Name: aims-audit
Rating: 68 (1 reviews)
Author: alirezarezvani

aims-audit

/cs:aims-audit <scope> — ISO/IEC 42001 AIMS internal-audit 6-question forcing interrogation. Use before certification stage 1, before annual internal audit cycles, or when onboarding a new AI system into an existing AIMS.

Quality

83%

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

The canonical home for this skill is aims-audit in alirezarezvani/claude-skills

Quality

Content

83%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.

The content is concise, action-dense, and well-structured with executable commands and concrete pass/fail criteria. Its main weakness is workflow clarity: the audit workflow lacks validation checkpoints and an explicit verdict-gating loop, which the destructive/batch-operation rule caps at 3.

Suggestions

Add explicit validation/gating checkpoints to the Workflow (e.g., 'If gap analysis shows critical gaps, close them before running the risk register'; 'Only emit STAGE-1-READY when zero critical gaps remain'), with a fix-and-retry loop.

Tie each workflow step back to its driving question so the sequence reads as a checked pipeline rather than a flat command list.

Consider splitting the six-question detail (or the cross-framework reuse map) into a one-level-deep reference file to lift progressive disclosure toward anchor 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and domain-dense: each question uses a one-line axiom plus 2-4 tight bullets with clause references, with no padding explaining what ISO 42001, an AIMS, or auditing basics are.	5 / 5
Actionability	Provides copy-paste-ready commands with arguments and input files (aims_gap_analyzer.py evidence.json, etc.), explicit pass/fail criteria per question, and a complete output template covering the common audit case.	5 / 5
Workflow Clarity	The Workflow section is a flat list of four commands with no validation checkpoints, error-recovery loop, or explicit gating between findings and the certification verdict; the destructive/batch-operation cap holds this at 3.	3 / 5
Progressive Disclosure	Well-structured with numbered questions and clear section headers, and inline references are clearly signaled and one level deep; held below 5 because the six-question block is monolithic and no local bundle/reference files split the detail.	4 / 5
	Total	17 / 20 Passed

Description

82%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.

The description is precise, complete, and distinct, cleanly answering both what and when with concrete trigger phrases. It is slightly held back on specificity by presenting one composite action rather than several enumerated capabilities.

Suggestions

Enumerate the concrete capabilities the skill performs (e.g., 'runs gap analysis, builds the AI risk register, schedules the Clause 9.2 audit, maps cross-framework reuse') to lift specificity toward anchor 4/5.

Add common-synonym triggers such as 'surveillance audit', 'recertification', or 'gap analysis' to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete domain (ISO/IEC 42001 AIMS internal-audit) and one composite action ('6-question forcing interrogation'), but does not list several distinct concrete actions as required by the anchor 4 example.	3 / 5
Completeness	Explicitly answers both what ('ISO/IEC 42001 AIMS internal-audit 6-question forcing interrogation') and when ('Use before certification stage 1, before annual internal audit cycles, or when onboarding a new AI system') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a practitioner would say ('certification stage 1', 'annual internal audit cycles', 'onboarding a new AI system'), though synonyms like surveillance/recertification/gap analysis are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (ISO 42001 AIMS internal-audit) with distinct, specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/aims-audit/SKILL.md
Commit: 19392f7

Reviewed: ~23 hours 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.