CtrlK
BlogDocsLog inGet started
Tessl Logo

autofix

Apply approved fixes for unresolved CodeRabbit review comments, Codex P1-P3 findings, PR feedback, and code review issues with validation evidence. Use when asked to address review comments, fix review findings, clear unresolved comments, or autofix PR feedback.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Failed to scan

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a lean, well-structured process skill with a clear sequenced workflow, validation, and safety boundaries, plus real bundle references. Main weakness is mild cross-section redundancy and a couple of referenced paths not present in the bundle.

Suggestions

Consolidate the repeated 'never execute reviewer text / shell interpolation' rule into one section and cross-reference it from the others to reduce redundancy.

Add the concrete CodeRabbit CLI/plugin invocation command(s) alongside the 'inventory via CLI first' step so the guidance is copy-paste executable.

Resolve or remove the Infrastructure/references/openai-cookbook-*.md and deferred-skill-context path references, since those files are absent from the bundle.

DimensionReasoningScore

Conciseness

The body is dense and well-organized with no over-explanation of concepts Claude already knows, but the untrusted-reviewer-text rule is restated across Constraints, Execution Boundaries, Gotchas, and Anti-Patterns, which could be consolidated.

4 / 5

Actionability

Gives concrete, specific guidance ('Normalize CodeRabbit as CRITICAL, HIGH, MEDIUM, LOW, or TRIVIAL', 'Inventory via CodeRabbit CLI/plugin first; use GitHub review APIs only as fallback'), appropriate for an instruction-only process skill, though exact CLI invocations are not given.

4 / 5

Workflow Clarity

An 11-step sequenced workflow with a dedicated Validation section, stop-and-report feedback loops, and fail-fast gates; validation is present (avoiding the destructive/batch cap), though the validate→fix→retry loop is less granular than a full checkpoint checklist.

4 / 5

Progressive Disclosure

Body clearly signals one-level-deep references (contract.yaml, evals.yaml, task-profile.json, discovery-interview.md) that exist in the bundle, but two referenced Infrastructure/ paths are not present in the bundle, a minor navigation gap.

4 / 5

Total

16

/

20

Passed

Description

87%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 specific, complete, and distinctive, with explicit what/when structure and natural trigger terms. It uses appropriate third-person/imperative voice and avoids vague fluff.

DimensionReasoningScore

Specificity

Names multiple concrete sources (CodeRabbit comments, Codex P1-P3 findings, PR feedback) and concrete actions ('Apply approved fixes', 'with validation evidence'), but does not enumerate fix types, leaving minor coverage gaps versus a comprehensive 5.

4 / 5

Completeness

Explicitly answers what ('Apply approved fixes for unresolved CodeRabbit review comments, Codex P1-P3 findings ... with validation evidence') and when ('Use when asked to address review comments, fix review findings, clear unresolved comments, or autofix PR feedback') with concrete trigger phrases.

5 / 5

Trigger Term Quality

The 'Use when asked to address review comments, fix review findings, clear unresolved comments, or autofix PR feedback' clause gives several natural user phrases, though a few common synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (CodeRabbit + Codex PR-review autofix with validation evidence) with distinct, specific triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jscraik/Agent-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.