issue-to-pr-resolver

Implement a GitHub issue end-to-end — create a worktree branch, implement the feature with tests, create a draft PR, then iteratively resolve all CI failures and review comments until the PR is clean. Use when you need to fully implement a GitHub issue from start to merge-ready. Triggers on "implement issue", "resolve issue", "/issue-to-pr-resolver <number>".

Quality

88%

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

81%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 well-structured, executable workflow document with strong sequencing, validation checkpoints, and a genuine feedback loop for CI and review resolution. Main gaps are placeholder-laden commands and an all-inlined structure that could benefit from separating the GraphQL/PR-resolution details into a reference file.

Suggestions

Move the GraphQL review-thread and resolve-thread mutation details (and the reply/resolve patterns) into a referenced file, leaving SKILL.md as a concise overview pointing to it.

Provide a concrete example of a populated PR title/body and a resolved-comment reply to reduce placeholder ambiguity for the actionability dimension.

Dimension	Reasoning	Score
Conciseness	The body is lean and does not explain concepts Claude already knows; the Philosophy and Rules sections earn their tokens. A few template placeholders and prose lines could be trimmed slightly, keeping it just below the fully efficient anchor.	4 / 5
Actionability	Provides concrete, executable gh/git/GraphQL commands throughout, but placeholders like "<descriptive title>", "<COMMENT_ID>", and "<PRRT_...>" keep it from being fully copy-paste ready, sitting between the mostly-executable and fully-executable anchors.	4 / 5
Workflow Clarity	A clearly sequenced five-phase workflow with explicit validation checkpoints ("gh pr checks --watch", "After pushing fixes, wait and re-check") and an explicit feedback loop ("Repeat until all checks green and no unresolved threads"), with a max-5-iteration safeguard.	5 / 5
Progressive Disclosure	Well-organized into clearly headed phases with a single one-level-deep signaled reference (AGENTS.md) and no nested references. All content is inline with no bundle files, which is appropriate here but leaves minor organization room versus the ideal overview-plus-references split.	4 / 5
	Total	17 / 20 Passed

Description

95%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 both capability and trigger conditions with natural user phrasing. The only issue is second-person voice ("you need to"), which costs one specificity point per the rubric.

Suggestions

Rephrase "Use when you need to fully implement" in third person (e.g., "Use when a GitHub issue must be fully implemented from start to merge-ready") to avoid the second-person voice penalty.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("create a worktree branch, implement the feature with tests, create a draft PR, then iteratively resolve all CI failures and review comments"), but the second-person phrasing "Use when you need to" triggers the voice penalty, capping it just below the comprehensive anchor.	4 / 5
Completeness	Explicitly answers what (the end-to-end action list) and when ("Use when you need to fully implement a GitHub issue from start to merge-ready") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural user phrases and synonyms ("implement issue", "resolve issue") plus the explicit slash-command trigger "/issue-to-pr-resolver <number>", giving comprehensive coverage including the command form.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (full issue-to-merge-ready PR implementation) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: homeassistant-ai/ha-mcp
Path: .claude/skills/issue-to-pr-resolver/SKILL.md
Commit: 47582a7

Reviewed: ~23 hours 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.