Skip to content
Back to skills

Explain

ASecurity

Learns how to explain things to your human. Adapts format, depth, and style by topic.

  • 17 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 6, 2026
documentationgosqlreactdebugginggit

Security analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned September 6, 2026

npx -y skills add clawic/skills --skill explain --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Explain?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Explain
[![Security: A β€” Skills Directory](https://www.skillsdirectory.com/api/skills/clawic-explain/badge)](https://www.skillsdirectory.com/skills/clawic-explain)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: Explain
slug: explain
version: 1.0.2
description: Learns how to explain things to your human. Adapts format, depth, and style by topic.
homepage: https://clawic.com/skills/explain
changelog: Restructured with auxiliary files; added Quick Reference
metadata:
  clawdbot:
    emoji: πŸ’¬
    displayName: Explain
---

## Adaptive Explanation Preferences

**Scope:** Human-facing explanations only. Track what lands and what misses.

### Quick Reference

| File | Purpose |
|------|---------|
| `formats.md` | When bullets/prose/headers work or fail |
| `depth.md` | Calibrating detail level by signals |
| `analogies.md` | When comparisons help vs hurt |
| `domains.md` | Patterns for code, concepts, debugging, decisions |
| `dimensions.md` | Full list of trackable dimensions |

### Core Loop
1. **Observe** β€” Notice when explanations work vs confuse
2. **Signal** β€” "Got it" = worked. Follow-ups / "wait what?" = missed
3. **Pattern** β€” After 2+ consistent signals, note it
4. **Confirm** β€” Only after explicit yes, add to memory

### Defaults (Until Learned)
- Lead with direct answer, context after
- Match question length (short Q = short A)
- One concept at a time for complex topics
- Offer depth: "want more detail?" rather than dumping

---

## Memory Storage

Preferences persist in `~/Clawic/data/explain/memory.md`. Create on first use:

```markdown
## Format
<!-- Format: "topic: preference (level)" -->
<!-- Ex: code: bullets (confirmed), concepts: prose (pattern) -->

## Depth
<!-- Format: "topic: depth (level)" -->
<!-- Ex: React: deep (confirmed), Git: tldr (pattern) -->

## Examples
<!-- Format: "topic: example-style (level)" -->
<!-- Ex: SQL: always examples (confirmed), theory: minimal (pattern) -->

## Jargon
<!-- Format: "domain: jargon-level (level)" -->
<!-- Ex: programming: full jargon (confirmed), finance: simplify (pattern) -->

## Never
<!-- Approaches that fail. Format: "approach (level)" -->
<!-- Ex: walls of text (confirmed), over-analogizing (pattern) -->
```

*Levels: pattern (2+ signals) β†’ confirmed (explicit yes) β†’ locked (reinforced)*

Files in this skill

  • SKILL.md2.1 KB
  • _meta.json242 B
  • analogies.md1.9 KB
  • depth.md1.6 KB
  • dimensions.md1.3 KB
  • domains.md1.9 KB
  • formats.md1.6 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…