writing-intelligence
Writing Intelligence v6 — the Sovereign Meaning Runtime.
Testing what is locked and what isn’t
What it does
Writing Intelligence v6 — The Sovereign Meaning Runtime
What it can touch
Includes 45 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/build-skill.sh, scripts/check-links.py, scripts/check-manifest.py, scripts/wi.py…; binary files: writing-intelligence-craft.skill.
Uses terminal commands
It shows your AI commands to run. In a coding agent that means your terminal; in a chat app it usually can’t.
How we know
The SKILL.md contains shell code blocks.
12 smaller things worth knowing
Contains commands that delete or overwrite; Sets itself up to run again automatically later; Tells your AI to ignore its other instructions. Usually legitimate — listed so nothing is hidden.
How we know
Contains commands that delete or overwrite — CHEATSHEET.md line 147; Sets itself up to run again automatically later — CHEATSHEET.md line 332; Contains commands that delete or overwrite — USER_GUIDE.md line 49; Tells your AI to ignore its other instructions — USER_GUIDE.md line 202; Contains commands that delete or overwrite — docs/INSTALL.md line 415; Tells your AI to ignore its other instructions — docs/MIGRATION_v3_to_v4.md line 65. Read 2026-10-04, commit b59ef95.
CHEATSHEET.md, line 147 ↗CHEATSHEET.md, line 332 ↗USER_GUIDE.md, line 49 ↗USER_GUIDE.md, line 202 ↗docs/INSTALL.md, line 415 ↗docs/MIGRATION_v3_to_v4.md, line 65 ↗Partly checked
Launch7’s check could not read everything in this skill: 1 compiled program file it cannot read; 1 file too large to read. Nothing is known about the parts it skipped.
How we know
322 text files read; skipped files are listed by name only. Read 2026-10-04, commit b59ef95.
Recently maintained
Its repository has had changes recently.
How we know
Last push to antonio0720/writing-intelligence: 2026-09-30 (4 days before the scan).
Read automatically from the skill’s own files on GitHub on 4 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 45 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