Sub-skill of improve: Manual vs Automatic Invocation.
Scanned 9/9/2026
Install to Claude Code
Skills Directorynpx -y skills add vamseeachanta/workspace-hub --skill manual-vs-automatic-invocation --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Manual Vs Automatic Invocation?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/vamseeachanta-manual-vs-automatic-invocation-workspace-hub)More formats (shields.io, HTML) on the badges page.
---
name: improve-manual-vs-automatic-invocation
description: 'Sub-skill of improve: Manual vs Automatic Invocation.'
version: 1.4.0
category: workspace-hub
type: reference
scripts_exempt: true
---
# Manual vs Automatic Invocation
## Manual vs Automatic Invocation
| Mode | Trigger | Engine | AI Quality |
|------|---------|--------|------------|
| Manual | `/improve` command | Claude session (full reasoning) | Highest — full context |
| Automatic | Stop hook at session exit | `improve.sh` + API calls | Good — structured prompts |
| Quick | Ctrl+C or `--quick` | `improve.sh` shell-only | None — metrics + logging only |
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
