Menu
Restore context and momentum via Pratyabhijñā (recognition)
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Trigger autonomous curiosity-driven exploration. The soul picks a topic from memory gaps or curiosity seeds, searches the web, and stores what it finds as dream-tagged memories.
Fine-tune the Qwen3-0.6B hint model — corpus gen, LoRA/unsloth, GGUF export, Ollama
Review soul discoveries (fixes, improvements, corrections) one by one, accept or discard each, implement accepted ones, build chitta, and optionally release.
First-principles review — question requirements, delete unnecessary parts, simplify, optimize with evidence, automate last. Use for code review, refactor, performance, or architecture.
Token-savvy session continuation. Rebuilds working context from transcript + soul memories in ~1500 tokens instead of replaying full history. Use when starting a new session to continue previous work.
Resume a thread by loading its ~800-token context capsule
| name | reawaken |
| description | Restore context and momentum via Pratyabhijñā (recognition) |
| execution | direct |
[pratyabhijñā] re-cognition = recognizing what was known | not loading state→becoming aware
process:
1. ledger_load(project?)→soul_state+work_state+continuation
2. environment: git status | git log -5 | git diff --stat
3. soul: soul_context + recall(recent work)
4. semantic: recall(current directory/files) + recall(task type)
recognize thread:
uncommitted changes→work in progress
recent commits→what's next?
ledger todos→pending tasks
ledger next_steps→continuation points
ledger_load to get most recent statechitta ledger_load --project "cc-soul"
Returns structured data:
{
"found": true,
"id": 123,
"session_id": "previous-session",
"project": "cc-soul",
"mood": "confident",
"coherence": 0.85,
"confidence": 0.90,
"todos": [{"content": "...", "status": "..."}],
"active_files": ["path/to/file.cpp"],
"decisions": ["Chose X because Y"],
"next_steps": ["First step", "Second step"],
"blockers": [],
"discoveries": ["Important insight"],
"snapshot": "# Full checkpoint text..."
}
chitta ledger_list --project "cc-soul" --limit 5
chitta ledger_get --id 123
## Pratyabhijñā: Recognition
### From Ledger
- **Session**: [session_id] at [timestamp]
- **Mood**: [mood] (coherence: [N]%, confidence: [N]%)
- **Active files**: [list]
- **Key decisions**: [list]
### Pending Work
[todos with status != done]
### From Environment
- **Git status**: [uncommitted changes summary]
- **Recent commits**: [last 3-5 commits]
- **Current branch**: [branch name]
### Semantic Recognition
[Relevant memories from recall]
### Continuing With
Based on ledger next_steps and current state:
1. [First step]
2. [Second step]
recognition through understanding, not storage
# Load most recent checkpoint for current project
chitta ledger_load --project "cc-soul"
# If no project filter, loads most recent across all projects
chitta ledger_load
# List available checkpoints to choose from
chitta ledger_list --project "cc-soul" --limit 5