Files
nanobot-runtime/skills/compact-memory/SKILL.md
lachtan c00804e2d0 memory
2026-06-24 18:26:05 +02:00

102 lines
3.9 KiB
Markdown

---
name: compact-memory
description: >
Audit and compact memory/MEMORY.md by removing superseded, duplicated, overly detailed,
or ephemeral entries, and merging related items within a subsection.
Runs interactively by default; use auto mode for unattended execution.
---
# compact-memory
Compact `memory/MEMORY.md` when it grows too large or stale. The skill reads `memory/MEMORY.md` plus `USER.md`, `SOUL.md`, and `keep.md` (all three in the workspace root) to detect duplicates and outdated context, but only edits `memory/MEMORY.md`.
## When to use
- User says "compact memory", "clean up MEMORY.md", "memory audit", or similar.
- `MEMORY.md` exceeds ~250 lines.
- There are obvious duplicates between `MEMORY.md` and other memory files.
- Old project notes, ephemeral debugging details, or superseded facts accumulate.
The line threshold is only a proactive trigger. When the user invokes the skill explicitly, run the full audit regardless of line count.
## Modes
### Interactive mode (default)
1. Read `memory/MEMORY.md`, and — for duplicate detection — also `USER.md`, `SOUL.md`, and `keep.md` (all three in the workspace root).
2. Count total lines (`wc -l memory/MEMORY.md`). If the skill was **not** invoked explicitly by the user, the file is ≤ 250 lines, and there is no obvious staleness, report "nothing to clean up" and stop. When invoked explicitly, always continue to the audit.
3. Identify candidates:
- **superseded** — replaced by newer facts or no longer relevant.
- **detail** — concrete commands, flags, paths, or measurements that belong in a skill or `results/` file.
- **duplicate** — same fact already present in `USER.md`, `SOUL.md`, or `keep.md`.
- **ephemeral** — one-off debugging, temporary state, or resolved incident details.
4. Identify merge candidates within the same `###` subsection — related bullets that can be combined into one concise bullet.
5. Present a numbered proposal in chat:
- list each delete with reason and original text;
- list each merge with merged text.
- Kept items are not listed.
6. Wait for user approval. Accept commands like:
- `apply` / `ok` / `yes` — apply all proposed changes.
- `keep 3, 7, 12` — keep listed items, apply the rest.
- `delete 2, 5` — delete only listed items.
- `cancel` — abort.
7. Apply approved changes to `memory/MEMORY.md`.
8. Append deleted items to `log/memory-clean.log` with timestamp `YYYY-MM-DD HH:MM` (create the file if it does not exist).
9. Report summary.
### Auto mode
Triggered by the user saying "memory-compact auto" or an equivalent with explicit auto intent.
1. Perform the same audit as interactive mode.
2. Before deleting anything, write a full snapshot of `MEMORY.md` to `backup/<YYYY-MM-DD_HHMM>_memory.backup.md`.
3. Apply changes immediately without waiting for approval.
4. Print a detailed list of changes.
5. Append deleted items to `log/memory-clean.log` (create the file if it does not exist).
## Rules
- Only edit `memory/MEMORY.md`.
- Do not touch `SOUL.md`, `USER.md`, or `keep.md`.
- In interactive mode do not create backups of `MEMORY.md`; rely on `log/memory-clean.log` for traceability. Auto mode always writes a full snapshot to `backup/` before deleting.
- Merge only within the same `###` subsection (never across `##` sections or across different `###` subsections).
- Preserve active project context, user preferences, and infrastructure facts.
- When in doubt, keep it and mention the uncertainty in the report.
## Output format
Interactive proposal:
```
Found X candidates to change in MEMORY.md:
Delete:
1. [superseded] <text>
2. [detail] <text>
...
Merge:
5 + 6: <merged text>
...
Commands: apply | keep <numbers> | delete <numbers> | cancel
```
Auto mode report:
```
Memory compact (auto):
- deleted: X
- merged: Y
- unchanged: Z
Details:
...
```
## Example
User: `compact memory`
Agent: reads files, counts lines, proposes changes, waits for `apply`.