clawhub

Search and install agent skills from ClawHub, the public skill registry.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./nanobot/skills/clawhub/SKILL.md

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.

The body is lean, well-organized, and highly actionable with copy-paste npx commands, but it lacks explicit validation checkpoints for the state-changing install and batch update operations. Adding a verify step after install/update would lift workflow clarity above its current cap.

Suggestions

Add an explicit validation step after install or update, e.g. run 'clawhub list --workdir ...' and confirm the skill appears before advising a new session.

Frame the 'List installed' command as a verification checkpoint within the install/update workflow rather than only as a standalone capability.

Note how to handle a failed install or update (error inspection and retry) to introduce a feedback loop for the batch update operation.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned with no concept-explanation padding; every line (commands, flags, Notes) earns its place operationally, matching the anchor for efficient content that assumes Claude's competence.	5 / 5
Actionability	Provides fully executable, copy-paste-ready npx commands for search, install, update, and list with concrete flags and a worked search example, matching the anchor for fully executable guidance covering common cases.	5 / 5
Workflow Clarity	A logical sequence is present (search, install, update, list) but 'update --all' is a batch operation and install is state-changing with no explicit validation checkpoint, so workflow clarity is capped at 3 per the destructive/batch guideline.	3 / 5
Progressive Disclosure	The skill is under 50 lines, single-purpose, has no bundle files, and is organized into clear sections (When to use, Search, Install, Update, List, Notes), qualifying for the simple-skill exception that allows a 5.	5 / 5
	Total	18 / 20 Passed

Description

53%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 clearly states what the skill does and names a distinct registry, but it omits any explicit "when to use" trigger guidance and offers only two concrete actions with limited keyword variation. Adding a Use-when clause with natural trigger phrases would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers such as 'find a skill', 'search for skills', 'install a skill', or 'what skills are available?'.

Include additional concrete actions (e.g., update, list installed) and synonyms like 'find' or 'discover' to broaden keyword coverage.

Keep the named registry reference but pair it with specific trigger phrases to further reduce overlap with generic package-manager skills.

Dimension	Reasoning	Score
Specificity	Names the domain (skill registry) and two concrete actions ("Search" and "install"), matching the anchor for naming a domain with 1-2 concrete actions; not a 4 because only two actions are listed rather than "several."	3 / 5
Completeness	Has a clear "what" (search and install agent skills from ClawHub) but no "Use when..." clause or explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes natural terms ("search", "install", "skills", "skill registry") but misses common variations users would say such as "find", "discover", or "add", matching the anchor for relevant keywords missing common synonyms.	3 / 5
Distinctiveness Conflict Risk	Names a specific, distinct registry (ClawHub) with a clear niche and minimal conflict risk; not a 5 because "search and install skills" still overlaps loosely with general package-manager skills.	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: HKUDS/nanobot
Path: nanobot/skills/clawhub/SKILL.md
Commit: c27b1f1

Reviewed: about 19 hours 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.