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.
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- add-learningSkill
- bump-rfcSkill
- closeoutSkill
- create-github-issueSkill
- create-planSkill
- create-pr-descriptionSkill
- fixSkill
- flag-compiler-bugSkill
- fleet-auditSkill
- hello-worldSkill
- loopSkill
- orchestrate-parallel-workSkill
- ralph-loopSkill
- review-and-fixSkill
- review-architectureSkill
- review-code-smellsSkill
- review-docs-claimsSkill
- review-incan-source-qualitySkill
- review-orchestrateSkill
- review-rfcSkill
- review-scopeSkill
- reviewSkill
- review-test-styleSkill
- start-workSkill
- testSkill
- write-commit-messageSkill
- write-rfcSkill
- yeet-prSkill
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
- Distinctive: line 28
Write a slice report at:
- Very specific: line 32
Do not write to the canonical .agents/state/review-report.md.
- Distinctive: line 43
Treat the accepted shape as:
- Distinctive: line 50
Keep slice reports findings-first.
- Very specific: line 76
Only include ## Reviewed Clean Surfaces when the clean call matters to the orchestrator, such as:
- Distinctive: line 82
If there are no findings, say so explicitly.
≈ “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.
Files
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
- Review only the touched
.rsfiles assigned by the orchestrator. If no slice was assigned, limit yourself to touched.rsfiles with prose comments. - For each file, inspect touched prose blocks directly. Do not infer prose quality from broad code reading.
- 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
- Treat the accepted shape as:
- natural paragraph prose, then
make fmtwrapping - or multiple paragraphs separated for a real semantic break
- natural paragraph prose, then
- 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 Surfacessection 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 findingsOnly include ## Reviewed Clean Surfaces when the clean call matters to the orchestrator, such as:
- touched
.rsfiles 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.
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
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.

