agentleFS
speaches-aispeaches-ai/speaches/CLAUDE.md

speaches

CLAUDE.md3.7k starsChanged 7 months agoMITView on GitHub

Trending

Steady talk.about the whole repository

Dec 2025: 0 mentionsJan 2026: 3 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 1 mentionMay 2026: 2 mentionsJun 2026: 2 mentionsJul 2026: 0 mentionsAug 2026: 1 mentionSep 2026: 2 mentionsOct 2026: 0 mentionsNov 2026: 1 mention
Dec 2025Jun 2026Nov 2026
Mentions a month of the speaches-ai/speaches repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about speaches-ai/speaches

The biggest 5 of 27 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 27

Talked about on GitHub (27 times).

On GitHub · 27

22 more on GitHub

The file

Show its rules and text

We split this CLAUDE.md into the rules it gives an agent

14 rules. About 0 are common, 5 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always: use type hints for function/method parameters and return types.

    line 1
  2. Distinctive:

    Use latest type hinting format (Python 3.12).

    line 2
  3. Very specific:

    Use list[str] instead of List[str].

    line 3
  4. Very specific:

    Prefer using pathlib module over os.path for file and path manipulations.

    line 7
  5. Very specific:

    Prefer using pydantic.BaseModel over dataclasses.dataclass for data validation and serialization.

    line 8
  6. Very specific:

    Use logger.exception for logging exceptions with stack traces instead of logger.error(f"Error occured: {e}")

    line 9
  7. Very specific:

    Use logger.xxx() for logging instead of print()

    line 10
  8. Distinctive:

    Do not use emojis or any special characters in code comments or log messages.

    line 11
  9. Very specific:

    Use f-strings for string formatting instead of str.format() or concatenation.

    line 12
  10. Distinctive:

    Do not write docsctrings

    line 13
  11. Distinctive:

    Prefer defining functions over classes with methods when state is not needed.

    line 14
  12. Very specific:

    Use pydantic_settings.BaseSettings for configuration settings.

    line 15
  13. Very specific:

    Always run ruff format <modified files> and ruff check <modified files> (add --fix to ruff check to auto-fix some of the issues).

    line 16
  14. Very specific:

    Use semantic git commit messages (e.g., feat: add new feature, fix: correct a bug, docs: update documentation).

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md 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
CLAUDE.md
  • Always use type hints for function/method parameters and return types.
  • Use latest type hinting format (Python 3.12). For example:
    • Use list[str] instead of List[str].
    • Use dict[str, int] instead of Dict[str, int].
    • Use tuple[int, ...] instead of Tuple[int, ...].
    • Use set[str] instead of Set[str].
  • Prefer using pathlib module over os.path for file and path manipulations.
  • Prefer using pydantic.BaseModel over dataclasses.dataclass for data validation and serialization.
  • Use logger.exception for logging exceptions with stack traces instead of logger.error(f"Error occured: {e}")
  • Use logger.xxx() for logging instead of print()
  • Do not use emojis or any special characters in code comments or log messages.
  • Use f-strings for string formatting instead of str.format() or concatenation.
  • Do not write docsctrings
  • Prefer defining functions over classes with methods when state is not needed.
  • Use pydantic_settings.BaseSettings for configuration settings.
  • Always run ruff format <modified files> and ruff check <modified files> (add --fix to ruff check to auto-fix some of the issues).
  • Use semantic git commit messages (e.g., feat: add new feature, fix: correct a bug, docs: update documentation).

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.