ai-paste-cleanup
Apply the proven-safe AI-paste cleanup transforms to a note or folder.
Connecting the steps of a workflow
What it does
Apply the proven-safe AI-paste cleanup transforms to a note or folder. Deterministic Node script; always dry-run first; never writes without confirmation.
Use when AI-generated or pasted Markdown carries cruft - bold/italic-wrapped headings, citation markers, non-breaking spaces, zero-width…
You don’t need to name it. Ask for the job in your own words — your AI loads the skill when the request matches.
What it can touch
Includes 4 scripts
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: scripts/clean.js, scripts/rules.js, tests/clean.test.js, tests/rules.test.js.
1 smaller thing worth knowing
Hides invisible characters inside words. Usually legitimate — listed so nothing is hidden.
How we know
Hides invisible characters inside words — tests/fixtures/dirty-note.md line 7. Read 2026-10-05, commit 1c6f7ac.
tests/fixtures/dirty-note.md, line 7 ↗No serious risk pattern found
Launch7’s automated check read all 7 text files in this skill and matched none of its serious risk patterns. This is not a guarantee: a check like this can miss new or disguised tricks, and the author can change the files after the check.
How we know
Read 2026-10-05, commit 1c6f7ac by pipeline/trust/analyze.py — 40+ patterns for hidden text, prompt injection, downloads that run, credential access and more. It reads; it never runs the skill.
Recently maintained
Its repository has had changes recently.
How we know
Last push to neckarshore-skills/obsidian-vault-autopilot: 2026-10-01 (4 days before the scan).
Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 4 scripts beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end
More from neckarshore-skills
All from this publisher →- note-rename
Give poorly named vault notes clear, descriptive filenames.
- tag-manage
Audit a vault's existing tags, score them against the PascalCase convention, and apply guided cleanup: rename, merge, remove orphans, fix convention violations.
