summarization

# Summarization ## Purpose / When to Activate Activate when: - Session memory grows large - Decisions accumulate across sessions - Project context becomes fragmented - Memory retrieval returns too many files - Token usage increases noticeably This skill is both preventive and corrective. --- ## Process **Step 0: Enumerate categories.** Read `contexts/memory/index.md`. List all registered categories. For each category, assess whether summarization is warranted: trigger if >5 files in the category OR estimated token count >5000 tokens OR memory-retrieve is returning too many results for this category. Skip categories that do not meet any threshold. For each category that meets the threshold: 1. **Identify durable information** — extract confirmed decisions, stable constraints, validated assumptions, current priorities, key outcomes, known risks. Ignore brainstorming noise, intermediate reasoning, abandoned ideas. 2. **Compress into structured summary** — use the template below. Prefer bullets over prose. 3. **Archive raw memory** — move original files to `contexts/memory/archive/{category}-{YYYY-MM-DD}.archive.md`. Concatenate multiple files from the same category into a single archive file. Only summaries remain active. 4. **Update memory index** — record new summary files, archived sources, affected categories. --- ## Summary File Template ```markdown # {Category} — Summary > Summarized from {N} files on {YYYY-MM-DD} > Compression: ~{original_tokens} → ~{summary...