From cc-harness
Extracts durable memories from recent conversation turns into user, feedback, project, and reference categories, avoiding stale code-state facts. Use to persist collaboration context like user preferences and project constraints.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cc-harness:memory-extractorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when you want to persist durable collaboration context from the latest conversation turns.
Use this skill when you want to persist durable collaboration context from the latest conversation turns.
Build a manifest of existing memories:
python3 {baseDir}/scripts/memory_manifest.py --memory-root /path/to/memory
Then use the portable prompt in references/prompt-template.md.
userfeedbackprojectreferencepython3 {baseDir}/scripts/memory_manifest.py ...npx claudepluginhub learnprompt/cc-harness-skills --plugin cc-harnessPersists learnings into a 5-layer memory hierarchy (CLAUDE.md files, memory/MEMORY.md) and consolidates by pruning outdated entries and promoting recurring patterns. Triggers on 'extract learnings', 'remember', 'dream'.
Saves durable facts, decisions, and preferences to the memini memory service. Automatically invoked when the user says 'remember this' or after discovering root causes, making architectural decisions, or learning project conventions.
Persists facts, preferences, constraints, project decisions across conversations via a memory backend. Recall automatically when starting new sessions or facing recurring issues.