Index of every page on this site: llms.txt
All skills
davila7 avatar

/brainstorming

@053feb2
Run it yourself

You MUST use this before any creative or build work: creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a website, a talk, a business). Finds out what the user actually wants and why, one question at a time, compares 2-3 approaches and gets a design doc approved before anything is built. Use it even if they never say brainstorm or design; skip it only for fully specified one-line tasks.

Use this Skill: https://skilld.dev/gh/davila7/claude-code-templates/brainstorming

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesbuilder-check.md

≈443 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Builder check

Run this once the full written design exists (projects only, not small changes). The goal is to find the places where someone planning from the doc would have to guess, while the user is still around to answer.

1. Get a fresh reader

If you can start a subagent, give it this prompt with the domain and the document path filled in. Without a subagent, read the document yourself as that builder, ignoring everything you know from the conversation.

You are a talented [DOMAIN, e.g. "software engineer", "event planner"].
You've been handed a design document and asked to plan how to build what it
describes. You cannot talk to the person who wrote it.

Read [DOCUMENT_PATH].

Report only the questions you'd still need answered before you could plan
this well: places where you'd have to guess and a wrong guess would matter.
For each, give the question and why the answer changes the plan. Rank them
by importance.

Skip anything the document explicitly leaves to the builder, anything you
could reasonably decide yourself, and wording nitpicks.

If nothing important is left, say "nothing important left".

2. Sort what comes back

  • Answered already by the conversation or the project: put the answer in the document.
  • Minor: a sensible builder could settle it without changing what gets built. Settle it and mark it in the document as your call.
  • Theirs: only the user can answer it, and the answer changes what gets built.

3. One round with the user

Bring the "theirs" pile in a single message, most important first. Update the document with their answers, then hand it over with a short list of the calls you made so they can check those while reading. That is the only round of questions the check produces.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts20d5 checks · Risk SAFE
  • Gen Agent Trust Hub20d

    The skill facilitates a collaborative brainstorming and design process. It is generally safe, though it possesses an indirect prompt injection surface because it ingests project files and documentation that could theoretically contain untrusted instructions.

  • Socket20d

    No alerts

  • Snyk20d

    Risk: LOW · No issues

  • Runlayer9mo

    1 file scanned · No issues

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 053feb2. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 3 weeks ago
Other metadata
metadata
{
  "author": "Jesse Vincent (obra/superpowers), adapted by claude-code-templates",
  "source": "https://github.com/obra/superpowers/tree/2ce8aa15d05bd57213e6f746f953aafb7ded7a8b/skills/brainstorming",
  "version": "2.0.0"
}

README badge

README badge for davila7/claude-code-templates/brainstorming