respond-to-pr-comments-in-blocklist

Interactively walk a user through PR review comments one at a time, collect a per-comment decision, then post agent-authored replies on GitHub and resolve the review threads once the user approves a preview. Use only when the user wants to reply to or resolve review threads on GitHub. Skip when the user only wants comments fetched or displayed (use `pr-comments`), or only wants the code changes made without posting anything back to GitHub.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%Weight 40%Scale 1-5

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

A thorough, highly actionable workflow skill with executable GitHub CLI snippets and strong validation checkpoints. Its main weakness is mild redundancy and a monolithic structure that could split its long code blocks into bundled files.

Suggestions

Consolidate the repeated 'Other...' freeform-field requirement and the explanation-loop behavior into a single stated rule instead of restating them in each mode/walkthrough section.

Move the multi-line GraphQL thread-query and REST reply-posting shell scripts into a scripts/ file and reference them from SKILL.md to reduce the inline token footprint.

Trim the batch-mode paragraph; the one-line distinction ('code edits deferred, information gathering stays interactive') conveys the same intent as the current longer explanation.

Dimension	Reasoning	Score
Conciseness	Mostly efficient procedural guidance that assumes Claude's competence and avoids explaining known concepts, but the 'Other...' freeform requirement and the explanation-loop behavior are each restated across multiple sections and could be tightened.	4 / 5
Actionability	Provides copy-paste-ready, executable shell for REST reply posting (mktemp + python3 JSON payload + gh api --input), PR comments (gh pr comment --body-file), GraphQL thread querying/resolution, plus concrete decision-record fields and disposition enums.	5 / 5
Workflow Clarity	Clear end-to-end sequence (filter → mode select → walkthrough → decisions → apply → validate → commit/push → preview → post → summarize) with explicit validation checkpoints, a preview-edit re-approval feedback loop, and stop-on-failure guards for the batch/destructive GitHub-posting steps.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested references, but the 263-line body is entirely inline — the long GraphQL and REST shell blocks could live in a scripts/ file to keep the overview lean.	4 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states what the skill does and when to use it, with explicit boundary guidance against neighboring skills. Trigger-term coverage is strong though not exhaustively synonymous.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'walk a user through PR review comments one at a time', 'collect a per-comment decision', 'post agent-authored replies on GitHub', 'resolve the review threads' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (walk through comments, collect decisions, post replies, resolve threads) and when ('Use only when the user wants to reply to or resolve review threads on GitHub'), plus explicit skip guidance with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('reply to or resolve review threads on GitHub', 'PR review comments', 'comments fetched or displayed') with good synonym coverage, but a few natural variants like 'respond to PR comments' or 'close review threads' are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (posting replies/resolving GitHub review threads) and explicitly distinguishes itself from the `pr-comments` fetch/display skill and from pure code-change work, minimizing conflict risk.	5 / 5
	Total	19 / 20 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: warpdotdev/common-skills
Path: .agents/skills/respond-to-pr-comments-in-blocklist/SKILL.md
Commit: 69b4753

Reviewed: 5 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.