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.
94
93%
Does it follow best practices?
Impact
100%
3.84xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies the tool (ClawHub CLI), lists concrete actions (search, install, update, publish), and provides explicit 'Use when' triggers with practical scenarios. The description is concise, uses third person voice appropriately, and is highly distinctive due to the specific product name.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'search, install, update, and publish agent skills from clawhub.com'. Also mentions syncing to specific versions and publishing skill folders. | 3 / 3 |
Completeness | Clearly answers both what ('search, install, update, and publish agent skills from clawhub.com') and when ('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'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'ClawHub', 'clawhub.com', 'CLI', 'install', 'publish', 'skills', 'sync', 'update', 'npm'. Users looking for skill management via ClawHub would naturally use these terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'ClawHub CLI' and 'clawhub.com'. This is a clear niche with very low conflict risk against other skills. | 3 / 3 |
Total | 12 / 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 CLI reference skill that provides fully actionable, copy-paste ready commands organized into clear sections. Its main weakness is the lack of validation/verification steps and error handling guidance, particularly for destructive operations like --force updates and publishing. The notes section efficiently covers configuration overrides without being verbose.
Suggestions
Add a brief verification step after publish (e.g., `clawhub search my-skill` to confirm it's live) and after update (check output or list to confirm version).
Add a note about what happens on error for --force or --all --no-input flags, or at minimum a caution about when to use --force.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Every line is a concrete command or essential note. No unnecessary explanations of what a CLI is or how npm works. Every token earns its place. | 3 / 3 |
Actionability | All guidance is concrete, copy-paste ready bash commands covering every major operation (search, install, update, list, publish, auth). Flag variations are shown explicitly rather than described abstractly. | 3 / 3 |
Workflow Clarity | Commands are logically grouped and sequenced (install → auth → search → install skills → update → list → publish), but there are no validation checkpoints or error recovery steps. For example, publish has no verification step to confirm success, and update with --force has no warning about potential consequences. | 2 / 3 |
Progressive Disclosure | For a simple CLI reference skill under 50 lines with no need for external references, the content is well-organized into clearly labeled sections. Each section is a distinct operation, making navigation easy. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 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 |
Total | 9 / 11 Passed | |
- Repository
- Hung-Reo/hungreo-openclaw
- Commit
d8d7f4b
- 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.