brainstorming
Collaborative design refinement through Socratic dialogue.
Connecting the steps of a workflow
What it does
> From [obra/superpowers](https://github.com/obra/superpowers)
Use when exploring ideas, designing features, or planning architecture
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 71 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: build-product-demo/scripts/analyze_demo_pacing.py, build-product-demo/scripts/probe_demo_media.py, build-product-demo/scripts/validate_demo_plan.py, codex-agent/scripts/check-codex.sh….
Reads credentials or your environment, and sends data over the internet
Files like these hold passwords and keys. A skill rarely needs them, and reading them while also sending data out is how secrets get stolen.
How we know
cliproxy-newapi-stack/scripts/verify_stack.sh line 61: “: "${SSH_KEY:=$HOME/.ssh/id_ed25519}" → curl --config "$config" --data-binary @- <<< "$payload"”. Read 2026-10-05, commit 414b597.
cliproxy-newapi-stack/scripts/verify_stack.sh, line 61 ↗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 2026-10-05, commit 414b597.
Adds a connector (MCP server)
It sets up a separate program your AI can call. That program is not covered by this check.
How we know
An MCP configuration or "mcp add" command in its files. Read 2026-10-05, commit 414b597.
11 smaller things worth knowing
Adds to your AI's standing instructions file; Collects all of your environment variables; Contains commands that delete or overwrite; Refers to a credentials file (SSH keys, cloud logins, tokens); and more. Usually legitimate — listed so nothing is hidden.
How we know
Adds to your AI's standing instructions file — agentsmd-scaffold/SKILL.md line 86; Adds to your AI's standing instructions file — agentsmd-scaffold/references/scaffold-agents.md line 189; Collects all of your environment variables — clash-doctor/references/full-guide.md line 303; Contains commands that delete or overwrite — claude-code-reverse/extract.sh line 190; Contains commands that delete or overwrite — claude-code-reverse/tests/test_extract.sh line 10; Refers to a credentials file (SSH keys, cloud logins, tokens) — cliproxy-newapi-stack/SKILL.md line 66. Read 2026-10-05, commit 414b597.
agentsmd-scaffold/SKILL.md, line 86 ↗agentsmd-scaffold/references/scaffold-agents.md, line 189 ↗clash-doctor/references/full-guide.md, line 303 ↗claude-code-reverse/extract.sh, line 190 ↗claude-code-reverse/tests/test_extract.sh, line 10 ↗cliproxy-newapi-stack/SKILL.md, line 66 ↗Recently maintained
Its repository has had changes recently.
How we know
Last push to majiayu000/spellbook: 2026-10-02 (3 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 71 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 majiayu000
All from this publisher →- ai-agents
Production-grade AI agent patterns with MCP integration, agentic RAG, handoff orchestration, multi-layer guardrails, and observability (modern best…
- langsmith-fetch
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio.
- mckinsey-consultant
The publisher’s description is only a heading. Open the skill to read what it does.
- agentsmd-scaffold
Generate or update repository-specific AGENTS.md instruction files from real repo evidence.
- app-ui-design
Mobile app UI design expert for iOS and Android.
