// Compress a long agent conversation into a nine-part continuation summary that preserves request, files, errors, user messages, current work, and the next aligned step.
Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.
Build a lightweight proactive mode with scheduled checks, sleep intervals, concise user briefs, and expiry safeguards so an agent can work in the background without becoming an uncontrolled daemon.
Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.
Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw exploration.
Run a read-only verification pass after implementation to check whether completion claims are real, validation actually ran, and obvious edge cases or regressions were missed.
| name | structured-context-compressor |
| description | Compress a long agent conversation into a nine-part continuation summary that preserves request, files, errors, user messages, current work, and the next aligned step. |
Use this skill when a free-form summary is too lossy and you need a reliable continuation artifact.
Render the standard template:
python3 {baseDir}/scripts/render_template.py
Then apply the prompt in references/prompt-template.md.
Preserve all user messages or an accurate equivalent. Do not compress away the corrections that changed the direction of work.
python3 {baseDir}/scripts/render_template.py