braindump
Skill4 starsChanged 5 months agoMITView on GitHub
Turn a messy voice ramble into clean, structured output — fixes transcription slips and organizes stream-of-consciousness into a spec, task list, outline, or decision.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- andreaskelm/pm-braintheir own version, first seen Oct 17, 2026
- atomicpapa/claude-obsidian-setuptheir own version, first seen Oct 9, 2026
- SamuelNDCE/claude-super-skill-librarytheir own version, first seen Aug 1, 2026
- huytieu/COG-second-braintheir own version, first seen Jul 30, 2026
- SamuelNDCE/ai-workbenchtheir own version, first seen Jul 24, 2026
- MohGanji/skillstheir own version, first seen Jul 10, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- huytieu/COG-second-brain★ 1.3ksame name
- andreaskelm/pm-brain★ 235same name
- MohGanji/skills★ 5same name
- broomva/skills★ 4same name
- atomicpapa/claude-obsidian-setup★ 2same name
- SamuelNDCE/ai-workbench★ 1same name
- SamuelNDCE/claude-super-skill-library★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository18 other files it gives its agents.
- biz-validateSkill
- catch-upSkill
- clone-websiteSkill
- double-checkSkill
- explain-for-grandmaSkill
- heavy-buildSkill
- heavy-reviewSkill
- heavySkill
- make-promptSkill
- monitor-claudeSkill
- orientSkill
- overnightSkill
- reelSkill
- sanity-checkSkill
- save-sessionSkill
- shipSkill
- what-breaksSkill
- yt-tranSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
1
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
- Distinctive: line 19
If genuinely ambiguous, pick the most useful one and say which you chose — don't block on it.
“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.
Files
The user thinks out loud through voice-to-text, so the input is a raw, possibly garbled ramble. Turn it into clean, organized output. The content is in $ARGUMENTS, or the user's most recent message if empty.
Step 1 — Clean the transcription
Silently fix likely voice-to-text errors: homophones, mangled technical terms, dropped or duplicated words, run-on sentences. If a fix would change the meaning and you're not sure, keep the user's wording and flag it — never silently invent intent.
Step 2 — Detect the shape
Work out what they're actually producing and pick the structure that fits:
- Spec / plan → goal, requirements, approach, open questions.
- Task list → grouped, ordered, actionable checkboxes.
- Notes / outline → headings + bullets by theme.
- Decision → options with honest trade-offs + a recommendation. If genuinely ambiguous, pick the most useful one and say which you chose — don't block on it.
Step 3 — Output
- Lead with a one-line summary of what they were getting at.
- Then the structured version — tight, deduplicated, logically ordered.
- End with Open questions / gaps if the ramble left anything undecided or contradictory.
Principles
- Organize and clarify; do not pad or add ideas they didn't express.
- Preserve every distinct point — structuring must never drop content.
- Surface contradictions you find rather than smoothing them over.
- Offer to save it to a file if it's substantial (a spec/plan worth keeping).
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
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.