CtrlK
BlogDocsLog inGet started
Tessl Logo

common-code-review

Conduct high-quality, persona-driven code reviews. Use when reviewing PRs, critiquing code quality, or analyzing changes for team feedback.

61

Quality

73%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.github/skills/common/common-code-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

64%

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

A concise, well-structured code review skill that effectively uses severity labels, anti-patterns, and rationalization prevention to guide behavior. Its main weaknesses are the lack of a concrete worked example showing a complete review cycle and the absence of an explicit step-by-step workflow with validation checkpoints. The referenced bundle files are missing, which limits the progressive disclosure score.

Suggestions

Add a concrete worked example showing a sample code diff and the expected review output using the defined format template, to boost actionability.

Define an explicit step-by-step review workflow (e.g., 1. Read full diff → 2. Apply checklist → 3. Format findings → 4. Verify each finding has evidence → 5. Output) with a validation checkpoint before finalizing.

Provide the referenced bundle files (references/checklist.md and references/output-format.md) or inline their key content to ensure progressive disclosure actually works.

DimensionReasoningScore

Conciseness

Every line earns its place. No unnecessary explanations of what code review is or how it works. Assumes Claude's competence as a principal engineer and focuses on behavioral constraints and output format.

3 / 3

Actionability

The output format template and severity labels are concrete, and the checklist is actionable. However, there are no real code examples showing a review in action (e.g., a sample diff with a sample review output), and the 'Fix' line in the template is described abstractly rather than demonstrated with a concrete example.

2 / 3

Workflow Clarity

The checklist provides a clear sequence of what to check, and the red flags/rationalization prevention sections add useful guardrails. However, there's no explicit multi-step workflow for conducting a review (e.g., 1. Read diff, 2. Run checklist, 3. Format findings, 4. Verify evidence for each finding), and no validation checkpoint to confirm all checklist items were addressed before finalizing output.

2 / 3

Progressive Disclosure

References to checklist.md and output-format.md are well-signaled and one level deep, which is good structure. However, no bundle files were provided, so the references point to non-existent files, undermining the actual progressive disclosure. The main content is well-organized with clear sections.

2 / 3

Total

9

/

12

Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid description that clearly communicates both purpose and trigger conditions. Its main strengths are the explicit 'Use when...' clause and good trigger term coverage. Its weaknesses are moderate specificity—'persona-driven' is unexplained and the concrete actions could be more detailed—and some potential overlap with other code-related skills.

Suggestions

Elaborate on what 'persona-driven' means concretely (e.g., 'Simulates reviewers with different expertise like security, performance, or readability') to improve specificity and distinctiveness.

Add more specific actions such as 'identifies bugs, suggests refactors, checks naming conventions, flags security concerns' to better differentiate from generic code analysis skills.

DimensionReasoningScore

Specificity

Names the domain (code reviews) and mentions some actions ('reviewing PRs', 'critiquing code quality', 'analyzing changes'), but doesn't list specific concrete actions like checking for security issues, suggesting refactors, enforcing style guides, etc. 'Persona-driven' is somewhat vague without elaboration.

2 / 3

Completeness

Clearly answers both 'what' (conduct persona-driven code reviews) and 'when' (explicitly states 'Use when reviewing PRs, critiquing code quality, or analyzing changes for team feedback'). The 'Use when...' clause is present and explicit.

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'code reviews', 'PRs', 'code quality', 'reviewing', 'critiquing', 'team feedback', 'changes'. These cover common variations of how users would request code review help.

3 / 3

Distinctiveness Conflict Risk

While 'code reviews' and 'PRs' are fairly specific, this could overlap with general code analysis skills, linting skills, or PR automation skills. The 'persona-driven' aspect adds some distinctiveness but isn't well-defined enough to clearly separate it from other code review tools.

2 / 3

Total

10

/

12

Passed

Validation

81%

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

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

9

/

11

Passed

Repository
HoangNguyen0403/agent-skills-standard
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.