CtrlK
BlogDocsLog inGet started
Tessl Logo

fix-review

Verify fix commits address audit findings without new bugs

47

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/fix-review/SKILL.md

The canonical home for this skill is fix-review in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

46%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 skill is well-structured and concise-ish for a simple review skill, but its guidance stays at the level of abstract directives with no concrete commands or methods, and two near-duplicate step lists blur the workflow. Tightening redundancy and adding executable verification steps would markedly improve it.

Suggestions

Replace abstract directives with concrete, runnable verification steps, e.g. 'git show <commit> --stat', 'git diff <finding-baseline>..<fix>', and 'run the project test suite before and after applying the fix'.

Merge the Instructions and Review Process sections into a single sequenced checklist with an explicit validation/feedback loop ('If a regression or unresolved sub-finding appears, report it and do not mark the finding resolved').

Cut the redundant restatements of purpose in the Overview, When-to-Use intro, and Instructions intro so each section adds new information.

DimensionReasoningScore

Conciseness

The body is short and avoids explaining concepts Claude already knows, but it is padded with redundant sections — the Overview, the When-to-Use intro, and the Instructions intro all restate the same purpose, and the Instructions and Review Process step lists overlap heavily.

3 / 5

Actionability

Guidance is high-level and abstract ('Compare the fix against the original audit finding', 'Verify the fix addresses the root cause') with no concrete commands, tooling, or executable method, matching 'minimal concrete guidance; high-level hints but missing the specific steps to execute'.

2 / 5

Workflow Clarity

A numbered sequence exists, but two overlapping step lists (Instructions vs Review Process) muddy the flow, and validation checkpoints ('Validate Completeness', 'Validate that tests cover the fixed scenario') are present yet implicit with no feedback loop for what to do when a regression is found.

3 / 5

Progressive Disclosure

No bundle files exist and the body is under 50 lines with clear section headers (Overview, When to Use, Instructions, Review Process, Best Practices, Resources), so it is well-organized; the redundant sections are a minor organization gap keeping it just below 5.

4 / 5

Total

12

/

20

Passed

Description

53%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 states a clear purpose and niche but omits an explicit 'Use when' trigger clause and offers only one composite action, leaving it mid-rubric on specificity, triggers, and completeness. Adding trigger phrases and 1-2 more concrete actions would lift it toward the top anchors.

Suggestions

Append a 'Use when reviewing commits that fix security audit findings, or when validating remediation of reported vulnerabilities.' clause to satisfy the explicit trigger requirement.

Add a second concrete action verb (e.g., 're-run regression tests', 'diff the fix against the reported finding') to broaden specificity beyond the single 'verify' action.

Include natural synonyms users say (e.g., 'patch', 'hotfix', 'remediation', 'regression') to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain ('fix commits', 'audit findings') and one concrete action ('Verify ... address audit findings without new bugs'), but lists only a single composite action rather than several specific ones, matching the '1-2 concrete actions, not comprehensive' anchor.

3 / 5

Completeness

It clearly answers 'what' (verify fix commits address findings without new bugs) but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords are present ('fix commits', 'audit findings', 'new bugs') but common synonyms and variations a user might actually say ('review the patch', 'check the remediation', 'hotfix') are missing, fitting 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

The audit-finding-fix-verification niche is mostly distinct with clear triggers, though it has minor overlap risk with general code-review skills, matching 'mostly distinct; minor overlap risk'.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.