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.

55

Quality

63%

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 ./.github/skills/common/common-code-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%Weight 40%Scale 1-3

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-organized and instruction-only guidance is acceptable, but it is weakened by repeated principles, abstract actionability, a malformed code fence, and a missing explicit review workflow with validation checkpoints. Progressive disclosure is reasonable but leaves three reference files orphaned.

Suggestions

Collapse the overlapping Review Principles, Anti-Patterns, and Red Flags sections into a single concise block to remove repetition and improve token efficiency.

Replace abstract directives ('Find bugs', 'Findings First') with a concrete step-by-step review workflow ending in a validation checkpoint (e.g., 'confirm each finding cites file/test evidence before reporting').

Fix the malformed fenced code block in the Output Format section and link the orphaned reference files (lenses.md, report.md, request-template.md) or remove them.

DimensionReasoningScore

Conciseness

The body is mostly tight and assumes Claude's competence, but overlapping sections (Review Principles, Checklist, Anti-Patterns) repeat the same 'substance over style / findings first' message several times.

2 / 3

Actionability

The output-format block and severity tags give concrete templates, but most guidance is abstract ('Find bugs, flaws, design errors', 'Findings First') with few executable specifics; the inline code fence is malformed.

2 / 3

Workflow Clarity

Principles and a checklist are listed, but there is no ordered review workflow with validation checkpoints; destructive/batch-style claims ('Every substantive finding must include Why') are asserted without a verify step.

2 / 3

Progressive Disclosure

The body points to references/checklist.md and references/output-format.md (both present), but three bundle files (lenses.md, report.md, request-template.md) are unlinked, and the main checklist is duplicated inline rather than cleanly split.

2 / 3

Total

8

/

12

Passed

Description

77%Weight 40%Scale 1-3

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 concise, third-person, and clearly states both what the skill does and when to use it, with concrete actions. It is slightly weakened by generic trigger keywords ('review', 'analyze code') that risk overlap with adjacent skills and omit common variations like 'pull request' or 'diff'.

Suggestions

Add natural trigger variations such as 'pull request', 'code review', or 'diff' to broaden keyword coverage and reduce collision risk.

Tighten the 'when' clause to a more distinctive trigger (e.g., 'Use when reviewing pull requests or diffing changes for team feedback') to lower conflict risk with sibling analysis skills.

DimensionReasoningScore

Specificity

Lists concrete actions ('reviewing PRs, critiquing code quality, analyzing changes') and persona-driven framing rather than vague language like 'Helps with documents'.

3 / 3

Completeness

Clearly answers what ('conduct high-quality, persona-driven code reviews') and when ('Use when reviewing PRs, critiquing code quality, or analyzing changes for team feedback'). Both halves are explicit.

3 / 3

Trigger Term Quality

Keywords like 'review', 'pr', 'critique', 'analyze code' are relevant, but common natural variations ('code review', 'pull request', 'diff', 'team feedback') are missing.

2 / 3

Distinctiveness Conflict Risk

The code-review niche is clear, but generic triggers like 'review' and 'analyze code' could overlap with other analysis or review skills.

2 / 3

Total

10

/

12

Passed

Validation

87%

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

Validation14 / 16 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

14

/

16

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.