fix-review

Verify fix commits address audit findings without new bugs

Quality

33%

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 ./skills/fix-review/SKILL.md

Quality

Content

21%Scale 1-5

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

This skill is essentially a collection of generic review platitudes that Claude already knows. It provides no concrete techniques, no code examples, no specific patterns to look for, and no actionable methodology for reviewing fix commits against audit findings. The content could be replaced by a single sentence ('Review fix commits to verify they address audit findings without regressions') without losing any practical information.

Suggestions

Add concrete examples showing an audit finding, a fix commit diff, and the specific review analysis (e.g., 'Finding: SQL injection in user query → Fix: parameterized query → Verify: check all query construction paths use parameters')

Include specific, actionable checks such as grep patterns for common vulnerability classes, diff analysis techniques, or a checklist of concrete security anti-patterns to look for in fixes

Provide a structured output format for the review (e.g., a template with fields like 'Finding ID', 'Root cause addressed: yes/no', 'New issues introduced', 'Similar patterns found elsewhere')

Remove the redundant 'When to Use This Skill' and 'Instructions' sections that repeat the overview, and replace with substantive technical content

Dimension	Reasoning	Score
Conciseness	The content is noticeably verbose with redundant sections. The 'When to Use This Skill' section repeats the overview, and the instructions are generic platitudes Claude already knows (e.g., 'check for regressions', 'review fixes in context'). The 'Overview' and 'When to Use' and 'Instructions' sections all say essentially the same thing in different words.	2 / 5
Actionability	The skill provides entirely vague, abstract guidance with no concrete code, commands, examples, or specific techniques. Every instruction is a high-level platitude like 'verify the fix addresses the root cause' without showing how to actually do that—no diff analysis patterns, no specific checks, no example audit finding with corresponding fix review.	1 / 5
Workflow Clarity	There is a rough sequence present (review, verify, check, validate) but steps are poorly defined with no specifics on what constitutes proper verification. No validation checkpoints, no concrete criteria for pass/fail, and no feedback loops for when a fix is found to be incomplete.	2 / 5
Progressive Disclosure	The content is structured with headers and sections, and there's a link to the source repository. However, there are no bundle files and no references to detailed supporting documents. The content is short enough that it doesn't need splitting, but it also doesn't provide any depth to disclose progressively.	3 / 5
	Total	8 / 20 Passed

Description

45%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 identifies a specific niche (verifying fix commits against audit findings) but is too terse to be highly effective for skill selection. It lacks a 'Use when...' clause, synonyms/variations of key terms, and detail about what the verification entails.

Suggestions

Add a 'Use when...' clause with trigger phrases like 'when reviewing commits that fix audit findings, security vulnerabilities, or remediation patches'

Include more specific actions such as 'checks that fixes address the root cause, validates no regressions introduced, confirms audit item closure criteria are met'

Add natural keyword variations like 'security audit', 'remediation', 'patch review', 'vulnerability fix', 'audit remediation verification'

Dimension	Reasoning	Score
Specificity	Names the domain (fix commits, audit findings) and describes one concrete action (verify), but lacks detail on how verification is performed or what specific checks are done.	3 / 5
Completeness	Has a somewhat clear 'what' (verify fix commits address audit findings without new bugs) but completely lacks a 'when' clause or trigger guidance. Per rubric, missing 'Use when...' caps this at 3, and the 'what' is only moderately clear.	2 / 5
Trigger Term Quality	Contains relevant terms like 'fix commits', 'audit findings', and 'bugs', but misses natural user phrases like 'review fix', 'check patch', 'security audit', 'remediation', or 'vulnerability fix'.	3 / 5
Distinctiveness Conflict Risk	Fairly distinct niche combining audit findings verification with commit review, which is unlikely to overlap heavily with generic code review or testing skills, though some overlap with general code review skills is possible.	4 / 5
	Total	12 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/fix-review/SKILL.md
Commit: 57c135b

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.