28 lines
1.1 KiB
Markdown
28 lines
1.1 KiB
Markdown
---
|
|
name: workspace-memory-curation
|
|
description: Maintain file-based operational memory by deciding what to log, promote, correct, or route into tool behavior across reusable AI workspaces.
|
|
compatibility: opencode
|
|
trigger: always_on
|
|
glob: ""
|
|
---
|
|
|
|
## When To Use
|
|
|
|
Use this skill when new information may change workspace memory, project state, work-item context, people context, decisions, or reusable agent/tool behavior.
|
|
|
|
## Workflow
|
|
|
|
1. Read `core/memory/operational-memory.md`.
|
|
2. Classify the information as daily, state, work-item, stable-context, people, decision, or tooling-behavior.
|
|
3. Update the smallest correct canonical file.
|
|
4. If new information corrects older memory, replace or refine the stale statement instead of appending a contradiction.
|
|
5. If a correction affects future output, update the command, prompt, agent, skill, or knowledge file that controls that behavior.
|
|
6. Keep imported evidence separate from promoted memory.
|
|
|
|
## Output Rules
|
|
|
|
- Report updated files and the memory change.
|
|
- Preserve uncertainty when confidence is mixed.
|
|
- Do not promote tool failures, sync noise, or generic chat chatter as project facts.
|
|
|