Braindump capture
Skill a5c-ai/babysitter/library/methodologies/cog-second-brain/skills/braindump-capture
Capture raw thoughts with automatic domain classification and vault routingFrom its SKILL.md
npx -y skills add a5c-ai/babysitter --skill braindump-captureAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.5 KB, 244 tokens by cl100k_base, as published. Nobody here has run it
- Classify content into personal, professional, and project-specific domains
- Extract embedded URLs for separate processing
- Route classified content to appropriate vault directories
- Tag entries with metadata: date, domain, confidence, topics
- Maintain strict domain separation (02-personal vs 03-professional)
- Quality-gated capture with iterative refinement
Tool Use Instructions
- Use
file-readto load user profile from 00-inbox for classification context - Classify content by domain using natural language analysis
- Use
file-writeto create classified entries in appropriate vault directories - Use
file-searchto find related existing entries for cross-referencing - Use
file-writeto add cross-references to new and existing entries - Use
git-committo commit captured content
Examples
{
"vaultPath": "./cog-vault",
"captureType": "braindump",
"content": "Had a great idea about the auth system redesign. Also need to book vacation for July. The React 19 features look promising for our dashboard project.",
"targetQuality": 80
}
What ships with it: 1 file
761 B alongside SKILL.md
- README.md761 B