Tessl • The package manager for agent skills

SkillPublic

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

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

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 exemplarily lean CLI reference: all guidance is executable, organized by command, and free of padding. The only weakness is the absence of validation/verification checkpoints around its batch and destructive operations (update --all --force, publish), which caps workflow clarity.

Suggestions

Add a verification step after batch updates, e.g. run "clawhub list" (or "clawhub list --json") after "clawhub update --all" to confirm the installed versions and catch failed upgrades.

Frame "clawhub whoami" as a pre-publish checkpoint in the Publish section so auth status is confirmed before an outward-facing release.

Briefly note what "clawhub update --force" overrides and when it is safe to use, since force-upgrading all skills without confirmation is the riskiest documented operation.

Dimension	Reasoning	Score
Conciseness	The body is pure command listings under terse headers ("Search", "Publish", "Notes") with zero explanation of concepts Claude already knows; every token earns its place, matching the lean-and-efficient anchor. It is clearly not the level-4 case since there is no over-explanation to trim at all.	5 / 5
Actionability	Every example is a copy-paste-ready executable command covering the common cases, including flag variants ("clawhub install my-skill --version 1.2.3", "clawhub update --all --no-input --force") and a fully populated publish invocation. This matches the fully-executable top anchor with no gaps.	5 / 5
Workflow Clarity	Per-command usage is unambiguous, but the skill documents batch and potentially destructive operations ("clawhub update --all --no-input --force", "clawhub publish") with no validation or verification steps such as confirming state with "clawhub list" or checking "clawhub whoami" before publishing. Per the rubric, missing feedback loops for batch operations caps workflow clarity at 3 even though each single command is clear.	3 / 5
Progressive Disclosure	The body is under 50 lines, needs no external references, and is organized into clear per-command sections (Install, Auth, Search, Update, List, Publish, Notes). This satisfies the rubric's short-skill provision for a top score; no bundle files exist that should have been referenced (references/, scripts/, and assets/ are absent).	5 / 5
	Total	18 / 20 Passed

Description

87%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 that names a distinct niche, lists four concrete operations, and provides an explicit multi-clause "Use when..." trigger. It is concise without padding and scores near the top of the scale, losing only a little on action coverage and synonym variety.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions ("search, install, update, and publish agent skills") anchored to a named domain ("ClawHub CLI ... from clawhub.com"), matching the anchor for several specific actions with minor gaps. Secondary capabilities (list, login/whoami) are absent, keeping it below the comprehensive-coverage anchor.	4 / 5
Completeness	It explicitly answers both "what" (search, install, update, publish) and "when" via a concrete "Use when you need to..." clause with three distinct trigger phrases, matching the anchor that requires both what and when with concrete triggers. It is clearly above the level-4 anchor where the 'when' is less explicit.	5 / 5
Trigger Term Quality	Natural phrases like "fetch new skills on the fly", "sync installed skills to latest or a specific version", and "publish new/updated skill folders" mirror what a user would actually say, giving good keyword coverage. A few natural variations (e.g., "download" or "browse skills") are missing, so it falls just short of the comprehensive-synonyms anchor.	4 / 5
Distinctiveness Conflict Risk	"ClawHub CLI" and "clawhub.com" establish a clear niche with distinct triggers, making conflict with other skills minimal. There is no overlap with generic skill descriptions, matching the top anchor.	5 / 5
	Total	18 / 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
Revision: a0ad537

Reviewed: 21 days ago

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.

clawhub

Table of Contents

Is this your skill?