ce-resolve-pr-feedback

Resolve PR review feedback. Use when addressing review comments, resolving review threads, or fixing code-review feedback.

Quality

85%

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

70%Weight 40%Scale 1-3

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

A well-structured orchestration skill with clear workflow sequencing, validation checkpoints, and clean progressive disclosure to verified bundle files. It loses points on conciseness (verbose pipeline-mode elaboration) and actionability (executable detail lives in referenced scripts rather than inline).

Suggestions

Tighten the `mode:pipeline` paragraph: move the non-convergence / treadmill rationale into its referenced flow and keep only the three numbered specifics inline.

Reduce redundancy between the intro sentence and the "Judge centrally, fan out only the fixes" blockquote, which restates the same gating model.

Add a short inline example of invoking one bundled script (e.g. a `gh api graphql -f query=@scripts/get-pr-comments` snippet) so the actionability does not depend entirely on the referenced files.

Dimension	Reasoning	Score
Conciseness	The body is substantive and avoids explaining concepts Claude already knows, but the dense `mode:pipeline` paragraph (nested clauses and parentheticals) and the repeated "Judge centrally" blockquote could be tightened.	2 / 3
Actionability	Concrete commands and identifiers appear (`gh repo view`, `export GH_HOST`, specific script names, `repos/OWNER/REPO/pulls/comments/COMMENT_ID`), but the executable mechanics are largely delegated to referenced scripts rather than presented as inline copy-paste-ready steps.	2 / 3
Workflow Clarity	A clear sequence is given — the 9-step full-mode list (fetch → … → verify → summary), the 2-step targeted mode, and an explicit verify/validation checkpoint backed by success criteria.	3 / 3
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references (full-mode.md, targeted-mode.md, evaluation-rubric.md, agents/pr-comment-resolver.md) and scripts — all of which exist as real bundle files, with content appropriately split out.	3 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 concise, well-constructed description that states concrete capabilities and an explicit trigger in third person. It cleanly answers what the skill does and when to use it without fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Resolve PR review feedback", "addressing review comments", "resolving review threads", "fixing code-review feedback" — matching the anchor for listing several specific actions.	3 / 3
Completeness	Explicitly answers both what ("Resolve PR review feedback") and when via a "Use when..." trigger clause, satisfying the top anchor for completeness.	3 / 3
Trigger Term Quality	Uses natural terms a user would say — "PR review feedback", "review comments", "review threads", "code-review feedback" — giving good coverage rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The PR review-feedback resolution niche is distinct with specific triggers, making conflict with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: EveryInc/compound-engineering-plugin
Path: skills/ce-resolve-pr-feedback/SKILL.md
Commit: a9f6d53

Reviewed: 7 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.