fusion-github-review-resolution

Resolves unresolved GitHub PR review threads end-to-end: evaluates whether each review comment is correct, applies a targeted fix when valid, replies with rationale when not, commits, and resolves the thread. USE FOR: unresolved review threads, PR review feedback, changes requested PRs, PR review URLs (#pullrequestreview-...), fix the review comments, close the open threads, address PR feedback. DO NOT USE FOR: summarizing feedback without code changes, creating new PRs, or read-only branches.

1.06x

Quality

—

Does it follow best practices?

Impact

93%

1.06x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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

A well-structured, actionable workflow document with strong sequencing, validation, and progressive disclosure via real bundle files. Its single weakness is mild verbosity in the trigger list and step-9 example duplication.

Suggestions

Trim the 'When to use' URL-pattern and explicit-request bullet lists, which duplicate triggers already covered by the frontmatter description; keep only the unique agent-detected/implicit triggers.

In step 9, collapse the three near-identical full-command examples into one parameterized form plus a short note on the differing flag (--include-outdated, --apply, --allow-additional-reply) rather than repeating the full owner/repo/pr/review-id prefix each time.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no explaining what a PR or review is), but the long 'When to use' trigger enumeration and the duplicated full-command examples in step 9 partly restate the description and could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready script invocations with concrete flags and values (e.g. '--owner equinor --repo fusion-skills --pr 27 --review-id 3837647674 --apply --message "..."') plus a tooling-map table naming specific MCP tools and .graphql files.	3 / 3
Workflow Clarity	Gives an explicit ordered phase sequence (fetch → analyze → fix → validate → push → reply → resolve → verify) with validation checkpoints, re-fetch-on-error feedback loops, a closure-verification step, and a checklist working document — appropriate for a batch mutation workflow.	3 / 3
Progressive Disclosure	The overview body points one level deep to real, existing bundle files (assets/review-resolution-checklist.md, scripts/.sh, assets/.graphql) and signals each via a tooling-map table, with no deeply nested references.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 third-person, concise yet comprehensive, and clearly specifies both capability and trigger conditions with strong natural-language phrasing. Its only minor weakness is length, but every clause earns its place and it avoids fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'evaluates whether each review comment is correct, applies a targeted fix when valid, replies with rationale when not, commits, and resolves the thread' — matching the comprehensive-action anchor.	3 / 3
Completeness	Explicitly answers what ('Resolves unresolved GitHub PR review threads end-to-end...') and when (a 'USE FOR' clause with explicit triggers plus a 'DO NOT USE FOR' exclusion list).	3 / 3
Trigger Term Quality	Includes natural phrasings a user would say — 'fix the review comments', 'close the open threads', 'address PR feedback', 'changes requested PRs', 'PR review URLs (#pullrequestreview-...)' — with good coverage.	3 / 3
Distinctiveness Conflict Risk	Occupies a narrow niche — unresolved PR review-thread resolution — with distinct triggers and explicit exclusions (no summarizing, no new PRs, no read-only branches), making misfires unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: equinor/fusion-framework
Commit: 54fb2a7

Reviewed: 4 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.