get-pr-comments

Fetch and summarize review comments from the active pull request

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is admirably concise and well-organized for a simple read-only skill, scoring top marks on token efficiency and structure. Its weakness is actionability and workflow clarity: the steps are abstract with no concrete commands or validation checkpoints to make the process executable and verifiable.

Suggestions

Add concrete commands to the workflow steps, e.g. `gh pr view --json number` to resolve the PR and `gh api repos/{owner}/{repo}/pulls/{n}/comments` to fetch comments.

Insert a validation checkpoint after resolving the PR (e.g. confirm the PR number/branch before fetching) to introduce a feedback loop.

Briefly specify how severity/actionability grouping is determined so the 'Group feedback' step is actionable rather than abstract.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean — three short sections with no padding, no explanation of concepts Claude already knows, and every line earning its place, matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	The workflow gives structured guidance ('Resolve the active PR', 'Fetch review comments and discussion comments', 'Group feedback by severity and actionability') but no concrete executable commands such as `gh pr view` or `gh api`, so it describes rather than fully instructs, fitting the 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	Steps are clearly numbered 1–4, but there are no validation checkpoints or feedback loops (e.g. confirming the resolved PR is correct before fetching), and the rubric's level-3 anchor requires explicit validation steps.	2 / 3
Progressive Disclosure	The skill is under 50 lines, needs no external references (none exist), and is organized into clearly labeled Trigger, Workflow, and Output sections, so per the rubric's simple-skills guidance progressive disclosure scores 3.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 is concise and clearly conveys what the skill does, but it omits any explicit 'when to use' trigger guidance and lacks common keyword variations, leaving it at level 2 across all dimensions. Adding a 'Use when...' clause and terms like 'PR' or 'code review' would raise completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a summary of PR/code review feedback or wants to triage comments on the active pull request.'

Include natural keyword variations such as 'PR', 'code review', and 'feedback' to improve trigger-term coverage.

Mention concrete sub-actions (e.g. group by severity, surface blockers) to lift specificity from 2 to 3.

Dimension	Reasoning	Score
Specificity	The description names the domain (PR review comments) and two concrete actions ('Fetch and summarize'), but it is not a comprehensive list of actions, matching the 'Names domain and some actions' anchor rather than the multi-action level-3 example.	2 / 3
Completeness	It clearly states what the skill does ('Fetch and summarize review comments from the active pull request') but provides no 'Use when...' trigger guidance, so per the rubric completeness is capped at 2.	2 / 3
Trigger Term Quality	'review comments' and 'pull request' are natural terms a user would say, but common variations like 'PR', 'code review', and 'feedback' are absent, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The PR-comment-summarization niche is fairly specific, but without explicit triggers it could overlap with broader PR-review skills, matching the 'somewhat specific but could still overlap' anchor rather than a clearly distinct level-3 niche.	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cursor/plugins
Commit: 0452e08

Reviewed: 14 days ago

Table of Contents

Discovery Implementation Validation

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.