keel
Measure whether a codebase's verification actually touches the world, or whether it is checking itself.
Reading sources and marking what holds up
What it does
A ship's keel is the reference line everything else is measured from. It is also what keeps the ship from capsizing — an even keel is a stability property, not a decoration.
What it can touch
Includes 63 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: docs/probes-as-minted/argv-array-test-runner-target.v1.ts, docs/probes-as-minted/artifact-publish-upload.v1.ts, docs/probes-as-minted/browser-binary-provisioning.v1.ts, docs/probes-as-minted/build-tool-target-test-invocation.v1.ts….
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.
Its code sends data over the internet
A script in it uploads or posts data. That is normal for a skill that talks to a service — check that the address is the service you expect.
How we know
reports/karaoke-gen.json line 144: “"raw": "\"\"\"\nFixtures for emulator integration tests.\n\nThese tests use REAL Firestore and GCS emulators, so we DON'T mock google.cloud…”. Read 2026-10-04, commit c9e02ba.
reports/karaoke-gen.json, line 144 ↗Asks for administrator rights
Some of its commands use sudo or "run as administrator". Those can change anything on your computer.
How we know
Seen in its code. Read 2026-10-04, commit c9e02ba.
9 smaller things worth knowing
Refers to a credentials file (SSH keys, cloud logins, tokens); Contains commands that delete or overwrite; Posts to a Discord or Telegram bot; Collects all of your environment variables. Usually legitimate — listed so nothing is hidden.
How we know
Refers to a credentials file (SSH keys, cloud logins, tokens) — SECURITY.md line 41; Contains commands that delete or overwrite — docs/2026-07-25-production-roadmap.html line 454; Refers to a credentials file (SSH keys, cloud logins, tokens) — docs/2026-07-25-production-roadmap.html line 550; Posts to a Discord or Telegram bot — docs/probes-as-minted/chat-webhook-notification.v1.ts line 25; Contains commands that delete or overwrite — reports/browser-use.json line 156; Contains commands that delete or overwrite — reports/keel-current.json line 324. Read 2026-10-04, commit c9e02ba.
SECURITY.md, line 41 ↗docs/2026-07-25-production-roadmap.html, line 454 ↗docs/2026-07-25-production-roadmap.html, line 550 ↗docs/probes-as-minted/chat-webhook-notification.v1.ts, line 25 ↗reports/browser-use.json, line 156 ↗reports/keel-current.json, line 324 ↗No serious risk pattern found
Launch7’s automated check read all 193 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 2026-10-04, commit c9e02ba 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 broomva/skills: 2026-10-04 (0 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 63 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 broomva
All from this publisher →- audit-harness-usage
Audit token usage and estimated API-equivalent cost across local agent harness traces from Codex CLI, Claude Code, Gemini CLI, and Cursor…
- bookkeeping
After any knowledge-gathering session: social engagement runs, research experiments, deep-dive sessions, conversation transcripts - When…
- broomva-design
Materialize and apply Broomva's platform-neutral calm blue-axis design system across digital products.
- citable
Make authored content survive the two selection surfaces it now faces: human engagement and LLM retrieval for citation.
- colombia-conflict
Knowledge engine over the Colombian Truth Commission (CEV) final report "Hay Futuro Si Hay Verdad" (2022) — the findings, statistics, armed-actor…
