xurl
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.
86
82%
Does it follow best practices?
Impact
97%
1.44xAverage 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 an excellent skill description that clearly identifies the tool's purpose, lists comprehensive concrete actions, and includes an explicit 'Use when' clause with natural trigger terms. It uses proper third-person voice and covers both the platform names (X and Twitter) for maximum discoverability. The description is concise yet thorough.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, and interact with X API v2 endpoints. | 3 / 3 |
Completeness | Clearly answers both what ('A CLI tool for making authenticated requests to the X (Twitter) API') and when ('Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'tweets', 'reply', 'quote', 'search', 'DMs', 'followers', 'X', 'Twitter', 'upload media', 'post'. Good coverage of common variations including both 'X' and 'Twitter'. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused on X/Twitter API interactions. The specific platform name and API version (v2) make it highly distinct and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable skill with excellent concrete examples covering the full xurl CLI surface area. Its main weaknesses are redundancy (quick reference table duplicates command details), lack of validation/verification steps in workflows, and a monolithic structure that could benefit from splitting detailed references into separate files. The security guidance around credential handling is thorough and well-placed.
Suggestions
Remove the redundancy between the Quick Reference table and Command Details section — keep the table as a concise lookup and remove duplicate examples from one or the other.
Add validation checkpoints to workflows: e.g., after media upload, check the response for media_id before proceeding; after posting, verify the response contains the new post ID; for rate limit 429 errors, include a concrete retry pattern.
Trim the Notes section — Claude already understands concepts like rate limits, token refresh, and OAuth scopes. Keep only the xurl-specific behaviors (e.g., auto-refresh, ~/.xurl format).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-organized but contains significant redundancy — the Quick Reference table duplicates nearly all the Command Details section, and many examples are repeated across sections (e.g., media upload workflow appears three times). Some notes at the end explain things Claude already knows (token refresh, rate limits). Could be tightened substantially. | 2 / 3 |
Actionability | Excellent actionability — every command is fully executable and copy-paste ready with concrete examples. Installation commands, auth setup, posting, reading, engagement, media upload, raw API access, and streaming all have specific, runnable CLI commands with clear argument patterns. | 3 / 3 |
Workflow Clarity | Common workflows are clearly sequenced (upload then post, read then reply), but there are no validation checkpoints or error recovery loops. For example, the media upload workflow doesn't check if upload succeeded before posting, and there's no guidance on handling rate limit errors beyond 'wait and retry'. The destructive operations (delete, unfollow, block) have no confirmation or verification steps. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a useful quick reference table, but it's monolithic at ~300+ lines with no references to external files. The detailed command examples, global flags, streaming details, and notes could be split into separate reference files. However, since no bundle files are provided, the single-file approach is understandable though not ideal. | 2 / 3 |
Total | 9 / 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
a5bf5e0
- 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.