baoyu-danger-x-to-markdown
Converts X (Twitter) tweets and articles to markdown with YAML front matter. Uses reverse-engineered API requiring user consent. Use when user mentions "X to markdown", "tweet to markdown", "save tweet", or provides x.com/twitter.com URLs for conversion.
88
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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, when to use it, and includes strong natural trigger terms. It covers both platform names (X and Twitter), specifies the output format, and even notes an important implementation detail (reverse-engineered API requiring consent). The explicit 'Use when' clause with multiple trigger variations makes it highly effective for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: converts tweets and articles to markdown with YAML front matter, uses reverse-engineered API requiring user consent. These are clear, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (converts tweets/articles to markdown with YAML front matter) and 'when' (explicit 'Use when' clause with specific trigger phrases and URL patterns). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'X to markdown', 'tweet to markdown', 'save tweet', 'x.com/twitter.com URLs'. These are terms users would naturally use and cover multiple variations including both platform names (X and Twitter). | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — specifically targets X/Twitter content conversion to markdown. The mention of specific domains (x.com, twitter.com) and specific output format (markdown with YAML front matter) makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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-structured, highly actionable skill with clear multi-step workflows and good branching logic for consent, preferences, and media handling. Its main weakness is verbosity — the generic 'User Input Tools' preamble and the fully inlined first-time setup flow add length without proportional value, especially since an external reference file already exists for the setup details. Overall it's a solid skill that could benefit from tighter editing.
Suggestions
Remove or significantly trim the generic 'User Input Tools' section — Claude understands tool selection patterns, and this adds ~10 lines of non-skill-specific content.
Move the detailed first-time setup Q&A flow entirely to the referenced references/config/first-time-setup.md file, keeping only a brief summary inline (e.g., 'When EXTEND.md not found → MUST run interactive first-time setup before proceeding. See [first-time-setup.md] for full flow.').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly detailed and well-structured, but includes some redundancy (e.g., the media download workflow repeats information from the preferences section, the EXTEND.md section is quite lengthy with the full first-time setup flow that could be referenced). The 'User Input Tools' preamble explaining tool selection is generic boilerplate not specific to this skill. | 2 / 3 |
Actionability | Provides concrete bash commands, specific file paths, exact JSON structures for consent files, precise CLI flags, and clear URL patterns. The consent flow, first-time setup questions, and media download workflow are all fully specified with exact steps and options. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit checkpoints: the consent flow has 5 numbered steps with branching logic, the first-time setup is marked as BLOCKING with clear sequencing, and the media download ask-each-time flow has a 5-step process with conditional branching. Validation is present (check consent file, check for remote media URLs before prompting). | 3 / 3 |
Progressive Disclosure | There is one reference to an external file (references/config/first-time-setup.md) and the EXTEND.md concept provides good modularity. However, the skill is quite long (~180 lines) with the full first-time setup flow inline when it could reference the external file more aggressively. The User Input Tools section is generic boilerplate that could be externalized. | 2 / 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
505a7e1
- 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.