cog-braindump-capture
Scannednpx machina-cli add skill a5c-ai/babysitter/braindump-capture --openclawCOG 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-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
}
Source
git clone https://github.com/a5c-ai/babysitter/blob/main/plugins/babysitter/skills/babysit/process/methodologies/cog-second-brain/skills/braindump-capture/SKILL.mdView on GitHub Overview
Cog Braindump captures raw thoughts and automatically classifies them into personal, professional, and project-specific domains. It then routes entries to the correct vault directories, tags metadata such as date, domain, confidence, and topics, and extracts URLs for separate processing.
How This Skill Works
Raw text is fed into the system, which loads the user profile from 00-inbox to provide context. It uses NLP to classify the content by domain and writes the organized entry to the appropriate vault directory using file-write. It then searches for related notes, adds cross-references, and commits the changes with git-commit, all while attaching metadata like date, domain, confidence, and topics.
When to Use It
- Capturing raw thoughts or ideas and routing them to the correct vault domain (personal, professional, or project).
- Documenting meeting notes to ensure items are filed under the appropriate domain.
- Extracting embedded URLs for separate processing and linking to related vault entries.
- Creating cross-references between new captures and existing notes for quick lookup.
- Maintaining strict domain separation (02-personal vs 03-professional) in archival.
Quick Start
- Step 1: Provide the raw braindump text to the Capture tool.
- Step 2: System loads profile from 00-inbox and classifies by domain.
- Step 3: System writes to the vault, links related notes, and commits.
Best Practices
- Load your profile from 00-inbox before classification to provide context for routing.
- Keep braindump text concise but include key topics to improve metadata tagging.
- Review confidence scores and adjust domain routing if needed before finalizing.
- Use file-search to locate related entries and enrich new captures with links.
- Commit changes with git-commit to maintain a versioned, auditable history.
Example Use Cases
- Idea: redesign auth flow for the dashboard; route to project vault.
- Personal note: plan July vacation; route to 02-personal vault.
- Meeting recap: Q3 KPI targets discussed; route to 03-professional vault.
- URL: https://docs.example.com/api-auth updated docs; cross-reference to project notes.
- Brain-dump: outline for quarterly personal budget and project backlog.
