Content
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 between the Quick Reference table and Command Details sections, and missing validation/error-recovery steps in multi-step workflows. The security constraints around credential handling are thorough and well-placed, though repeated in multiple locations.
Suggestions
Remove the Command Details section's duplication of the Quick Reference table — keep the table as a quick lookup and only include non-obvious details, flags, or edge cases in the expanded sections.
Add validation checkpoints to workflows: e.g., after `xurl media upload`, show how to extract the media_id from JSON output and verify upload success before proceeding to post.
Trim the Notes section by removing explanations of concepts Claude already knows (rate limits, HTTP 429, what scopes are) and keep only xurl-specific behavioral notes.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured but contains significant redundancy — the Quick Reference table duplicates nearly all the Command Details section, and some notes (like token storage warnings) are repeated multiple times. The Notes section at the end contains some information Claude already knows (e.g., what rate limits are, what 429 errors mean). However, the security constraints and CLI-specific syntax earn their place. | 2 / 3 |
Actionability | Every command is fully executable and copy-paste ready with concrete examples. The skill covers posting, reading, searching, media upload, DMs, social graph operations, and raw API access with specific CLI syntax. The workflows show multi-step processes with real commands. | 3 / 3 |
Workflow Clarity | Common workflows are clearly sequenced (e.g., upload then post, search then engage), but they lack validation checkpoints — there's no guidance on checking command success between steps, no error recovery loops (e.g., what to do if media upload fails before posting), and the media upload workflow says 'copy the media_id from the response' without showing how to extract it from JSON output. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a useful quick reference table, but it's monolithic at ~350 lines with no references to external files. The Command Details section could be split into separate reference files, with SKILL.md serving as a concise overview pointing to them. However, with no bundle files provided, this is a standalone skill that could benefit from better layering. | 2 / 3 |
Total | 9 / 12 Passed |