baoyu-post-to-x
Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".
89
86%
Does it follow best practices?
Impact
92%
3.06xAverage score across 6 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 communicates what the skill does (post content and articles to X/Twitter with media support), how it works (Chrome with CDP), and when to use it (with four natural trigger phrases). It is concise, specific, and highly distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: posting content, posting articles, supporting images/videos, long-form Markdown articles, and describes the technical approach (real Chrome with CDP). Very concrete and actionable. | 3 / 3 |
Completeness | Clearly answers both 'what' (posts content and articles to X with image/video support and long-form Markdown articles) and 'when' (explicit 'Use when' clause with four specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'post to X', 'tweet', 'publish to Twitter', 'share on X'. Also includes both platform names (X and Twitter), and mentions 'articles', 'images/videos' which users would naturally reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific platform (X/Twitter) with specific posting actions. The mention of CDP and anti-automation bypass further narrows the niche. Unlikely to conflict with other social media or general posting skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with good progressive disclosure and concrete executable commands for each post type. Its main weaknesses are repetitive notes across sections and a somewhat implicit overall workflow that could benefit from a clearer end-to-end sequence with validation checkpoints. The EXTEND.md preferences section is disproportionately verbose relative to its importance.
Suggestions
Consolidate the repeated 'Script opens browser with content filled in. User reviews and publishes manually' note into a single statement at the top (e.g., in a 'General Notes' section) rather than repeating it in every post type section.
Trim the EXTEND.md/Preferences section significantly — the dual bash/PowerShell blocks and two ASCII tables could be replaced with a simple priority list and a one-liner check command.
Add a brief end-to-end workflow summary (e.g., numbered steps: determine post type → run command → check output for warnings → user reviews and publishes) to improve workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some unnecessary repetition (e.g., the 'Note: Script opens browser with content filled in. User reviews and publishes manually' is repeated 4 times verbatim). The EXTEND.md section with both bash and PowerShell check commands plus two ASCII tables is verbose for what amounts to 'check if config file exists'. The Extension Support section at the end just repeats what was already said. However, the core command documentation is reasonably lean. | 2 / 3 |
Actionability | Every post type has concrete, executable command-line examples with clear parameter tables. The troubleshooting section provides a specific kill command. The pre-flight check script and fix guidance table are actionable. Commands are copy-paste ready (modulo the template variables which are clearly explained). | 3 / 3 |
Workflow Clarity | The post type selection logic is clear, and individual commands are well-documented. However, the overall workflow lacks explicit validation checkpoints — there's no clear sequence like 'run pre-flight → compose content → execute script → verify output → user publishes'. The Post-Composition Check for articles is good, but regular posts lack similar verification. The troubleshooting auto-retry for Chrome is a good feedback loop, but the general workflow could be more explicitly sequenced. | 2 / 3 |
Progressive Disclosure | The skill appropriately keeps the main file as an overview with command references, and delegates detailed workflows to `references/regular-posts.md` and `references/articles.md`. References are one level deep and clearly signaled. The script table at the top provides good navigation. Content is well-organized with clear sections. | 3 / 3 |
Total | 10 / 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
- jimliu/baoyu-skills
- Commit
9eb032a
- 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.