clawhub

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

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

87%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.

An efficiently organized, fully executable CLI cheat-sheet that is copy-paste ready. Its main gap is the absence of validation/verification guidance for consequential batch and publish operations, which caps workflow clarity.

Suggestions

Add a pre-publish validation step, e.g. "clawhub publish --dry-run" or a check that the skill folder has a valid SKILL.md before running the real publish.

Before "clawhub update --all --force", document a preview step (e.g. "clawhub list" or a "--dry-run") so changes can be reviewed before applying batch forced upgrades.

Add a brief sequenced workflow for the publish path (login → verify folder → publish → confirm with clawhub whoami/search) with an explicit checkpoint after each step.

Dimension	Reasoning	Score
Conciseness	Lean section-and-command structure with no concept over-explanation ("Install\n```bash\nnpm i -g clawhub\```"); every token earns its place and assumes Claude's competence.	5 / 5
Actionability	Fully executable, copy-paste-ready commands for every operation, including common-case variants ("--version 1.2.3", "--all --no-input --force", publish with slug/name/version/changelog flags).	5 / 5
Workflow Clarity	Sections are grouped (install → auth → search → update → publish) but no validation checkpoints exist for batch/destructive operations like "clawhub update --all --force" and "clawhub publish", which the rubric caps at 3.	3 / 5
Progressive Disclosure	A simple single-purpose CLI reference with well-organized section headers and no need for external files; no bundle files exist and nothing is buried or nested, so the simple-skill exception applies.	5 / 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, specific description with an explicit Use-when trigger clause and concrete action verbs covering the CLI's full operation set. Minor room to broaden trigger-term coverage, but it cleanly answers both what and when.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "search, install, update, and publish agent skills" — plus variants ("fetch new skills", "sync installed skills to latest or a specific version", "publish new/updated skill folders"), giving comprehensive coverage of the tool's operation set.	5 / 5
Completeness	Explicitly answers both "what" ("Use the ClawHub CLI to search, install, update, and publish agent skills") and "when" via a concrete "Use when you need to fetch new skills on the fly, sync..." trigger clause.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("install skills", "update skills", "publish a skill") with synonyms (fetch, sync), but coverage is good rather than exhaustive — terms like "browse" or "manage skills" are absent.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific named tool ("ClawHub CLI", "clawhub.com") with a clear niche (agent skill distribution), giving it distinct triggers and minimal overlap 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/clawhub/SKILL.md
Commit: f8d9f0b

Reviewed: 5 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.