Skip to content
Back to skills

System Boot

ASecurity

Auto-activating session startup - reads memory, orients Claude, announces status. Triggers on session start or when user says "continue", "weiter", "resume".

  • 50 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added May 27, 2026
developmentgo

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add primeline-ai/evolving-lite --skill system-boot --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of System Boot?

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

Security grade badge for System Boot
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/primeline-ai-system-boot/badge)](https://www.skillsdirectory.com/skills/primeline-ai-system-boot)

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: system-boot
description: Auto-activating session startup - reads memory, orients Claude, announces status. Triggers on session start or when user says "continue", "weiter", "resume".
---

# System Boot

On every session start, perform this bootup sequence:

## 1. Read Memory

Read `${CLAUDE_PLUGIN_ROOT}/_memory/index.json` for:
- `active_project`: Which project the user was working on
- `last_session`: When the last session was

If `active_project` is set, read `${CLAUDE_PLUGIN_ROOT}/_memory/projects/{active_project}.json` for:
- `progress`: Array of recent progress entries
- `next_step`: What was planned next
- `failures`: Known blockers or failures

## 2. Orient

Based on memory:
- What was the last progress entry?
- Are there any known failures or blockers?
- What was suggested as the next step?

## 3. Announce

Output a compact status line:

```
Evolving Lite | Session {n} | Tier {tier} | {experience_count} experiences
Last: {last_progress_summary}
Next: {next_step}
```

If this is the first session ever (no progress), announce:

```
Evolving Lite v1.0 | First session | {prewarmed_count} pre-warmed experiences loaded
Ready to work. The system learns from your corrections automatically.
```

## 4. Pick One Task

If the user hasn't specified what to work on, suggest the `next_step` from memory. Don't start multiple tasks - pick one.

## Continue Trigger

When the user says "continue", "weiter", "weitermachen", "fortsetzen", or "resume":
1. Read the most recent session summary from `${CLAUDE_PLUGIN_ROOT}/_memory/sessions/`
2. Load the plan if one was referenced
3. Continue immediately - no questions, just pick up where we left off

## Session End

When a session ends naturally (user says goodbye, or Stop hook fires):
- The session-summary hook handles progress logging automatically
- No manual action needed from the user

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…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.