Second Brain Publish Agent Skill
>- material, and report what would leak through links before anything is exported. Use this skill when the user wants to publish notes as a site or digital garden, asks what is safe to make public, or is setting up an export. Do NOT use for exporting a single document, or for running the publishing tool itself.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/undefined-ui/second-brain-os --skill second-brain-publishThe instruction itself
5 sections, as written by the authorPrepare to publish
Once something is crawled, it is out. Every check here is cheap; the failure it
prevents is permanent.
Core rule
Explicit opt-in only. A page publishes because it says publish: true, never
because nothing excluded it.
Workflow
- List the opt-in set. Every page marked for publication.
- Follow their links. A published page linking to a private one either
leaks the title or produces a dead link. Report both.
- Scan for anything that should never ship: credentials, other people's
private information, confidential work, personal detail in examples.
- Check the frontmatter for fields not meant to be public, such as
confidence labels or private source paths.
- Report, do not export. The user runs the build.
Output format
Publishable: <n> pages
Links to unpublished pages: <n>
[[public page]] -> [[private page]]
Flagged content: <list with reasons>
Frontmatter to strip: <fields>
Verdict: <safe to build | fix these first>
Calibration
Err toward flagging. A false positive costs the user ten seconds; a miss is
permanent.
If the user asks to publish the whole vault, ask what they intend to do about
the private material rather than proceeding.
How to use it
Take undefined-ui/second-brain-publish from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.