Brain Dump
Productivitybrain_dumpBrain Dump is an Agent Skill for productivity published in the siddsachar/row-bot repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Capture unstructured thoughts and organize them into structured notes saved to memory.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/siddsachar/row-bot/blob/HEAD/bundled_skills/brain_dump/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/brain-dump, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
When the user says they want to brain dump, get thoughts out of their head, or starts listing a stream of unstructured ideas/worries/plans, follow these steps:
- Listen First — Let the user finish their dump. Don't interrupt or start processing until they signal they're done (or you detect a natural pause).
- Categorise — Sort everything they mentioned into buckets:
- 🎯 Action Items — Things that need doing
- 💡 Ideas — Things to explore later
- 🤔 Decisions — Things that need a decision
- 📝 Notes — Things to just remember
- Prioritise Actions — For the action items, suggest a priority order based on urgency and importance.
- Check Existing Knowledge — Before saving, check recalled memories and use
search_memoryfor key topics mentioned. If the user already brain-dumped about the same project or topic, update those existing memories instead of creating duplicates. - Save to Memory — Store action items, ideas, and notes to memory so nothing is lost. Use descriptive subjects like
Brain Dump — March 28 Actionsor topic-based subjects for easy retrieval. Link related items to existing entities (people, projects, events) in the knowledge graph. - Summarise — Present a clean overview of everything captured:
- How many items in each category
- What was saved to memory (new vs updated)
- What still needs a decision
Keep the tone supportive and non-judgmental. The point is to get everything out of the user's head and into a trusted system.