audit

a user-authored audit skill

Quality

25%

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

Fix and improve this skill with Tessl

tessl review fix ./tests/oracle/workspaces/ctx-pin/.claude/skills/audit/SKILL.md

Quality

Content

26%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 body consists of a single uninformative fragment ('Not pinned.') with no actionable guidance, no workflow, and no structure. It effectively documents nothing about how to perform the audit, making the skill unusable as written.

Suggestions

Replace 'Not pinned.' with concrete, executable guidance: the commands or steps Claude should run to perform an audit.

Add a sequenced workflow with explicit validation/checkpoint steps, especially if the audit involves batch or destructive operations.

Organize the body into clear sections (e.g. Quick start, What to check, Validation) so the overview is navigable, and pull large detail into reference files if needed.

Dimension	Reasoning	Score
Conciseness	The body 'Not pinned.' is maximally lean with no padding and no over-explanation of concepts Claude already knows, sitting just below 5 because the terseness is opaque rather than every token clearly earning its place.	4 / 5
Actionability	'Not pinned.' provides no concrete code, commands, or steps and only vaguely alludes rather than instructs, matching 'Entirely vague or abstract; no concrete code or commands; only describes rather than instructs'.	1 / 5
Workflow Clarity	There are no steps, no sequence, and no validation checkpoints of any kind, matching 'Steps missing or incoherent; no sequence; no validation for risky operations'.	1 / 5
Progressive Disclosure	The body has no section headers or organization and no bundle files exist to reference, matching 'Minimal structure'; it is not 3 because even basic sectioning is absent, though it avoids deep nested references.	2 / 5
	Total	8 / 20 Passed

Description

25%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 a near-empty label ('a user-authored audit skill') that names a domain but states no concrete capabilities, no trigger terms beyond 'audit', and no usage guidance. It would be hard for Claude to know when to invoke it or what it actually does.

Suggestions

List concrete actions the skill performs, e.g. 'Audits code for X, Y, and Z' instead of the bare label 'audit skill'.

Add an explicit 'Use when...' clause stating when Claude should invoke the skill, including natural user phrases and relevant file types or extensions.

Drop the non-functional metadata 'user-authored' from the description and replace it with distinguishing capability details to reduce overlap with other review/audit skills.

Dimension	Reasoning	Score
Specificity	The phrase 'audit skill' names a domain but provides no concrete actions (no verbs describing what the skill does), matching the anchor 'Names the domain but actions are minimal or generic'; it does not reach 3 because no specific actions are listed at all.	2 / 5
Completeness	'a user-authored audit skill' gives only a vague 'what' (an audit skill) and no 'when' clause, matching 'Has a vague what and no when'; the missing 'Use when...' guidance also caps completeness at 3, and it falls below that.	2 / 5
Trigger Term Quality	Only the single generic keyword 'audit' appears, with no natural trigger phrases a user would actually say, matching 'One or two generic keywords; missing the natural phrases users say'; not 3 because synonyms and common variations are absent.	2 / 5
Distinctiveness Conflict Risk	'audit' is a broad term that overlaps heavily with review, security-review, and other audit skills, matching 'Very broad; high overlap risk with many similar skills'; not 3 because no narrower trigger scope is given.	2 / 5
	Total	8 / 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: pbakaus/impeccable
Path: tests/oracle/workspaces/ctx-pin/.claude/skills/audit/SKILL.md
Commit: 0a4e72a

Reviewed: 3 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.