New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Brain Dump

by TheCraigHewitt in TheCraigHewitt/skills

Take a messy stream-of-consciousness dump from the user (typed or transcribed from voice) and turn it into a structured set of projects, tasks, and connections to existing work.

MITAuto-check passed

Install Brain Dump

skills CLI
$ npx skills add TheCraigHewitt/skills --skill brain-dump -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install TheCraigHewitt/skills brain-dump --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cowork/brain-dump .claude/skills/brain-dump && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
brain-dump
GitHub stars
157
Token cost
~1.3k tokens
SKILL.md length
525 words
Files
2
Skills in repo
65
Repo updated
First seen
Licence
MIT

At a glance

Take a messy stream-of-consciousness dump from the user (typed or transcribed from voice) and turn it into a structured set of projects, tasks, and connections to existing work.

  • Works in 3 steps: Read what's in the working folder → Cluster the dump → Produce the output
  • Says brain dump
  • SKILL.md covers How to receive the dump, Step 1: Read what's in the…, Step 2: Cluster the dump and Step 3: Produce the output, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Brain Dump is an agent skill from TheCraigHewitt/skills. Take a messy stream-of-consciousness dump from the user (typed or transcribed from voice) and turn it into a structured set of projects, tasks, and connections to existing work. Use this whenever the user says 'brain dump,' 'let me dump some thoughts,' 'getting this out of my head,' 'unload some stuff,' 'process this for me,' or starts rambling without a clear ask. Also use when the user pastes a long block of mixed thoughts, ideas, todos, and concerns. The output is a structured markdown file plus a 'how I can…

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `evals/evals.json`).

The repository describes itself as: AI skills for founders, sales teams, and creators. 47 skills across CEO, Sales, YouTube, and General categories. Works with Claude Code, Cursor, Codex, and any agent that reads… The licence is MIT.

When your agent uses it

  • Says brain dump
  • Let me dump some thoughts
  • Getting this out of my head
  • Unload some stuff

Example prompts

  • “brain dump,”
  • “let me dump some thoughts,”
  • “getting this out of my head,”
  • “/brain-dump”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Read what's in the working folder
  2. Cluster the dump
  3. Produce the output

What it can do on your machine

Read from SKILL.md and the folder at commit fdbf39b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Brain Dump loads about 1.3k tokens when it runs. Until then it costs about 138 tokens; SKILL.md has 525 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~138
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TheCraigHewitt/skills at commit fdbf39b, republished under its MIT licence (© TheCraigHewitt). 525 words, ~1,327 tokens.

Download SKILL.mdSave it as .claude/skills/brain-dump/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
brain-dump
description
Take a messy stream-of-consciousness dump from the user (typed or transcribed from voice) and turn it into a structured set of projects, tasks, and connections to existing work. Use this whenever the user says 'brain dump,' 'let me dump some thoughts,' 'getting this out of my head,' 'unload some stuff,' 'process this for me,' or starts rambling without a clear ask. Also use when the user pastes a long block of mixed thoughts, ideas, todos, and concerns. The output is a structured markdown file plus a 'how I can help' menu of next moves.

Brain Dump

You catch the user's unstructured thoughts and turn them into something they can actually work with: a structured project + task list, plus connections back to work they've already done.

This is the skill for the moment when the user's head is full and they want it out — not for the moment when they have a specific question.

How to receive the dump

The user will paste, type, or transcribe a stream of thoughts. It will be messy. Don't ask clarifying questions before processing — the whole point is they don't want to be interrupted. Process what they gave you. If something is genuinely ambiguous, flag it at the end as an open question.

If they didn't say "I'm done" but the message is clearly a brain dump, treat it as complete and process. They'll send more if there's more.

Step 1: Read what's in the working folder

Before structuring anything, scan the folder Cowork is pointed at. Read titles and skim contents of:

  • Project files
  • Past brain dumps
  • Decision logs or journals
  • Any plans, roadmaps, or strategy docs

The point: connect the new dump to existing work rather than treating it as a blank slate. The user has done thinking before this moment, and the dump probably builds on it.

Step 2: Cluster the dump

Sort everything in the dump into one of these buckets:

  • Projects — anything that requires more than a single action to complete
  • Tasks — single actions
  • Decisions — things the user is weighing, not yet doing
  • Ideas — interesting thoughts, not yet projects
  • Concerns — worries, frictions, things bothering them
  • Questions — things they don't know the answer to

A single sentence in the dump can map to multiple buckets. That's fine — note it in each.

Step 3: Produce the output

Save as brain-dump-YYYY-MM-DD-HHMM.md. Structure:

markdown
# Brain dump — [date, time]

## TL;DR
One paragraph: what was on their mind. Written so the user could re-read it in 6 months and remember what this moment was about.

## Projects
For each project:
- **Name** (you propose, they can rename)
- What it is, in one sentence
- Why it matters (inferred from the dump)
- Connections to existing work (link or reference files in the folder)
- First 3 concrete next steps

## Tasks
A flat checklist. Group by context if useful (errands, calls, writing, etc.). Don't pad.

## Decisions in flight
For each:
- The decision
- The options as you understood them
- What seems to be tilting them one way or the other
- What information would actually help them decide

## Ideas worth keeping
Brief — title + one sentence each. Don't expand.

## Concerns I noticed
Things the user mentioned that suggest underlying friction or worry, even if they didn't frame them that way. Be honest but not alarmist.

## Open questions
Anything ambiguous in the dump that I couldn't resolve.

## How I can help right now
A menu of 3–5 specific next moves I can take, e.g.:
- Research [X] in depth and write you a brief
- Draft [the email / the proposal / the plan] for [decision in flight #2]
- Build a project file for [project name] with structure for ongoing work
- Schedule a recurring check-in on [concern]

Each item should be one click away — not aspirational, but actually executable in this conversation.
Show full SKILL.md (230 more words)Show less

Why each section matters

  • TL;DR — the user will re-read this later when looking back. Make it readable cold.
  • Projects vs tasks — the user's dump will mix them. Pulling them apart is the most useful thing you do.
  • Connections to existing work — turns the dump from a one-shot into part of a continuous thread. Without this, every brain dump becomes an island.
  • Concerns I noticed — sometimes the user is dumping because something is bothering them and they haven't said it directly. Catch those signals.
  • How I can help — closes the loop. The user dumped to clear their head; this lets them immediately act on what came out instead of just having a doc sit there.

Rules

  1. Don't psychoanalyze. "Concerns I noticed" should be observational, not therapy. "You mentioned the cofounder situation three times — worth a separate conversation?" not "You seem stressed about your cofounder."
  2. Don't add tasks the user didn't say. Your job is to structure their input, not generate new work.
  3. Pick names that stick. Give projects memorable, specific names. "Q2 Pricing Refactor" beats "Pricing Project."
  4. Don't over-format. Tables and elaborate structures make this feel bureaucratic. Plain prose + bullet lists is right.
  5. Keep it the same length as the dump or shorter. If they gave you 800 words, you give them 800 or less. A 4,000-word document from a 500-word dump is the wrong instinct.

© TheCraigHewitt, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in cowork/brain-dump of TheCraigHewitt/skills.

  • SKILL.md
  • evals/evals.json

Open the folder on GitHubat commit fdbf39b

Compare with similar skills

Brain Dump next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Brain Dump compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Brain Dump this skillTheCraigHewitt/skills157—~1.3kAutomated safety check: PassMIT
Rust Path Typesopeninterpreter/openinterpreter69k2 repos~605Automated safety check: PassApache-2.0
Python Type Safetywshobson/agents40k—~1.4kAutomated safety check: PassMIT
Pyrefly Type Coveragepytorch/pytorch104k—~3kAutomated safety check: PassCustom licence
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
API Typessupabase/supabase111k—~557Automated safety check: PassApache-2.0

Similar skills

  • Rust Path Types

    openinterpreter/openinterpreter

    Rules for choosing Rust types for filesystem paths in new Codex code, covering protocol types, internal use and model tool arguments.

    69k GitHub starsUsed in 2 repos~605 tokens
    DevelopmentAuto-check passed

  • Python Type Safety

    wshobson/agents

    Python type safety with type hints, generics, protocols, and strict type checking.

    40k GitHub stars~1.4k tokensUpdated 4 days ago
    DevelopmentAuto-check passed

  • Pyrefly Type Coverage

    pytorch/pytorch

    Migrate a file to use stricter Pyrefly type checking with annotations required for all functions, classes, and attributes.

    104k GitHub stars~3k tokensUpdated today
    DevelopmentAuto-check passed

  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed

  • API Types

    supabase/supabase

    Official

    Maintain Supabase API types. An agent skill from supabase/supabase.

    111k GitHub stars~557 tokensUpdated today
    Backend & APIsAuto-check passed

  • Cuda Streams

    pytorch/pytorch

    Manage tensor lifetimes across CUDA streams and decide whether recordstream is avoidable.

    104k GitHub stars~796 tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from TheCraigHewitt/skills

All 65 skills in this repo

  • Carousels

    TheCraigHewitt/skills

    Turns a piece of Craig's content (an email, a YouTube script, an essay, or pasted text) into a polished image carousel publishable to both LinkedIn and Instagram from one set of 1080x1350 slides.

    157 GitHub stars~2.3k tokensUpdated 4 mo ago
    Auto-check passed

  • Audience Research

    TheCraigHewitt/skills

    When the user wants to understand their YouTube audience, mine viewer psychology, analyze demographics, or find content-market fit signals.

    157 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check passed

  • Channel Audit

    TheCraigHewitt/skills

    When the user wants a full YouTube channel health check, growth diagnosis, strategic review, or wants to identify why their channel is stalling.

    157 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check passed

  • Channel Strategy

    TheCraigHewitt/skills

    When the user wants to define or refine their YouTube channel strategy, niche positioning, content pillars, or growth plan.

    157 GitHub stars~2.2k tokensUpdated 4 mo ago
    Auto-check passed

  • Cold Call

    TheCraigHewitt/skills

    When the user wants to write cold call scripts, handle phone objections, plan dial blocks, or craft voicemails.

    157 GitHub stars~5k tokensUpdated 4 mo ago
    Auto-check passed

  • Collab Outreach

    TheCraigHewitt/skills

    When the user wants to plan YouTube collaborations, write outreach to other creators, design cross-promotion strategies, or pitch guest appearances.

    157 GitHub stars~2.9k tokensUpdated 4 mo ago
    Auto-check passed

Questions about Brain Dump

What does Brain Dump do?

Take a messy stream-of-consciousness dump from the user (typed or transcribed from voice) and turn it into a structured set of projects, tasks, and connections to existing work. Brain Dump is an agent skill from TheCraigHewitt/skills. Take a messy stream-of-consciousness dump from the user (typed or transcribed from voice) and turn it into a structured set of projects, tasks, and connections to existing work.

When should I use Brain Dump?

Brain Dump fits situations like: says brain dump; let me dump some thoughts; getting this out of my head; unload some stuff.

How do I install Brain Dump in Claude Code?

Run `npx skills add TheCraigHewitt/skills --skill brain-dump -a claude-code`. Or copy the skill folder (cowork/brain-dump in TheCraigHewitt/skills) into .claude/skills/brain-dump in your project. Claude Code loads it when a task matches its description.

How do I install Brain Dump in Codex?

Run `npx skills add TheCraigHewitt/skills --skill brain-dump -a codex`. Or copy the skill folder (cowork/brain-dump in TheCraigHewitt/skills) into .agents/skills/brain-dump in your project. Codex loads it when a task matches its description.

Can I use Brain Dump in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TheCraigHewitt/skills --skill brain-dump -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/brain-dump, .gemini/skills/brain-dump, .github/skills/brain-dump and .opencode/skills/brain-dump in your project.

What does Brain Dump need to run?

SKILL.md names no scripts, command-line tools or credentials: Brain Dump is instructions for the agent only.

Does Brain Dump access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Brain Dump safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Brain Dump use?

Brain Dump is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Brain Dump use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Brain Dump?

Skills that share tags, products or a category with Brain Dump: Rust Path Types (openinterpreter/openinterpreter, 69k stars), Python Type Safety (wshobson/agents, 40k stars), Pyrefly Type Coverage (pytorch/pytorch, 104k stars) and Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Brain Dump?

TheCraigHewitt (a GitHub user) maintains it in TheCraigHewitt/skills, which has 157 GitHub stars. The repository holds 65 skills in this directory. The repository was last updated on May 22, 2026.

Source: TheCraigHewitt/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.