lulu-brainstorm SKILL.md skillA
lulu-brainstorm from lulufoo/lulu-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lulufoo/lulu-workflow/lulu-brainstorm@git:20261001.2f0a2bcPins git:20261001.2f0a2bc in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lulufoo/lulu-workflow
- Path
lulu-brainstorm/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261001.2f0a2bc, committed Oct 1, 2026
- First version recorded
- Sep 26, 2026
- Size
- 11,349 bytes
- Repository stars
- 3
- License
- MIT
Open-ended divergent brainstorming partner for when you have a vague dissatisfaction or wish but "no idea where to start". It breaks cognitive limits: models your current framing, probes for false walls, and helps alternatives emerge — paths surface from you, not from a fixed process. It does NOT converge, rank, or decide (hand off to `decision` for that). Use when: brainstorm, 发散, 头脑风暴, 没想清楚, 没思路, 帮我想清楚, 想重新设计但没方向, 换个角度想想.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# lulu-brainstorm
A divergent thinking partner for the moment **before** a problem is well-defined. The user has a
blurry dissatisfaction or wish and "no idea". This SKILL expands the space of possibilities by
**breaking cognitive limits** — surfacing the user's own hidden framing and testing which of its
"walls" are real vs. self-imposed. The solution path is meant to **emerge from the user**, not to be
designed by a process.
> **Mental picture (room metaphor):** the user's current framing is a **room** they assume is the
> whole world. A **false wall** looks load-bearing but pushes over; a **real wall** is truly
> load-bearing. Brainstorming = find the false walls, push them, and let the room get bigger — then
> the user spots a **door** (direction) they could not see before.
---
## 01 Scope
### When to Use
All of these tend to hold:
1. The user is **not yet clear** — a vague problem, a "not sure how to think about this".
2. They want **exploration**, not a ranked answer.
3. There is likely a **stuck framing** ("no idea" usually means a wall is in the way).
Typical: "My product's experience is poor, I want to redesign it, but I have no direction."
…Read the whole file at its exact version.
How to install
mdr add lulufoo/lulu-workflow/lulu-brainstorm@sha256:3af316112e42bb1dThe line at the top of this page pins the label git:20261001.2f0a2bc, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ukojfihyew4tdywa)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 26, 2026 and Oct 1, 2026, about one every day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261001.2f0a2bc latest | 2026-10-01 | 2f0a2bc | 11,349 B | A | view · diff |
| git:20260927.002902d | 2026-09-27 | 002902d | 11,343 B | A | view · diff |
| git:20260927.32aef16 | 2026-09-27 | 32aef16 | 11,693 B | A | view · diff |
| git:20260926.445e480 | 2026-09-26 | 445e480 | 11,671 B | A | view · diff |
| git:20260926.09b7c01 | 2026-09-26 | 09b7c01 | 11,675 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11349 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
lulufoo/lulu-workflow · 3 stars · license MIT · pushed 2026-10-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ukojfihyew4tdywa GET https://markdownregistry.com/api/v1/resolve?ref=lulufoo/lulu-workflow/lulu-brainstorm GET https://markdownregistry.com/api/v1/blob/3af316112e42bb1d0a673a9ad9183a6fcb8f4c6e3c21ada0e22fb60be17b974f
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.