CtrlK
BlogDocsLog inGet started
Tessl Logo

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

40

Quality

40%

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/skills/requesting-code-review/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 is a functional skill that provides a clear workflow for requesting code reviews via a subagent, with a useful concrete example and good feedback triage guidance. Its main weaknesses are redundancy between sections (When to Request vs Integration with Workflows), some unnecessary advice in the Red Flags section that Claude would already know, and a missing bundle file for the referenced template.

Suggestions

Merge 'Integration with Workflows' into 'When to Request Review' to eliminate redundancy and reduce token count

Remove or significantly trim the 'Red Flags' section—most of it is obvious advice that doesn't add value for Claude

Include the referenced code-reviewer.md template in the bundle, or inline the essential template structure so the skill is self-contained

Remove the redundant 'When to Use' section at the bottom which adds no information beyond the description

DimensionReasoningScore

Conciseness

The skill is mostly efficient but includes some unnecessary sections like 'Red Flags' with obvious advice ('Never skip review because it's simple'), the redundant 'When to Use' section at the end, and the 'Integration with Workflows' section which largely restates the 'When to Request Review' section. The example is useful but somewhat verbose.

3 / 5

Actionability

Provides concrete bash commands for getting SHAs, clear placeholder names for the template, and a detailed example showing the full workflow. However, the actual dispatch mechanism ('Use Task tool with superpowers:code-reviewer type') is somewhat vague—it doesn't show the exact invocation syntax, and the template reference is to a file not included in the bundle.

4 / 5

Workflow Clarity

The three-step process (get SHAs → dispatch subagent → act on feedback) is clearly sequenced with a good triage system for feedback (Critical/Important/Minor). The example reinforces the workflow well. However, there's no explicit validation checkpoint—e.g., verifying the SHAs are correct before dispatching, or confirming fixes resolved the issues before proceeding.

4 / 5

Progressive Disclosure

References a template at 'requesting-code-review/code-reviewer.md' which is appropriate for progressive disclosure, but no bundle files are provided so we can't verify it exists. The skill itself contains content that could be better organized—the 'Integration with Workflows' section overlaps with 'When to Request Review', and the inline example is lengthy. The reference to the template is mentioned twice (once in step 2, once at the bottom) without consistent formatting.

3 / 5

Total

14

/

20

Passed

Description

16%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.

This description is critically weak because it only provides vague 'when' guidance without ever explaining what the skill does. The trigger terms are overly generic ('completing tasks', 'implementing major features') and would cause frequent false matches against many other skills. It needs a complete rewrite with concrete actions and specific trigger terms.

Suggestions

Add a clear 'what' clause describing the concrete actions this skill performs (e.g., 'Runs a verification checklist to validate code quality, test coverage, and requirement compliance').

Replace generic phrases like 'completing tasks' and 'implementing major features' with specific trigger terms users would naturally say (e.g., 'pre-merge check', 'verify requirements', 'acceptance criteria', 'definition of done').

Add domain-specific keywords and synonyms to reduce conflict risk with other skills (e.g., 'checklist', 'validation', 'QA review', 'pull request readiness').

DimensionReasoningScore

Specificity

The description contains no concrete actions whatsoever. It uses entirely vague language like 'completing tasks' and 'implementing major features' without specifying what the skill actually does.

1 / 5

Completeness

The description only provides a 'when' clause with no 'what' — it never explains what the skill actually does. The 'when' guidance itself is vague ('completing tasks' could apply to almost anything).

2 / 5

Trigger Term Quality

Terms like 'merging', 'verify', and 'requirements' are somewhat relevant but extremely generic. Missing natural user phrases and specific keywords that would distinguish this skill (e.g., 'checklist', 'code review', 'validation', 'QA').

2 / 5

Distinctiveness Conflict Risk

'Completing tasks' and 'implementing major features' are so generic they would conflict with virtually any skill. There is nothing to distinguish this from testing, code review, deployment, or any other verification-related skill.

1 / 5

Total

6

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.