agentleFS
idaibinidaibin/skills/skills/repo-audit/SKILL.md

repo-audit

Skill6 starsChanged 20 days agoApache-2.0View on GitHub

Audit existing frontend, Java, or Rust surfaces read-only. Use repo-review for change-based reviews.

24 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use handoff and code-review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 1

    Distinctive

    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. Very specific:

    Do not edit source, mutate Git, replace repo-review, or claim browser/client/runtime coverage without that evidence.

    line 35
  2. Distinctive:

    Read rule priority for every audit route.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “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

Repository Audit

Entry Gate

Audit declared existing path scope only. Require a language/profile and evidence basis; do not turn broad exploration into a change-basis review, source fix, or runtime claim.

Route Map

Request conditionReadResult
Any audit routerule priorityResolved evidence authority
Frontend baselinefrontend profile and frontend checklistSelected frontend concerns
Frontend architecture, state/data, or component ownership appliesarchitecture, state/data, and/or componentsConcern-specific findings
Frontend styling, CSS, layout, or design-system concern appliesstyling systems, style/layout, CSS, and/or layout governanceConcern-specific findings
Frontend framework, build, accessibility/performance, desktop, or anti-pattern concern appliesframework, build, accessibility/performance, desktop, and/or anti-patternsConcern-specific findings
Frontend selected-source, visual, or DESIGN authority appliesvisual evidence, DESIGN compliance, visual direction, and/or specification authoritiesQualified visual findings/gaps
Frontend protocol concern appliesfrontend protocol contractsQualified contract findings
Java baseline or engineering concern appliesJava profile, Java checklist, and Java engineeringSelected Java concerns
Java protocol concern appliesJava protocol contractsQualified contract findings
Rust baseline, architecture, ownership, API, async, or memory concern appliesRust profile, Rust checklist, baseline/lifecycle, architecture, ownership/resources, errors/API, async, and/or memorySelected Rust concerns
Rust unsafe/security, web/desktop, SQLite, performance, testing, or anti-pattern concern appliesunsafe/security, web/desktop, SQLite, performance, testing, and/or anti-patternsConcern-specific findings
Rust agent-runtime concern appliesagent runtimeRuntime-boundary findings/gaps
Cross-profile quality, OpenAPI, grounding, or design concern appliescodebase design, code quality, OpenAPI governance, and/or project groundingCross-boundary findings/gaps

Invariants

  • Audit only the declared profile/path scope; a miss or static signal is not absence/runtime proof.
  • Findings need owner, reachability, concrete impact, and falsifiable validation.
  • Do not edit source, mutate Git, replace repo-review, or claim browser/client/runtime coverage without that evidence.

Output Map

Return profile, scope/basis, findings, evidence, checks, exclusions, and Not verified gaps.

Calibrate severity by demonstrated impact and urgency: P0 is catastrophic, active or readily reachable, and immediately blocking; P1 is high-impact risk that should block delivery; P2 is a meaningful scoped defect; P3 is a minor actionable improvement. State reachability or impact uncertainty instead of treating an unverified worst case as established.

Reference Map

  • Read rule priority for every audit route.
  • Load only the concern-specific references in the selected Route Map row; do not load an entire language group by default.
  • Maintainers/calibration only: read eval cases, frontend scenarios, Java scenarios, Rust scenarios, frontend corpus, or Rust corpus; do not load them during ordinary runtime.

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.