@majiayu000/x-article-converter
BConvert blog posts or newsletters into X/Twitter articles with handles inserted and a posting strategy. Use when the user wants to turn an article into X content, create a tweetstorm, or promote content on Twitter/X with expert tagging. (project)
Install
agr install @majiayu000/x-article-converter --target claudeWrites 2 files into .claude/skills/, pinned to git-4da057e6.
- .claude/skills/x-article-converter/SKILL.md
- .claude/skills/x-article-converter/metadata.json
Document
name: x-article-converter description: Convert blog posts or newsletters into X/Twitter articles with handles inserted and a posting strategy. Use when the user wants to turn an article into X content, create a tweetstorm, or promote content on Twitter/X with expert tagging. (project)
X Article Converter
Transform blog posts and newsletters into X/Twitter-ready content with handles and a posting strategy.
Workflow
Step 1: Identify People and Companies
Read the source article and extract all:
- Named individuals (authors, experts quoted, founders)
- Companies/organizations mentioned
- Platforms/products referenced
Step 2: Find Twitter Handles
Use WebSearch to find Twitter/X handles for each person and company:
Search: "[Name] twitter" or "@[Name] site:twitter.com"
Create a handle reference table:
| Name | Handle | Role |
|---|---|---|
| Justin Skycak | @justinskycak | Math Academy, quoted |
If no handle found, note "No handle found" and skip tagging.
Step 3: Create the X Article Version
Duplicate the original article and insert handles at first mention only:
- Before: "Justin Skycak, Director of Analytics at Math Academy..."
- After: "@justinskycak (Justin Skycak), Director of Analytics at @MathAcademy..."
Keep handles natural - don't force them where they break flow.
Step 4: Create Launch Tweet Options
Write 3 ranked tweet options for the main article launch. Each should:
- Hook with the strongest insight or stat
- Tag 1-2 key people who might RT
- Include article link
- Stay under 280 chars (or use thread format)
Rank by: likelihood of engagement from tagged people.
Step 5: Create Weekly Posting Schedule
For each major expert/company in the article, write a standalone post:
| Day | Expert | Angle |
|---|---|---|
| Mon | [Name] | [Specific insight from their quote] |
| Tue | [Name] | [Different angle] |
Each standalone post should:
- Feature one person's insight
- Tag them directly
- Stand alone without requiring the full article
- Link back to article
Step 6: Output Files
Save to the same folder as the source article:
[Article-Name]-X-Article.md- Full article with handles[Article-Name]-Social-Assets.md- Contains:- Handle reference table
- 3 ranked launch tweets
- Weekly posting schedule with standalone posts
- Posting notes for handoff
Output Format
Social Assets File Structure
# [Article Name] - Social Media Assets
**Article:** [link]
**Date:** [date]
**Handoff Notes:**
- [Key instruction for assistant]
- [Who agreed to RT, if any]
---
## Twitter/X Handles
| Person | Handle | Role |
|--------|--------|------|
---
## MAIN LAUNCH TWEETS (Pick One)
### #1 PICK: [Label]
> [Tweet text]
**Why this one:** [Reasoning]
---
## WEEKLY SCHEDULE
### MONDAY: [Name]
**Angle:** [What makes this post unique]
> [Tweet text]
---
Keep It Simple
- One file for the X article version
- One file for posting strategy
- Handle reference table at top of both
- Clear handoff notes so assistant knows what to do
Repository README
Describes majiayu000/claude-skill-registry-data as a whole, which may contain artifacts other than this one. Where this artifact had no useful description of its own, its summary was taken from here.
Claude Skill Registry (Data)
This repo contains the archived skill contents (the heavy, browsable skill files).
Canonical layout
- Category folders at repo root (e.g.
development/,documents/,data/, ...) - Each skill lives under a category:
<category>/<skill>/SKILL.md+<category>/<skill>/metadata.json - Case conflicts are resolved with
{name}-{owner}-{repo}suffixes (fallback:-{short-hash}).
Archive status
- Live badges above are sourced from
claude-skill-registry-corestats.json. - Counts in this README are intentionally dynamic, not hardcoded.
- If the badges look stale, refresh the
corebuild/index pipeline rather than editing numbers here.
Where the index + site live
- Core repo: https://github.com/majiayu000/claude-skill-registry-core
- Main repo (merged publish artifact): https://github.com/majiayu000/claude-skill-registry
Trustgrade B
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- warnLicenseno SPDX license detected
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-4da057e65cf22026-07-31