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.
93
Quality
89%
Does it follow best practices?
Impact
99%
1.19xAverage score across 5 eval scenarios
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 excels across all dimensions. It provides specific concrete actions in a logical workflow sequence, includes natural trigger terms users would actually say, explicitly states both what the skill does and when to use it, and carves out a distinct niche around PR review comment resolution that won't conflict with general git or coding skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'critically assessing each one, fixing source files (not generated files), regenerating derived artifacts, running lint/format, committing, pushing, and replying to comment threads.' | 3 / 3 |
Completeness | Clearly answers both what (resolve PR comments through assessment, fixing, regenerating, linting, committing, pushing, replying) AND when with explicit 'Use when...' clause listing four trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'PR feedback', 'reviewer suggestions', 'code review', 'GitHub review comments', 'pull request review comments'. Good coverage of variations. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on PR review comment resolution workflow. The combination of GitHub PR context, review comments, and the full workflow (fix, regenerate, lint, commit, push, reply) creates distinct triggers unlikely to conflict with general coding or git 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 well-crafted skill with excellent actionability and workflow clarity. The step-by-step process is thorough with proper validation checkpoints and user confirmation gates. Minor improvements could be made by tightening some explanatory text and potentially splitting detailed troubleshooting into a reference file.
Suggestions
Trim the filtering explanation in step 1 - the numbered list format is clear but the prose around it is verbose
Consider moving the API troubleshooting section (retry logic for /replies endpoint) to a separate TROUBLESHOOTING.md file and linking to it
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundant explanations (e.g., explaining what filtering means, restating concepts). The workflow is comprehensive but could be tightened in places like the lengthy filtering explanation. | 2 / 3 |
Actionability | Provides fully executable bash commands throughout, specific API endpoints, concrete commit message format, and exact reply examples. Every step has copy-paste ready commands with proper variable placeholders. | 3 / 3 |
Workflow Clarity | Excellent 8-step workflow with clear sequencing, explicit validation checkpoints (step 6), error recovery guidance for API failures, and a confirmation gate (step 3) before destructive changes. Includes feedback loop for retry logic. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections and headers, but it's a monolithic document with no references to external files. For a skill of this length (~150 lines), some content like the API troubleshooting could be split out. | 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.
Install with Tessl CLI
npx tessl i sahildmk/pr-comment-resolverReviewed
Table of Contents