get-pr-comments

Fetch and summarize review comments from the active pull request

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./cursor-team-kit/skills/get-pr-comments/SKILL.md

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 skill is admirably concise and well-structured for a simple task, but its workflow is abstract rather than executable and lacks any validation step for the external PR fetch. Providing concrete `gh` commands and a verification checkpoint would substantially improve actionability and workflow clarity.

Suggestions

Replace abstract steps with concrete commands, e.g. resolve the PR with `gh pr view --json number,url` and fetch comments with `gh api repos/{owner}/{repo}/pulls/{number}/comments`.

Add a validation checkpoint such as 'Confirm a PR was found for the current branch; if none, ask the user which PR to summarize.'

Define the grouping buckets explicitly (e.g., blocking / suggestions / nits / unresolved threads) so the grouping step is reproducible.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized with no concept-explaining fluff or padding; every section (Trigger, 4-step Workflow, Output) earns its place.	3 / 3
Actionability	Steps are named actions but lack concrete, executable commands (e.g., `gh pr view --json number`, `gh api repos/.../comments`), so guidance is incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	The four steps are clearly sequenced, but fetching external PR state and grouping comments has no validation checkpoint (e.g., confirm the PR resolved, handle no-comments), which caps clarity at 2.	2 / 3
Progressive Disclosure	A sub-50-line single-purpose skill with clean Trigger/Workflow/Output sections needs no external references; well-organized sections earn a 3 per the simple-skills note.	3 / 3
	Total	10 / 12 Passed

Description

57%

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 clear about what it does with a distinct niche, but it lacks an explicit 'when to use' trigger clause and broader natural term coverage (e.g., PR, code review). Adding a 'Use when...' clause and common synonyms would lift it across the board.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks for a summary of PR feedback, code review comments, or reviewer suggestions.'

Add common natural synonyms ("PR", "code review", "reviewers", "nits") so the description matches how users actually phrase the request.

Optionally mention a third concrete action (e.g., 'highlight unresolved threads') to strengthen specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain and two actions ("Fetch" and "summarize review comments from the active pull request"), matching the 'names domain and some actions' anchor; it is not vague, but only two verbs keeps it short of 'multiple specific concrete actions'.	2 / 3
Completeness	It states what the skill does but has no "Use when..." trigger clause; per the judging guidelines, a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	It uses natural terms like "review comments" and "pull request", but omits common variations a user might say ("PR", "code review", "reviewers", "nits"), so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	"review comments from the active pull request" carves a clear niche with distinct triggers unlikely to overlap with unrelated skills.	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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cursor/plugins
Path: cursor-team-kit/skills/get-pr-comments/SKILL.md
Commit: fe77e77

Reviewed: 2 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.