Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
73
58%
Does it follow best practices?
Impact
97%
1.34xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/receiving-code-review/SKILL.mdQuality
Discovery
40%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 has a clear 'when' clause which is a strength, but it fundamentally fails to describe what the skill actually does — it only describes a philosophy or approach (technical rigor over blind agreement). Without concrete actions, Claude cannot understand what capabilities this skill provides, making it difficult to select appropriately among competing skills.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Evaluates code review feedback for technical accuracy, formulates evidence-based responses, and identifies which suggestions to accept, modify, or push back on.'
Expand trigger terms to include common variations like 'PR review', 'pull request comments', 'reviewer suggestions', 'code review response', 'review feedback'.
Replace the negative framing ('not performative agreement or blind implementation') with positive capability statements that describe what the skill outputs or produces.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description does not list any concrete actions or capabilities. It describes a mindset ('technical rigor and verification') and anti-patterns ('not performative agreement or blind implementation') but never states what the skill actually does — no verbs like 'analyzes', 'verifies', 'evaluates', or 'responds'. | 1 / 3 |
Completeness | The 'when' is explicitly addressed ('Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable'). However, the 'what' is essentially absent — it says what not to do (blind implementation, performative agreement) but never states what the skill actually does. | 2 / 3 |
Trigger Term Quality | It includes some relevant natural keywords like 'code review feedback', 'implementing suggestions', and 'technically questionable', which a user or Claude might encounter. However, it misses common variations like 'PR review', 'pull request comments', 'reviewer suggestions', 'code comments', or 'review response'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on code review feedback response is a reasonably specific niche, but the lack of concrete actions makes it potentially overlap with general code review skills, code analysis skills, or communication/response skills. The domain is identifiable but the boundaries are fuzzy. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong behavioral skill that provides genuinely useful, actionable guidance for handling code review feedback with technical rigor. Its main strengths are the concrete decision trees, specific examples of good vs bad responses, and clear workflow sequencing. The primary weakness is some repetition across sections (forbidden responses appear in multiple places) and the document's length could benefit from splitting detailed examples into a separate reference file.
Suggestions
Consolidate the repeated 'forbidden response' examples—they appear in 'Forbidden Responses', 'Acknowledging Correct Feedback', and 'Real Examples' sections. Define them once and reference that section.
Consider extracting the 'Real Examples' and 'Common Mistakes' table into a separate EXAMPLES.md file, keeping SKILL.md as a leaner overview with a reference link.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and covers genuinely useful behavioral guidance Claude wouldn't inherently know (specific forbidden phrases, pushback protocols, YAGNI checks). However, there's some repetition—the 'forbidden responses' examples appear multiple times across sections (overview, acknowledging correct feedback, real examples), and the 'no thanks' section belabors the point. Some sections like 'Common Mistakes' repeat what was already covered. | 2 / 3 |
Actionability | The skill provides highly concrete, specific guidance with clear decision trees, exact phrases to use and avoid, grep commands for YAGNI checks, specific GitHub API endpoints for thread replies, and detailed examples showing good vs bad responses. The pseudocode-style decision flows are appropriate for a behavioral/process skill rather than a code skill. | 3 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced (READ → UNDERSTAND → VERIFY → EVALUATE → RESPOND → IMPLEMENT) with explicit validation checkpoints. The 'Handling Unclear Feedback' section provides a clear feedback loop (stop, clarify, then proceed). Implementation order is well-defined with priority tiers and individual testing requirements. The external reviewer checklist has explicit verification steps before action. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and logical section progression, but it's a fairly long monolithic document (~180 lines) with no references to external files. Some sections like the detailed examples and the common mistakes table could be split into a separate reference file. However, given no bundle files exist, the inline approach is acceptable though not optimal. | 2 / 3 |
Total | 10 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
f2cbfbe
Table of Contents
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.