agentleFS
Sign inStart free
adeerkhanadeerkhan/vitruvius/skills/audit/SKILL.md

audit

Skill10 starsChanged 4 days agoMITView on GitHub

Audit a claim, specification, or documented result against its implementation or source — paper-vs-code, spec-vs-design, datasheet-vs-application, standard-vs-as-built. Use when the user asks to audit, check consistency, find mismatches, or confirm that what was claimed matches what was actually done. Flags omissions, mismatches, ambiguous defaults, and reproduction risks. The code, spec, or diff may be pasted inline: an inline pasted artifact is still an audit request.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use delight, teach-impeccable and 10 more.

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.
  • HK-hubSkill

    delight

    Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. Use when the user asks to add polish, personality, animations, micro-interactions, delight, or make an interface feel fun or memorable.

    Also in 32 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 19 projects that use this

  • zwy123zwySkill

    normalize

    将用户随意输入的提示词规范化为结构清晰、便于大模型执行的标准化提示词。适用于需要整理、统一提示词格式时调用。

    Also in 19 projects that use this

  • SkillPilotCHSkill

    level-up

    Eine Automatisierung pro Woche finden, scopen, shippen. Output landet als proposed-Eintrag in cadence.md mit konkreten Implementations-Schritten.

    Also in 12 projects that use this

  • ww-w-aiSkill

    pm-discovery

    PM Agent Team - Automated product discovery, strategy, and PRD generation. Runs PM analysis workflow to produce comprehensive PRD before PDCA Plan phase.

    Also in 3 projects that use this

  • +7 more from HK-hub

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before searching, name the question, the artifact/scope (or say it is a literature review), the jurisdiction/edition, and the effort budget …

    line 28
  2. Distinctive:

    Never conclude "consistent" from a skim.

    line 57

“Common” is measured: kept by at least 6 in 10 of the 175 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
<!-- VITRUVIUS-COMPILED-SKILL:BEGIN v1 sha256=fcecb76083d67587a67bbb56a5b83a8529fa16e3e97d20fc41723f2b420465ed -->

Engineering Audit

Audit a claimed/specified behavior against its actual implementation or source. This reuses the engineering-research discipline, focused on consistency between two things.

Input Gate

Before searching, name the question, the artifact/scope (or say it is a literature review), the jurisdiction/edition, and the effort budget (user-set or thorough). Ask ONE clarifying question if the ask is too vague, then proceed. See references/input-gate.md.

Workflow

  1. Outline the audit — what is being compared (paper vs code, spec vs design, standard vs as-built, datasheet vs application), which claims to check, and the governing references. Write the plan to outputs/.plans/<slug>.md; briefly summarize and continue.
  2. Read both sides directly — the claim AND the implementation/source. For code: read the actual code, not the README. For a standard: read the actual provision. Record versions/editions/commits.
  3. Compare claim-by-claim — for each checked item record:
    • the claim (with its source location)
    • the actual behavior (with its location)
    • match / mismatch / missing / ambiguous Confirm each mismatch against the implementation itself before reporting it: a claim-level disagreement the code resolves is not a finding.
  4. Call out — missing code or provisions, mismatched defaults, ambiguous parameters, claims that outrun the evidence, and reproduction risks. When a baseline exists, label a mismatch already present in it as pre-existing, not introduced by the change under audit. Zero mismatches is a valid report: state what was checked and found consistent — never invent a blocker to look thorough.
  5. Save one audit report to outputs/<slug>-audit.md, ending with a Sources section (paper + repo URL, spec + section, standard + edition).

Never conclude "consistent" from a skim. Every claim in the audit's verdict must name the exact provision, line, or commit it was checked against.

Scope and Boundaries

  • This skill produces research — it does NOT produce final designs or construction documents.
  • Research-only, not for final engineering sign-off. Licensed engineers must review and approve any design based on this research.

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.

Check your setup, free