Babysitter cog-braindump-capture

Capture raw thoughts with automatic domain classification and vault routing

install

source · Clone the upstream repo

git clone https://github.com/a5c-ai/babysitter

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/methodologies/cog-second-brain/skills/braindump-capture" ~/.claude/skills/a5c-ai-babysitter-cog-braindump-capture && rm -rf "$T"

manifest: library/methodologies/cog-second-brain/skills/braindump-capture/SKILL.md

COG Braindump Capture Skill

Capture raw, unstructured thoughts and automatically classify them by domain (personal, professional, project-specific) for routing to appropriate vault sections.

Capabilities

Accept raw braindump text of any format
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-read
```
to load user profile from 00-inbox for classification context
Classify content by domain using natural language analysis
Use
```
file-write
```
to create classified entries in appropriate vault directories
Use
```
file-search
```
to find related existing entries for cross-referencing
Use
```
file-write
```
to add cross-references to new and existing entries
Use
```
git-commit
```
to 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
}