sahildmk/pr-comment-resolver
Review PR comments, address code issues in source files (not generated files), regenerate derived artifacts, run lint/format, commit, push, and reply to the comment thread confirming resolution.
92
90%
Does it follow best practices?
Impact
97%
1.21xAverage score across 5 eval scenarios
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 an excellent skill description that clearly articulates a specific multi-step workflow for resolving PR feedback. It uses third person voice, lists concrete actions, and provides comprehensive trigger terms covering various ways users might phrase their request. The distinction between source and generated files adds valuable specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: critically assessing feedback items, fixing source files (not generated files), regenerating derived artifacts, running lint/format, committing, pushing, and replying on GitHub threads. Very detailed workflow. | 3 / 3 |
Completeness | Clearly answers both 'what' (resolve PR feedback by assessing items, fixing source files, regenerating artifacts, running lint/format, committing, pushing, replying) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'PR feedback', 'reviewer suggestions', 'code review', 'GitHub review comments', 'PR issue comments', 'review summaries', 'resolve'. These are all terms users would naturally use when requesting this task. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining PR feedback resolution with a specific workflow (assess, fix source not generated files, regenerate, lint, commit, push, reply). The focus on GitHub PR review feedback with thread replies makes it clearly distinguishable from general git or code review skills. | 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, highly actionable skill with excellent workflow clarity and concrete executable commands throughout. Its main weakness is length — the filtering logic and error handling for replies add significant bulk that could be offloaded to supplementary files. The confirmation step with the user before making changes is a particularly good safety practice.
Suggestions
Extract the detailed feedback filtering logic (step 1's 'Filtering out already-handled feedback') into a separate reference file to reduce the main skill's token footprint.
Move the reply fallback/diagnostic procedure into a supplementary troubleshooting file, keeping only the primary happy-path commands inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and provides necessary detail for a complex multi-step workflow, but some sections could be tightened. For example, the filtering logic in step 1 is quite verbose, and the reply examples section, while useful, repeats patterns. The 'Important rules' section partially duplicates guidance already given in the workflow steps. | 2 / 3 |
Actionability | Excellent actionability throughout — provides specific gh API commands, exact endpoint paths, concrete bash examples for every step, copy-paste ready commit message format, and specific reply templates. The fallback logic for failed replies includes concrete diagnostic steps. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with explicit validation checkpoints (step 6: verify fix, run formatter/linter/tests), a confirmation gate with the user before making changes (step 3), and error recovery logic (retry/fallback for failed API calls). The feedback loop of assess → confirm → fix → verify → commit → reply is well-structured. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and logical sections, but it's a long monolithic file (~150+ lines of content) with no references to external files. The detailed API filtering logic and reply fallback procedures could be split into supplementary files to keep the main skill leaner. | 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