joeholdcroft/code-review-feedback
Systematically handle GitHub PR review feedback: fetch comments, plan responses, make code changes, and reply to reviewers with explicit approval at each stage.
90
90%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 a strong skill description that clearly articulates specific capabilities around handling GitHub PR code review feedback, includes natural trigger terms users would actually use, and explicitly defines both what the skill does and when to use it. The description is concise, uses third person voice, and occupies a clear niche that minimizes conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Address code review comments', 'implement suggested changes', and 'respond to reviewer feedback on GitHub pull requests'. | 3 / 3 |
Completeness | Clearly answers both 'what' (address code review comments, implement suggested changes, respond to reviewer feedback) and 'when' with an explicit 'Use when...' clause listing four distinct trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'GitHub PR URL', 'PR feedback', 'code review comments', 'review feedback', 'pull request'. These cover common variations of how users would phrase requests. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to GitHub PR code review feedback specifically, which is a distinct niche. The triggers around PR URLs, review comments, and reviewer feedback are unlikely to conflict with general coding skills or other GitHub-related skills like PR creation. | 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 high-quality, highly actionable skill with an excellent multi-phase workflow that includes proper user approval gates and clear validation checkpoints. The executable commands and GraphQL queries are specific and ready to use. The main weakness is that the document is somewhat long and could benefit from splitting detailed reference material (GraphQL queries, categorization rules) into separate files for better progressive disclosure.
Suggestions
Consider extracting the GraphQL queries and detailed API commands into a separate reference file (e.g., GITHUB_API_REFERENCE.md) to keep the main skill leaner while preserving discoverability.
Trim the categorization guidance in Phase 3 — Claude can infer severity from context cues without explicit enumeration of all label patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content earns its place — the GraphQL queries, resolution rules, and phase structure are all necessary. However, some sections could be tightened (e.g., the explanation of review bodies as a 'distinct feedback source' and some of the categorization guidance that Claude could infer). Overall mostly efficient with minor verbosity. | 2 / 3 |
Actionability | Excellent actionability throughout. Every phase includes specific, executable `gh` CLI commands and GraphQL queries with exact field names and parameters. The reply/resolve commands are copy-paste ready with clear variable placeholders. Resolution rules are concrete and unambiguous. | 3 / 3 |
Workflow Clarity | The 8-phase workflow is clearly sequenced with explicit approval checkpoints at Phase 5 and Phase 7. There are strong validation gates ('Do NOT proceed until the user explicitly gives the go-ahead'), clear separation between code changes and GitHub actions, and error recovery steps. The feedback loop for plan iteration is well-defined. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headings and sub-sections, but it's a monolithic document (~200 lines) with no references to external files. The GraphQL queries and detailed categorization rules could be split into reference files, with the main skill providing a leaner overview. | 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.
Reviewed
Table of Contents