agentleFS
dannys-code-cornerdannys-code-corner/incan/.agents/skills/review-rust-prose/SKILL.md

review-rust-prose

Skill73 starsChanged 6 days agoApache-2.0View on GitHub

Review touched Rust files for prose-comment quality, rustdoc accuracy, and manually chopped comment wrapping. Use when a broad review needs a dedicated Rust prose/rustdoc pass or when the user asks for comment-quality review specifically.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write a slice report at:

    line 28
  2. Very specific:

    Do not write to the canonical .agents/state/review-report.md.

    line 32
  3. Distinctive:

    Treat the accepted shape as:

    line 43
  4. Distinctive:

    Keep slice reports findings-first.

    line 50
  5. Very specific:

    Only include ## Reviewed Clean Surfaces when the clean call matters to the orchestrator, such as:

    line 76
  6. Distinctive:

    If there are no findings, say so explicitly.

    line 82

≈ “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

Review Rust Prose — Incan Compiler

Purpose

/review-rust-prose is a narrow report-only reviewer for touched .rs files that contain ///, //!, or prose //.

Own:

  • rustdoc paragraph shape
  • manually chopped comment wrapping
  • touched doc/comment accuracy against current behavior
  • public/non-trivial documentation coverage in touched Rust code

Do not own:

  • test style
  • docs-site markdown
  • architectural placement
  • final branch-clean judgment

Output artifact

Write a slice report at:

  • .agents/state/review-report.rust-prose.md

Do not write to the canonical .agents/state/review-report.md.

Workflow

  1. Review only the touched .rs files assigned by the orchestrator. If no slice was assigned, limit yourself to touched .rs files with prose comments.
  2. For each file, inspect touched prose blocks directly. Do not infer prose quality from broad code reading.
  3. Flag:
    • clause-by-clause or narrow-column manual wrapping
    • fake paragraph breaks
    • stale or misleading rustdoc
    • missing touched public/non-trivial docs that should exist
  4. Treat the accepted shape as:
    • natural paragraph prose, then make fmt wrapping
    • or multiple paragraphs separated for a real semantic break
  5. Record only Rust prose/documentation findings for this slice.

Slice report shape

Keep slice reports findings-first. Do not enumerate every clean file with a full checklist. Only record:

  • actual findings,
  • and, optionally, a short ## Reviewed Clean Surfaces section for risky or non-obvious clean calls.
# Review Slice Report

- role: rust-prose
- worker: <agent-id or stable label>
- status: in_progress | clean | blocked

## Scope
- assigned files:
  - src/foo.rs

## Findings

- [ ] warning | rustdoc prose | src/foo.rs:42
  Manually chopped single-paragraph rustdoc.

## Reviewed Clean Surfaces

- src/bar.rs — rust prose reviewed; no findings

Only include ## Reviewed Clean Surfaces when the clean call matters to the orchestrator, such as:

  • touched .rs files with prose comments,
  • files that are likely to be checked by another reviewer,
  • or surfaces involved in disagreement resolution.

If there are no findings, say so explicitly.

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.