OpenParable
Skip to content
← Back to skills

Distill Pending

Documents
distill-pending

Distill Pending is an Agent Skill for documents published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Process pending transcript distillation

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/workflow/distill-pending/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/distill-pending, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Distill Pending Sessions

Trigger distillation of pending transcripts and check distillation status.

How Distillation Works

  1. Automatic: The daemon distills transcripts every 5 minutes (configurable)
  2. On Compaction: PreCompact hook triggers immediate distillation before context is lost
  3. On Session Start: SessionStart hook triggers distillation of any pending work

Manual Trigger

If you need to manually trigger distillation for the current session:

# Add to queue for daemon processing
echo '{"tool":"distill_trigger","args":{"session_id":"CURRENT_SESSION_ID"},"ts":'$(date +%s)'}' >> /tmp/chitta-queue.jsonl

Check Distillation Status

View registered transcripts and their distillation state:

chitta transcript_list

This shows:

  • session_id: Transcript identifier
  • last_processed_line: How many lines have been distilled
  • distilled: Whether any distillation has occurred
  • realm: Project context

Distillation Output

Distilled learnings are stored as memories with:

  • [learn] prefix for extracted insights
  • SSL format for efficient storage
  • Connected via triplets for graph navigation

Configuration

Daemon distillation settings (in chittad --help):

  • --distill-interval MINS: Check interval (default: 5)
  • --distill-min-turns N: Min turns before distilling (default: 4)
  • --distill-model MODEL: LLM model for extraction
  • --no-distill: Disable automatic distillation

Troubleshooting

If distillation isn't running:

  1. Check daemon is running: chitta health_check
  2. Check opencode is available: which opencode
  3. Check transcript is registered: chitta transcript_list
  4. Check queue is being processed: ls -la /tmp/chitta-queue.jsonl*