baoyu-post-to-x
Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). In Codex, honor explicit requests for the Codex Chrome plugin/@chrome by using the Chrome Extension workflow; otherwise use Chrome Computer Use when available and fall back to real Chrome CDP scripts only when allowed. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".
65
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 defines what it does (post content and articles to X/Twitter with media support), when to use it (with explicit trigger phrases), and how it operates (multiple workflow paths). The inclusion of both 'X' and 'Twitter' branding ensures broad trigger coverage. The only minor weakness is the internal implementation detail about Codex Chrome plugin workflows, which adds complexity without helping skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: posting content, posting articles, supporting images/videos, X Articles (long-form Markdown), and describes multiple workflow paths (Chrome Extension, Chrome Computer Use, Chrome CDP scripts). | 3 / 3 |
Completeness | Clearly answers both 'what' (posts content and articles to X with images/videos, supports long-form Markdown articles) and 'when' (explicit 'Use when...' clause with four natural trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'post to X', 'tweet', 'publish to Twitter', 'share on X'. Also includes both platform names (X and Twitter) and mentions images/videos and articles. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: posting to X/Twitter specifically. The trigger terms are platform-specific ('tweet', 'post to X', 'Twitter') and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent workflow clarity, providing concrete commands, validation steps, and safety confirmations throughout. However, it suffers significantly from verbosity — the three execution modes create massive repetition of nearly identical workflows for each post type, and mode selection logic is restated redundantly in every section. The content would benefit greatly from deduplication and better use of progressive disclosure to move mode-specific details into separate reference files.
Suggestions
Deduplicate the repeated post-type workflows across the three modes by defining each workflow once with mode-specific callouts, rather than fully restating regular posts, video posts, quote tweets, and X Articles three times.
Remove the repeated 'Codex mode note' paragraphs from each CDP post-type section — the mode selection logic is already clearly defined at the top and doesn't need restating 4+ times.
Move the detailed Codex Chrome Plugin Mode and Chrome Computer Use Mode step-by-step workflows into separate reference files (e.g., references/chrome-plugin-mode.md, references/computer-use-mode.md) and keep only summaries in the main SKILL.md.
Consolidate the troubleshooting, prerequisites, and pre-flight check sections which contain information Claude likely already knows (e.g., how to install bun, what Accessibility permissions are).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines with massive repetition. The three execution modes (Codex Chrome Plugin, Computer Use, CDP) each repeat nearly identical workflows for regular posts, video posts, quote tweets, and X Articles. Every post type section includes a 'Codex mode note' that restates the mode selection logic. The mode selection rules are explained at the top and then re-explained throughout. | 1 / 3 |
Actionability | The skill provides fully executable bash commands with concrete parameters, specific script paths, detailed parameter tables, and step-by-step numbered workflows. Code examples are copy-paste ready with clear variable substitution patterns. Error recovery steps include specific commands (e.g., pkill for Chrome debug port issues). | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with numbered steps, explicit validation checkpoints (e.g., 'Verify no XIMGPH_ placeholders remain'), feedback loops (retry logic for Chrome plugin failures, validation after image insertion), and safety gates (explicit user confirmation before Publish). The mode selection decision tree is well-defined with clear priority ordering. | 3 / 3 |
Progressive Disclosure | The skill references external files (references/regular-posts.md, references/articles.md, EXTEND.md) and a scripts/ directory, which is good. However, the main SKILL.md is monolithic with enormous inline content that could be split — the three execution modes with their repeated workflows make the file very long. The Chrome Plugin Mode X Articles workflow alone is 10 detailed steps that could be in a reference file. | 2 / 3 |
Total | 9 / 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
bd5745f
- 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.