audit-architecture

Run an application-wide, read-only architecture audit that finds materially useful simplifications in a codebase's data structures, state representation, control flow, algorithms, and ownership boundaries. Fans out bounded read-only agents per subsystem, verifies every finding against the repo, and ranks results P0 to P3. Use when asked to audit architecture, review how state or data is modelled, find structural simplifications, or invoke /audit-architecture. Not a style or line-level quality pass (use /simplify for that) and not a bug hunt (use /code-review).

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, lean instruction body with a clear multi-step workflow, explicit validation, and feedback loops. It would benefit from a worked example of a finding output and is slightly long for a fully self-contained skill with no external references.

Suggestions

Add one short worked example of a worker finding (verdict, evidence with file:line, proposed representation) to lift actionability toward fully executable guidance.

Consider splitting the detailed worker brief (the 'Look for' list and 8-field template) into a references/ file referenced from the main body, improving progressive disclosure for a skill over 50 lines.

Trim redundant restatements of the read-only constraint (it appears in the intro, section 2, and the completion checklist) to tighten conciseness further.

Dimension	Reasoning	Score
Conciseness	The body is dense, all-instructional, and assumes Claude's competence — it never explains basic concepts and every line is actionable guidance, matching the lean level-5 anchor.	5 / 5
Actionability	As an instruction-only skill it gives highly concrete guidance — an exact 'Look for' list and an 8-field output template — but stops short of a worked example finding, placing it at the mostly-executable level-4 anchor rather than fully copy-paste ready level 5.	4 / 5
Workflow Clarity	Sections 1–4 plus a final output step form a clear sequence with explicit validation (verify every finding), feedback loops (audit-the-audit, reject/narrow/demote), and a completion checklist, matching the level-5 anchor; the read-only scope means the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	There are no bundle files and the single self-contained document is well organized into clearly headed sections with no nested references, but at ~100 lines it exceeds the under-50-line simple-skill exception that would allow a level-5 score, so it sits at the good-structure level-4 anchor.	4 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concretely states capabilities, gives explicit 'Use when' triggers, and actively disambiguates from sibling skills. Its only weakness is trigger-term breadth, where a few natural synonyms are absent.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — finding simplifications across data structures, state, control flow, algorithms and ownership, fanning out bounded agents, verifying findings, and ranking P0–P3 — which is comprehensive coverage, matching the score-5 anchor and clearly above the 1-2-action level 4.	5 / 5
Completeness	It explicitly answers both 'what' (a read-only architecture audit finding simplifications) and 'when' (a concrete 'Use when...' clause with multiple trigger phrases), matching the level-5 anchor.	5 / 5
Trigger Term Quality	Natural triggers like 'audit architecture', 'review how state or data is modelled', 'find structural simplifications', and '/audit-architecture' are present, giving good coverage, but a few common synonyms (e.g. 'refactor', 'design review') are missing so it falls just below the comprehensive level-5 anchor.	4 / 5
Distinctiveness Conflict Risk	Explicit disambiguation — 'Not a style or line-level quality pass (use /simplify...)' and 'not a bug hunt (use /code-review)' — gives it a clear niche with minimal conflict risk, matching the level-5 anchor.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: freekmurze/dotfiles
Path: config/claude/skills/audit-architecture/SKILL.md
Commit: 50345d3

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.