agentleFS
precise-alloyprecise-alloy/ritus/skills/code-conventions/SKILL.md

code-conventions

Skill1 starsChanged 4 months agoMITView on GitHub

Loaded automatically by execute-task and verify-task for any code change - covers comments, abstraction limits, dependency rules, and project-specific conventions from docs/CODE_CONVENTIONS.md. Do not invoke standalone unless the user specifically asks about coding conventions

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No helper extraction unless used in 3+ places.

    line 25
  2. Distinctive:

    No feature flags or backwards-compat shims - change the code directly.

    line 26
  3. Distinctive:

    No circular imports between modules.

    line 30
  4. Distinctive:

    Prefer explicit imports over wildcard/glob imports.

    line 31
  5. Very specific:

    Read docs/CODE_CONVENTIONS.md for this project's conventions: type system, naming, module structure, error handling, logging, and …

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Code Conventions

When to use

Auto-loaded by execute-task and verify-task for any code change. Validate against these conventions before reporting done. If the user asks about conventions directly, invoke this skill standalone.

Universal principles

Comments

Explain non-obvious constraints, invariants, or bug workarounds. For deliberate simplifications, state the known operating limit and an observable trigger for revisiting the design.

Abstraction limits

  • Three similar lines is better than a premature abstraction.
  • No helper extraction unless used in 3+ places.
  • No feature flags or backwards-compat shims - change the code directly.

Dependencies

  • No circular imports between modules.
  • Prefer explicit imports over wildcard/glob imports.

Project-specific conventions

Read docs/CODE_CONVENTIONS.md for this project's conventions: type system, naming, module structure, error handling, logging, and stack-specific rules. That file is filled by repo-scan and maintained by the team.

Project-specific rules in docs/CODE_CONVENTIONS.md override the universal principles above when they conflict.

Handoff

  • Report: the standard applied to the parent skill's work.

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.

Reviews can't be read right now.

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.