis conventions.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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. Very specific:

    Use the repository as the source of truth.

    line 8
  2. Distinctive:

    Prefer explicit pattern matching and clear error contracts over broad rescue paths.

    line 13
  3. Distinctive:

    Treat process ownership, mailbox growth, timeouts, retries, and supervision behavior as correctness concerns when concurrency changes.

    line 14
  4. Distinctive:

    Do not assume Ecto, Phoenix, Oban, Broadway, or any other library is present.

    line 15
  5. Distinctive:

    Do not change dependency versions or application topology without task scope requiring it.

    line 16
  6. Distinctive:

    Read only the reference needed by the change:

    line 18
  7. Very specific:

    Use elixir-docs for changed public API documentation, examples, or ExDoc output.

    line 25
  8. Distinctive:

    Use the project's native commands.

    line 29
  9. Distinctive:

    Run broader tests when the change crosses application boundaries or repository instructions require them.

    line 37
  10. Distinctive:

    Do not claim a standard command was run if the repository uses a different alias/toolchain.

    line 39

≈ “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

Elixir

Use the repository as the source of truth. Inspect mix.exs, .formatter.exs, lockfiles, aliases, and applicable AGENTS.md before choosing commands.

Working rules

  • Preserve established OTP/application boundaries and supervision semantics.
  • Prefer explicit pattern matching and clear error contracts over broad rescue paths.
  • Treat process ownership, mailbox growth, timeouts, retries, and supervision behavior as correctness concerns when concurrency changes.
  • Do not assume Ecto, Phoenix, Oban, Broadway, or any other library is present.
  • Do not change dependency versions or application topology without task scope requiring it.

Read only the reference needed by the change:

  • OTP ownership and concurrency for process, supervision, task, timer, or message behavior;
  • ExUnit evidence for test design or flaky checks;
  • Ash/Ecto boundaries when those dependencies are present and affected;
  • Generated interfaces when generated clients, schemas, or frontend contracts change.

Use elixir-docs for changed public API documentation, examples, or ExDoc output. Documentation and typespecs must agree with the implementation; do not change the contract as a prose fix.

Validation

Use the project's native commands. Where the repository supports the standard Mix equivalents, useful checks often include:

mix format --check-formatted
mix compile --warnings-as-errors
mix test <relevant scope>

Run broader tests when the change crosses application boundaries or repository instructions require them.

Do not claim a standard command was run if the repository uses a different alias/toolchain.

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.