
Publish Bundled Skill
Finds or writes a skill and publishes it to the Paperclip skills catalog.
Install
npx skills add paperclipai/paperclip --skill create-paperclip-bundled-skill -g -a claude-code -y- Repository
- paperclipai/paperclip110k
- Category
- AI and agents
- Updated
- 3d ago
- License
- MIT
- Context cost
- Mediumabout 2,603 tokens
- Runs scripts
- No, instructions only
What it does
Turn an idea, tweet, or task into a skill in the Paperclip skills catalog (packages/skills-catalog). Use when asked to FIND or MAKE a skill and publish it as a bundled/optional catalog skill: research prior art, reference or author it, add examples, regenerate the manifest, open a PR.
Create a Paperclip Bundled Skill
Take source material, a tweet, a task description, a blog post, "make a skill
that does X", and land it as a skill in the Paperclip skills catalog
(packages/skills-catalog/), delivered as a reviewed PR. The catalog is the
shelf every Paperclip company browses and installs from, so the bar is: correct
metadata, useful instructions, worked examples, and a clean validation run.
The core rule is FIND before MAKE: if a good skill already exists (in the catalog, in this repo, or published on GitHub), reference or adapt it instead of writing a duplicate from scratch.
When to use
- A human sends a tweet/link/idea and asks for it to become a Paperclip skill.
- A task asks to bundle an existing repo skill into the catalog.
- A task asks to add an external published skill to the catalog.
When not to use
- The skill is company-private (belongs in that company's library via the Skills UI/API, not the shipped catalog).
- You only need a repo-internal agent skill for working on Paperclip itself, that goes in
.agents/skills/orskills/, with no catalog machinery.
Step 0, Capture the source material
Understand exactly what the skill should teach before writing anything.
Tweets / X links. Use the xc CLI (X API client). Paperclip engineering
agent environments ship it preinstalled and pre-authenticated; it is not a
tool you install or mint credentials for yourself. Check availability before
relying on it:
command -v xc && xc whoami # on PATH and authenticated? if not, use the fallback below
xc get <post-url-or-id> --json # the post itself (conversation_id, author)
xc search 'conversation_id:<id>' --archive --json # rest of the thread (>7 days old needs --archive)
xc user <username> # author context
xc search '<topic keywords>' -n 30 # related discussion

