Skip to content
Back to search

raullenchai-skills

MarketplaceWorks with Claude CodeGitHub

Claude Code skills hand-crafted by Raullen from real day-to-day problems. More added over time.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/raullenchai--skills/badge.svg)](/listings/raullenchai--skills)

HTML

<a href="/listings/raullenchai--skills"><img src="/api/listings/raullenchai--skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Add the collection once:

/plugin marketplace add raullenchai/skills

Then install the skills you want:

/plugin install adjacent-possible@raullenchai-skills

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 12 lines
  1. {
  2. "name": "raullenchai-skills",
  3. "owner": { "name": "raullenchai" },
  4. "description": "Claude Code skills hand-crafted by Raullen from real day-to-day problems. More added over time.",
  5. "plugins": [
  6. {
  7. "name": "adjacent-possible",
  8. "source": "./plugins/adjacent-possible",
  9. "description": "Break out of your X (Twitter) filter bubble: prune noise, keep relationships, follow verified accounts one step outside what you already see."
  10. }
  11. ]
  12. }
README.md · README · 96 lines
  1. # skills
  2. A personal collection of [Claude Code](https://claude.com/claude-code) skills, hand-crafted by
  3. **Raullen** ([@Raullen](https://x.com/Raullen)) out of real problems in his own day-to-day work.
  4. Each skill is something he built for himself first, used for real, and then cleaned up to share.
  5. More skills will be added over time — each one is a separate plugin you can install on its own.
  6. ## Install
  7. Add the collection once:
  8. ```
  9. /plugin marketplace add raullenchai/skills
  10. ```
  11. Then install the skills you want:
  12. ```
  13. /plugin install adjacent-possible@raullenchai-skills
  14. ```
  15. ## Skills
  16. | Skill | What it does | Status |
  17. |---|---|---|
  18. | [adjacent-possible](#adjacent-possible) | Break out of your **X (Twitter) filter bubble**: prune noise, keep relationships, follow verified accounts one step outside what you already see | v0.1 |
  19. | *more coming* | | |
  20. ---
  21. ## adjacent-possible
  22. **A skill for breaking out of your filter bubble on X (Twitter).**
  23. > *The adjacent possible* — Stuart Kauffman's term for everything one step away from where you are:
  24. > reachable, but not yet explored.
  25. Recommendation feeds keep showing you more of what you already like. After a while that is all you
  26. see. This skill moves your X graph **one step outward** — not to random topics, but toward what *you*
  27. say you want to understand — and it does it from your own browser, at a human pace.
  28. ### What happens
  29. ```
  30. 1 Collect Claude reads your recent posts and who you follow (your logged-in Chrome, read-only)
  31. → a two-line diagnosis of your bubble
  32. 2 Ask "If your feed could teach you one or two new things this year, what would they be?"
  33. 3 Prune Followed accounts sorted into noise / sources / relationships.
  34. Relationships (your company, partners, investors, friends) are kept by default.
  35. 4 Expand 4–8 accounts per thing you want to learn, each verified as real and still active,
  36. each with one line on why it connects to you — plus a few long-form entry points
  37. 5 Apply Dry run first, then follow/unfollow in small batches at human speed
  38. 6 Check (optional) two weeks later: did the feed actually change? expand one more ring
  39. ```
  40. You spend about five minutes choosing. Claude does the reading, sorting, verifying and clicking.
  41. ### Requirements
  42. - Claude Code with [Claude in Chrome](https://claude.ai/chrome) connected
  43. - Chrome logged in to the X account you want to rebalance
  44. Then say something like *"my X feed is an echo chamber, help me break out"* or run `/adjacent-possible`.
  45. ### Safety
  46. - Runs entirely in your own browser tab. No passwords, no cookies, no private APIs, nothing sent
  47. anywhere by the script.
  48. - Nothing is followed or unfollowed until you approve the exact list and see a dry run.
  49. - Human pace: at most 20 actions per run, 15–35 s apart, and it stops if X shows a limit warning.
  50. Keep it under ~100 actions a day.
  51. - A keep-list protects accounts you never want touched.
  52. Automating clicks on X is your own call under X's terms of service; this tool is built to behave
  53. like a careful person, not a bot farm.
  54. ### Without Claude
  55. [`xedge.js`](plugins/adjacent-possible/skills/adjacent-possible/scripts/xedge.js) also works by hand:
  56. open X, paste it into DevTools → Console, then
  57. ```js
  58. // on https://x.com/<you>/following
  59. xEdge.start('following'); /* wait */ xEdge.status(); copy(xEdge.result(0, 9999))
  60. // follow / unfollow, dry run first
  61. xEdge.start('apply', { follow: ['someone'], unfollow: ['noise1'], keep: ['friend'], dryRun: true })
  62. xEdge.result(0, 50)
  63. ```
  64. The judgement parts — what to cut, what to add — are what the skill brings.
  65. ## License
  66. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.