Back to corpus
research noteexperiment writeup candidatescore 20
HandGuard Skill
- **Port**: 8766 (8765 is used by Clawdbot) - **Status URL**: http://localhost:8766/status - **State**: [home-path]
Full HTML reader
Read the full artifact
Extracted abstract or opening context
--- name: handguard description: Nail-biting prevention system - check status, confirm events, manage alerts homepage: https://github.com/diomandeee/comp-core user-invocable: true ---
- **Port**: 8766 (8765 is used by Clawdbot) - **Status URL**: http://localhost:8766/status - **State**: [home-path]
User phrases: "I'm biting my nails", "caught myself biting", "confirm nail bite", "nailbite"
The model needs 10+ confirmed events to learn your pattern: 1. When you catch yourself biting, say "nailbite" or run `nailbite` 2. System records the current sensor state 3. After 10+ samples, manifold_trained becomes True 4. Then it can detect and alert before you bite!
1. **Untrained** (0 samples): Uses only tension/velocity signals 2. **Training** (1-9 samples): Collecting data 3. **Trained** (10+ samples): Contact manifold active, high accuracy
Promotion decision
What has to happen next
Attach run IDs, datasets, metrics, and reproduction commands.
Why this is not always a full paper yet
Corpus pages are public-safe readers for discovered workspace artifacts. They are not automatically final papers. A corpus item becomes a polished paper only after the editable source, evidence checkpoints, references, figures, render path, and release status are attached through the paper schema.