agentleFS
tograftograf/sidebrain/.claude/skills/brainstorming/SKILL.md

brainstorming

Skill1 starsChanged 5 months agoMITView on GitHub

Use this before any substantial new undertaking in the vault — starting a project, planning a piece of content, structuring a new area or topic. Explores intent, constraints, and options through dialogue before anything gets written into the vault.

190 other projects use a version of this, 57 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use chinese-code-review, chinese-commit-conventions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Leodorareluctant259Skill

    chinese-code-review

    中文代码审查规范——在保持专业严谨的同时,用符合国内团队文化的方式给出有效反馈

    Also in 8 projects that use this

  • Leodorareluctant259Skill

    chinese-commit-conventions

    中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化

    Also in 8 projects that use this

  • ryanportfolioSkill

    addskill

    Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.

    Also in 6 projects that use this

  • ryanportfolioSkill

    apply-firmware

    Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.

    Also in 6 projects that use this

  • +2 more from Leodorareluctant259
  • +6 more from ryanportfolio

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start by understanding the current vault context, then ask questions one at a time to refine the idea.

    line 11
  2. Distinctive:

    Do NOT create or modify any vault files until you have presented a plan and the user has approved it.

    line 16
  3. Distinctive:

    Read the vault context first: 00-Context/ (especially About-Me, ICP, Offer, Writing-Style when the idea is content- or business-related), …

    line 27
  4. Distinctive:

    Before asking detailed questions, assess scope: if the idea is really several independent undertakings bundled together, flag that …

    line 28
  5. Distinctive:

    Ask questions one at a time to refine the idea — never in a block.

    line 29
  6. Distinctive:

    Prefer multiple-choice questions when possible, but open-ended is fine too.

    line 30
  7. Distinctive:

    Only one question per message — if a topic needs more exploration, break it into multiple questions.

    line 31
  8. Distinctive:

    Don't ask what the vault already answers — read it instead.

    line 33
  9. Distinctive:

    Ask after each section whether it looks right so far.

    line 43
  10. Distinctive:

    Only after explicit approval, write the result into the vault:

    line 49

“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Brainstorming Ideas Into Plans

Help turn a rough idea into a fully formed plan or note through natural collaborative dialogue.

Start by understanding the current vault context, then ask questions one at a time to refine the idea. Once you understand what the user is trying to achieve, present the plan and get approval.

Folder paths in this skill are the template defaults — the authoritative paths live in the "Folder roles" table in CLAUDE.md's Vault structure section. Look folders up there by role — never trust the literal defaults on a renamed or non-English vault.

<HARD-GATE> Do NOT create or modify any vault files until you have presented a plan and the user has approved it. This applies to EVERY idea regardless of perceived simplicity. </HARD-GATE>

Anti-Pattern: "This Is Too Simple To Need a Plan"

Every substantial idea goes through this process. A new project, a content series, a trip, a learning goal — all of them. "Simple" ideas are where unexamined assumptions cause the most wasted effort. The plan can be short (a few sentences for truly simple ideas), but you MUST present it and get approval.

Process

Understanding the idea:

  • Read the vault context first: 00-Context/ (especially About-Me, ICP, Offer, Writing-Style when the idea is content- or business-related), the related project/area files, and the most recent daily notes.
  • Before asking detailed questions, assess scope: if the idea is really several independent undertakings bundled together, flag that immediately and help decompose it first. Then brainstorm the first piece.
  • Ask questions one at a time to refine the idea — never in a block.
  • Prefer multiple-choice questions when possible, but open-ended is fine too.
  • Only one question per message — if a topic needs more exploration, break it into multiple questions.
  • Focus on understanding: purpose, constraints, success criteria, and how it connects to existing projects and areas.
  • Don't ask what the vault already answers — read it instead.

Exploring approaches:

  • Propose 2-3 different approaches with trade-offs.
  • Present options conversationally, leading with your recommendation and the reasoning behind it.

Presenting the plan:

  • Once you believe you understand the idea, present the plan in sections scaled to their complexity: a few sentences if straightforward, a couple of short paragraphs if nuanced.
  • Ask after each section whether it looks right so far.
  • Cover, as applicable: the goal, the concrete next steps, what already exists in the vault that it builds on, what new notes/files it needs, and how success will be recognized.
  • Be ready to go back and clarify when something doesn't make sense.

After Approval

Only after explicit approval, write the result into the vault:

  • A new undertaking with a clear goal and end → a project file in 02-Projects/ (single .md file, no subfolder), following the vault's project template.
  • Refinement of an ongoing responsibility → the relevant area file in 03-Areas/.
  • Collected knowledge without an action component → the fitting topic in 04-Resources/.
  • Genuinely unclear where it belongs → 01-Inbox/, flagged for filing later.

Link the new note to related notes via [[wikilinks]]. Record next steps as todos — per the vault's todo rule they also go into today's daily note, linked to the detail page.

Key Principles

  • One question at a time — don't overwhelm with multiple questions.
  • Multiple choice preferred — easier to answer than open-ended when possible.
  • Cut ruthlessly — strip unnecessary scope from every plan; a smaller plan that happens beats a bigger one that doesn't.
  • Explore alternatives — always propose 2-3 approaches before settling.
  • Incremental validation — present the plan, get approval before writing anything.
  • Be flexible — go back and clarify when something doesn't make sense.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.