receiving-review
Enforces rigorous technical evaluation of code review feedback before implementation -- verifying suggestions against the codebase, pushing back when wrong, clarifying ambiguity, and avoiding performative agreement. Use when processing PR review comments, inline suggestions, change requests, reviewer feedback, or any list of code fixes to address. Applies to feedback from human partners and external reviewers alike. DO NOT TRIGGER when writing a review of someone else's code.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 an excellent skill description that clearly articulates a specific niche (critically evaluating received code review feedback), lists concrete actions, provides comprehensive trigger terms, and explicitly disambiguates from a closely related but distinct task (writing code reviews). The negative trigger clause is a particularly strong addition for avoiding conflicts.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'verifying suggestions against the codebase', 'pushing back when wrong', 'clarifying ambiguity', 'avoiding performative agreement'. These are clear, actionable behaviors. | 3 / 3 |
Completeness | Clearly answers both what (rigorous technical evaluation, verifying suggestions, pushing back, clarifying ambiguity) and when ('Use when processing PR review comments, inline suggestions, change requests, reviewer feedback, or any list of code fixes to address'). Explicit 'Use when...' clause is present. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'PR review comments', 'inline suggestions', 'change requests', 'reviewer feedback', 'code fixes'. Also includes a negative trigger ('DO NOT TRIGGER when writing a review') which helps disambiguation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — focuses specifically on *responding to* code review feedback with critical evaluation, not writing reviews or general code editing. The explicit 'DO NOT TRIGGER' clause for writing reviews of others' code further reduces conflict risk with a code-review-writing skill. | 3 / 3 |
Total | 12 / 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 with excellent actionability and workflow clarity — it provides concrete decision trees, specific examples of correct vs incorrect behavior, and clear sequencing for multi-item feedback processing. Its main weakness is moderate redundancy across sections (performative agreement is addressed in at least 3-4 places) and the document length could benefit from some consolidation or progressive disclosure to external files.
Suggestions
Consolidate the overlapping 'Forbidden Responses', 'Acknowledging Correct Feedback', and parts of 'Common Mistakes' into a single section to reduce redundancy and improve conciseness.
Consider extracting the 'Real Examples' section into a separate EXAMPLES.md file referenced from the main skill, keeping only one or two inline examples for quick reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but has some redundancy — the 'Forbidden Responses' and 'Acknowledging Correct Feedback' sections overlap significantly, and the 'Common Mistakes' table largely restates points already covered. The repeated emphasis on no gratitude/performative agreement across multiple sections could be consolidated. | 2 / 3 |
Actionability | The skill provides highly concrete, specific guidance with clear examples of good vs bad responses, exact pseudocode workflows, specific CLI commands (gh api), grep-based verification steps, and decision trees. The examples are copy-paste ready behavioral patterns rather than vague descriptions. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints: the main response pattern is numbered 1-6, implementation order has clear prioritization, the external reviewer checklist has 5 verification steps before acting, and there are explicit feedback loops (clarify → implement → test → verify no regressions). The 'stop and clarify before partial implementation' pattern is a strong validation checkpoint. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, but it's a fairly long monolithic document (~180 lines) with no references to external files for deeper content. Some sections like the detailed examples and the common mistakes table could be split out. However, for a behavioral/instruction skill (not code-heavy), the inline approach is more defensible. | 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.
- Repository
- shousper/claude-kit
- Commit
a01bac9
- 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.