agentleFS
eugenezhangco-speceugenezhangco-spec/athena/.claude/skills/brain-dump/SKILL.md

brain-dump

Skill0 starsChanged 7 months agoMITView on GitHub

Capture unstructured thoughts and ideas into the user's Notion Brain Dumps database. Splits multi-idea dumps into separate entries, auto-categorizes, saves as Raw. Use when the user says "brain dump", "capture this", "save this thought", "dump this", "note this down", or sends a stream of loosely connected ideas.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If not present, ask the user to set it up or suggest running the onboard skill.

    line 25
  2. Very specific:

    Create one Notion page per distinct idea via mcp__notion__notion-create-pages.

    line 44
  3. Distinctive:

    If the idea has detail beyond the title, add it as page body content.

    line 46
  4. Distinctive:

    Keep Topic titles short and scannable (5–10 words max).

    line 52
  5. Distinctive:

    Default Status is "Raw" unless user says otherwise.

    line 53
  6. Distinctive:

    If the idea is clearly actionable, mention that in Note body but still save as Raw.

    line 54
  7. Distinctive:

    If a near-duplicate entry might already exist, flag it: "This looks similar to [existing].

    line 56

“Common” is measured: kept by at least 6 in 10 of the 7 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

Skill: Brain Dump

When to Use

  • User dumps unstructured thoughts, ideas, or observations
  • User says "brain dump", "capture this", "save this thought", "dump this", "note this down"
  • User sends a stream-of-consciousness message that contains actionable ideas
  • Auto-fire: when the user sends 3+ loosely connected ideas in one message

Prerequisites

This skill writes to a Notion database. The user must have configured their brain dumps database in personal/notion-databases.md:

braindumps_database_id: <user's Notion database ID>
braindumps_data_source: collection://<data source id>
braindumps_parent_page: <parent page id>

If not present, ask the user to set it up or suggest running the onboard skill.

Expected Notion Schema

PropertyTypeOptions
TopictitleFree text
CategoryselectBusiness, AI, Personal, Content, Ideas (user can customize)
DatedateAuto-set to today
StatusselectRaw, Refined, Actioned

Adapt to the user's actual property names if they differ.

Steps

  1. Parse the user's input. Identify distinct ideas or thoughts.
  2. For each distinct idea, determine:
    • Topic: a clear, concise title (not the full text — the essence in 5–10 words)
    • Category: best-fit from the options. If unclear, ask the user for that one.
  3. Create one Notion page per distinct idea via mcp__notion__notion-create-pages.
  4. Set Date to today. Set Status to "Raw".
  5. If the idea has detail beyond the title, add it as page body content.
  6. Confirm back to the user: list what was saved, with categories.

Rules

  • One idea per database entry. Split multi-idea dumps.
  • Keep Topic titles short and scannable (5–10 words max).
  • Default Status is "Raw" unless user says otherwise.
  • If the idea is clearly actionable, mention that in Note body but still save as Raw.
  • Green tier — save first, confirm after. Never ask for confirmation before saving a brain dump.
  • If a near-duplicate entry might already exist, flag it: "This looks similar to [existing]. Saving anyway."

Output Format

Saved to Brain Dumps:
- [Topic] (Category)
- [Topic] (Category)

One line per entry. No extra commentary.

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.