clawhub-pr-maintainer

Use when reviewing, triaging, validating, or discussing ClawHub GitHub issues or pull requests, including author context, CI, UI proof, evidence, labels, close decisions, and maintainer handoff.

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 highly actionable, well-sequenced maintainer workflow with executable commands, explicit output templates, and strong validation checkpoints for destructive/batch actions. The only weakness is mild redundancy between the read-beyond-the-diff and best-fix sections, and a long inline proof subsection that could be externalized.

Suggestions

De-duplicate the 'read touched files / callers / callees / sibling surfaces' guidance shared between 'Read Beyond The Diff' and step 4-5 of the 'Best-Fix Review Loop' so each section stays distinct.

Consider moving the detailed proof:ui/proof:publish command reference into a separate reference file and keeping SKILL.md as a concise pointer with the decision rules.

Add a short per-section 'what to verify before moving on' line for the UI-proof and comment/label sections to mirror the explicit checkpoints already present in the bug-fix and best-fix sections.

Dimension	Reasoning	Score
Conciseness	Mostly lean, directive bullet prose with executable commands and no padding about concepts Claude already knows; the 'Read Beyond The Diff' and 'Best-Fix Review Loop' sections overlap on callers/callees and sibling surfaces, which could be tightened.	4 / 5
Actionability	Provides copy-paste-ready gh/bun commands with full --json field lists, concrete output templates (LOC: +x/-y, Best-fix verdict:, Alternatives considered:, Code read:, Remaining uncertainty:), and exact artifact paths covering the common PR review cases.	5 / 5
Workflow Clarity	The Best-Fix Review Loop is a numbered 1-7 sequence with explicit validation checkpoints (verify live state before acting, publish proof before commenting, --dry-run before publish, confirmation cap for closing >5 issues), plus clear feedback loops for failed publish.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested references and no bundle files; the lengthy proof:ui/proof:publish subsections are kept inline and could plausibly be split into a dedicated reference, leaving a minor organization gap.	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, third-person description that clearly states both the maintainer-facing actions and the triggering contexts, with concrete facets that distinguish it from ordinary implementation work. Only minor keyword-synonym gaps prevent a perfect trigger_term_quality score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete maintainer actions (reviewing, triaging, validating, discussing) and enumerates specific facets (author context, CI, UI proof, evidence, labels, close decisions, maintainer handoff), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (reviewing/triaging/validating/discussing with listed facets) and when ('Use when reviewing, triaging, validating, or discussing ClawHub GitHub issues or pull requests') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural maintainer terms like 'issues', 'pull requests', 'CI', 'labels', and 'evidence' with an explicit 'Use when' clause, but omits common synonyms such as 'PR' and does not surface file extensions.	4 / 5
Distinctiveness Conflict Risk	Scoped to 'ClawHub GitHub issues or pull requests' with maintainer-specific triggers, creating a clear niche with minimal overlap risk against generic coding skills.	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: openclaw/clawhub
Path: .agents/skills/clawhub-pr-maintainer/SKILL.md
Commit: f98a436

Reviewed: 3 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.