clawhub-moderation

Use for ClawHub staff moderation actions with the repo-local ClawHub admin tool: skills, users, org publishers, plugin packages, trusted publishers, official publishers, and guarded staff email.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

96%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.

The body is a lean, fully executable command reference with strong safety guardrails, dry-run/confirmation feedback loops for destructive operations, and dedicated post-write verification guidance. Its only structural weakness is that the full six-group CLI reference is inlined rather than split into one-level-deep bundle files.

Dimension	Reasoning	Score
Conciseness	Every section is operational — command listings, executable examples, safety rules, and impact notes — with no explanations of concepts Claude already knows and no padding. Annotations carry non-obvious domain facts ('hard-delete requires an owner-qualified ref and defaults to a dry-run'), so every token earns its place.	5 / 5
Actionability	Commands are copy-paste ready with placeholders for every command group (e.g. 'bun run admin -- skills hard-delete @owner/<slug> --reason "<reason>" --apply --confirm "<token>" --yes'), covering the common cases for skills, users, orgs, packages, and email.	5 / 5
Workflow Clarity	Destructive operations get explicit validation loops: dry-run default, confirmation token from the dry-run, --apply --yes, a dedicated Verification section ('verify owner-scoped page/API reads return not found'), and reporting of verification blockers. Email requires dual confirmation flags. No cap applies since validation is present and explicit.	5 / 5
Progressive Disclosure	Sections are well-organized (Safety Rules, Command Map, per-group detail, Verification, Impact Notes) with no nested references, but the entire 243-line command reference for six command groups is inlined in SKILL.md. It exceeds the simple-skill 50-line exception, so per-group detail could live in reference files; structure is nonetheless clear, placing it above anchor 3.	4 / 5
	Total	19 / 20 Passed

Description

73%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.

The description has a well-defined niche and clear scope via its enumerated entity list, with explicit trigger guidance. Its main weakness is that the capability itself stays generic — no concrete moderation actions (ban, unhide, hard-delete, transfer, revoke) are named, which limits both specificity and natural trigger-term coverage.

Suggestions

Name the concrete actions the tool performs, e.g. '...actions (ban/unban users, hide or hard-delete skills, transfer or hard-delete plugin packages, manage trusted and official publishers, send guarded staff email)'.

Add an explicit 'Use when...' clause with user-side trigger phrasing, e.g. 'Use when asked to moderate, ban, hide, delete, or restore ClawHub content or accounts'.

Include common synonyms users would say (moderate, takedown, reinstate, suspend) to strengthen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The action verb is generic ('staff moderation actions') but the enumerated targets are concrete ('skills, users, org publishers, plugin packages, trusted publishers, official publishers, and guarded staff email'). This exceeds anchor 2's bare domain naming yet falls short of anchor 4, which requires several specific named actions.	3 / 5
Completeness	'Use for ClawHub staff moderation actions' is explicit trigger guidance, so the what and when are both present and the anchor-3 cap does not apply. It is not anchor 5 because the when lacks concrete user-side trigger phrases naming the specific moderation requests.	4 / 5
Trigger Term Quality	Good natural keywords ('ClawHub', 'staff moderation', 'admin tool', and the entity names) that a staff member would plausibly say, but common action phrases users would actually utter ('ban this user', 'hide this skill', 'delete this package', 'transfer') are missing, so it falls short of anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	'ClawHub staff moderation' with the 'repo-local ClawHub admin tool' carves out a clear niche with distinct triggers and minimal conflict risk with any other skill.	5 / 5
	Total	16 / 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-moderation/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.