get-pr-comments

Fetch and summarize review comments from the active pull request

Quality

45%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./cursor-team-kit/skills/get-pr-comments/SKILL.md

Quality

Discovery

32%

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 identifies a clear domain (pull request review comments) with two specific actions, but it lacks a 'Use when...' clause, misses common trigger term variations like 'PR' or 'code review', and doesn't fully distinguish itself from other PR-related skills. Adding explicit trigger guidance and broader keyword coverage would significantly improve skill selection accuracy.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to review PR comments, check feedback on a pull request, or summarize code review discussions.'

Include common keyword variations users would naturally say, such as 'PR', 'code review', 'reviewer feedback', 'GitHub comments', or 'PR feedback'.

Expand the list of concrete actions beyond 'fetch and summarize' to clarify scope, e.g., 'Fetches, summarizes, and categorizes review comments from the active pull request, highlighting unresolved threads and action items.'

Dimension	Reasoning	Score
Specificity	Names the domain (pull request review comments) and two actions (fetch and summarize), but doesn't list additional concrete capabilities beyond those two.	2 / 3
Completeness	Describes what the skill does (fetch and summarize review comments) but completely lacks a 'Use when...' clause or any explicit trigger guidance, which per the rubric caps completeness at 2, and since the 'when' is entirely missing, it scores 1.	1 / 3
Trigger Term Quality	Includes relevant terms like 'pull request' and 'review comments', but misses common variations users might say such as 'PR', 'code review', 'feedback', 'PR comments', or 'GitHub review'.	2 / 3
Distinctiveness Conflict Risk	Fairly specific to pull request review comments which narrows the domain, but 'active pull request' is somewhat ambiguous and could overlap with other PR-related skills (e.g., PR creation, PR status checking).	2 / 3
	Total	7 / 12 Passed

Implementation

57%

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

The skill is well-structured and concise but critically lacks actionability. It reads more like a high-level task description than an executable skill—there are no concrete commands, tool invocations, API calls, or code examples that would enable Claude to actually perform the task. The workflow steps are too abstract to be directly followed.

Suggestions

Add concrete tool usage or API calls for each workflow step (e.g., `gh pr view`, `gh api` commands, or specific MCP tool invocations to fetch PR comments).

Include an example of the expected output format (e.g., a sample grouped feedback summary with severity labels and action items).

Specify how to 'resolve the active PR for the current branch'—provide the exact command or tool call (e.g., `gh pr view --json number` or equivalent).

Dimension	Reasoning	Score
Conciseness	The content is lean and avoids explaining concepts Claude already knows. Every line serves a purpose and there's no unnecessary padding or explanation of what PRs or review comments are.	3 / 3
Actionability	The skill provides only vague, abstract steps ('Resolve the active PR', 'Fetch review comments') with no concrete commands, API calls, tool usage, or executable examples. It describes what to do but never shows how.	1 / 3
Workflow Clarity	Steps are listed in a logical sequence, but there are no validation checkpoints, no error handling guidance, and no specifics on how to resolve the PR or fetch comments (e.g., which tool or API to use). Missing feedback loops for potential failures like no active PR or API errors.	2 / 3
Progressive Disclosure	For a simple, short skill with no bundle files and under 50 lines, the content is well-organized into clear sections (Trigger, Workflow, Output) with no need for external references.	3 / 3
	Total	9 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: cursor/plugins
Commit: b8f2564

Reviewed: 3 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.