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

83%

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

82%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-structured skill body: executable gh and proof-runner commands, explicit output templates, validation checkpoints, and a batch-close guardrail. Remaining weaknesses are mild redundancy across the evidence sections and an implicit (rather than explicit) end-to-end workflow ordering, plus proof-mode mechanics that could be split into a reference file.

Suggestions

Consolidate the overlapping evidence requirements in "Review Evidence Bar", "Enforce Bug-Fix Evidence", and the best-fix loop into one section referenced from the others.

State the end-to-end review pipeline (live state -> evidence -> best-fix analysis -> proof -> final comment) explicitly at the top so section order does not have to be inferred.

Move the detailed proof:ui runtime mechanics (flags, baseline/candidate URLs, artifact layout) into a reference file, keeping SKILL.md as the overview.

Dimension	Reasoning	Score
Conciseness	Dense imperative bullets with no explanation of concepts Claude already knows, but with some redundancy: evidence requirements appear in three sections ("Review Evidence Bar", "Enforce Bug-Fix Evidence", "Best-Fix Review Loop") and the origin/main comparison appears in both "Read Beyond The Diff" and step 6 of the loop. Not a 5 because clear trims are available; not a 3 because it is mostly efficient.	4 / 5
Actionability	Fully executable, copy-paste-ready commands cover the common cases: `gh pr view <number> --repo openclaw/clawhub --json title,body,author,...`, `gh api users/<login> --jq ...`, `bun run proof:ui -- --runner local --mode feature --scenario ...`, and `gh pr comment ... --attach ...`, plus concrete output templates like `LOC: +x/-y (N files)` and `Best-fix verdict:`.	5 / 5
Workflow Clarity	A numbered 7-step best-fix loop, explicit validation checkpoints (verify live state before commenting, inspect every final image/video, verify the final comment), a feedback loop for uninspected paths, and a batch-operation confirmation guardrail for closing more than five issues/PRs. Not a 5 because the end-to-end sequence (live state -> review -> proof -> comment) is implied by section order rather than explicitly framed as a pipeline.	4 / 5
Progressive Disclosure	No bundle files exist, and the single external reference ([proof-video](../proof-video/SKILL.md)) is clearly signaled and one level deep. Sections are well-organized, but the ~200-line body inlines UI-proof runtime mechanics that could live in a separate reference file, keeping it below a 5.	4 / 5
	Total	17 / 20 Passed

Description

78%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 description: third-person, concise, with an explicit trigger clause and a clearly scoped niche. The main gap is that the capability list is embedded in the when-clause rather than stated as a standalone what, and a few natural trigger variations (merge, approve, PRs) are absent.

Suggestions

State the what independently of the when, e.g. "Maintainer-facing review of ClawHub GitHub issues and pull requests: verify live state, enforce evidence bars, decide UI proof, post labeled proof comments. Use when...".

Add natural trigger variations such as "merge decisions" or "approve" to widen keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists several specific concrete actions ("reviewing, triaging, validating, or discussing") plus enumerated subtopics ("author context, CI, UI proof, evidence, labels, close decisions, and maintainer handoff") with minor coverage gaps such as merge decisions only being implied. Not a 5 because some subtopics are nouns rather than actions and coverage is not fully comprehensive.	4 / 5
Completeness	An explicit "Use when..." clause with concrete triggers is present, and the what (maintainer review actions and their subtopics) is concrete, but the what is fused into the when-clause rather than independently stated as in a 5-anchor description.	4 / 5
Trigger Term Quality	Good coverage of natural terms users would say ("reviewing", "triaging", "GitHub issues", "pull requests", "CI", "labels", "close decisions"). A few natural variations are missing, e.g. "merge", "approve", or the shorthand "PRs".	4 / 5
Distinctiveness Conflict Risk	"ClawHub GitHub issues or pull requests" carves out a clear niche with distinct triggers and minimal conflict risk with other skills, matching the 5 anchor.	5 / 5
	Total	17 / 20 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: openclaw/clawhub
Path: .agents/skills/clawhub-pr-maintainer/SKILL.md
Commit: 0180b56

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.