clawhub
Search and install agent skills from ClawHub, the public skill registry.
68
63%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./nanobot/skills/clawhub/SKILL.mdQuality
Discovery
40%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 is concise and identifies a clear niche (ClawHub skill registry), making it distinctive. However, it lacks a 'Use when...' clause and could benefit from more specific action verbs and natural trigger terms that users might say when they want to find or add new skills.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user wants to find, browse, or install new agent skills, or mentions ClawHub, skill registry, or adding capabilities.'
Expand trigger terms to include natural user phrases like 'find skills', 'add a skill', 'browse plugins', 'skill marketplace', or 'download skill'.
List additional specific actions beyond search and install, such as 'browse categories, view skill details, check compatibility, and manage installed skills'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (agent skills from ClawHub) and two actions (search and install), but doesn't elaborate on additional capabilities like browsing, filtering, updating, or managing installed skills. | 2 / 3 |
Completeness | Describes what it does (search and install skills from ClawHub) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also thin, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'skills', 'ClawHub', 'install', and 'skill registry', but misses common user variations like 'find skills', 'add skill', 'plugin', 'marketplace', 'browse skills', or 'download skill'. | 2 / 3 |
Distinctiveness Conflict Risk | ClawHub is a very specific proper noun and 'public skill registry' is a distinct niche. This is unlikely to conflict with other skills due to the unique domain and terminology. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that provides fully actionable commands for all ClawHub operations. Its main weakness is that the search-install-restart workflow could be more explicitly sequenced, with the post-install reminder elevated from the notes section into the install workflow itself. Overall it's clean, efficient, and easy to follow.
Suggestions
Consider adding a brief numbered workflow showing the typical search → install → restart sequence, moving the 'remind user to start a new session' note into the install section as an explicit post-install step.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line earns its place. No unnecessary explanations of what a registry is or how npx works. The notes section contains only non-obvious, critical operational details (like the --workdir requirement). | 3 / 3 |
Actionability | All four operations (search, install, update, list) have complete, copy-paste-ready bash commands with correct flags. The placeholder `<slug>` is clearly explained. | 3 / 3 |
Workflow Clarity | The individual commands are clear, but the typical workflow (search → install → remind user to restart) is not explicitly sequenced as a numbered flow. For a non-destructive operation this is mostly fine, but the post-install step (new session reminder) is buried in notes rather than being part of an explicit install workflow. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines, the content is well-organized with clear section headers for each operation. No need for external references, and the structure makes each command easily discoverable. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 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 | 8 / 11 Passed | |
- Repository
- HKUDS/nanobot
- Commit
04a41e3
- Reviewed
Table of Contents
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.