cog-braindump-capture
Capture raw thoughts with automatic domain classification and vault routing
Best use case
cog-braindump-capture is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Capture raw thoughts with automatic domain classification and vault routing
Teams using cog-braindump-capture should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/braindump-capture/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How cog-braindump-capture Compares
| Feature / Agent | cog-braindump-capture | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Capture raw thoughts with automatic domain classification and vault routing
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# 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
1. Use `file-read` to load user profile from 00-inbox for classification context
2. Classify content by domain using natural language analysis
3. Use `file-write` to create classified entries in appropriate vault directories
4. Use `file-search` to find related existing entries for cross-referencing
5. Use `file-write` to add cross-references to new and existing entries
6. Use `git-commit` to commit captured content
## Examples
```json
{
"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
}
```Related Skills
packet-capture
Expert skill for packet capture and analysis using libpcap/Wireshark. Execute tcpdump/tshark commands, write BPF filter expressions, analyze pcap files, decode protocol layers, calculate statistics, and generate Wireshark dissectors.
motion-capture-analyzer
Motion capture data processing and analysis skill for gait analysis and biomechanical studies
screen-capture-api
Cross-platform screen and window capture for screenshots and recording
performance-baseline-capturer
Capture performance baselines before migration for regression comparison and SLA verification
Findings Capture
Capture and persist research findings, discoveries, and decision rationale to findings.md.
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.
retrospect
Summarize or retrospect on a completed Babysitter run.
resume
Resume an existing Babysitter run from Codex.