Menu
生产级长期记忆系统 v5.0，支持 L2→L1/L0 自动分层与智能摘要提取
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Generate and critically evaluate grounded improvement ideas for the current project. Use when asking what to improve, requesting idea generation, exploring surprising improvements, or wanting the AI to proactively suggest strong project directions before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on this project', 'surprise me with improvements', 'what would you change', or any request for AI-generated project improvement suggestions rather than refining the user's own idea.
Create structured plans for any multi-step task -- software features, research workflows, events, study plans, or any goal that benefits from structured breakdown. Also deepen existing plans with interactive review of sub-agent findings. Use for plan creation when the user says 'plan this', 'create a plan', 'write a tech plan', 'plan the implementation', 'how should we build', 'what's the approach for', 'break this down', 'plan a trip', 'create a study plan', or when a brainstorm/requirements document is ready for planning. Use for plan deepening when the user says 'deepen the plan', 'deepen my plan', 'deepening pass', or uses 'deepen' in reference to a plan.
[BETA] Execute work with external delegate support. Same as gh:work but includes experimental Codex delegation mode for token-conserving code implementation.
Execute work efficiently while maintaining quality and finishing features
Refresh stale or drifting learnings and pattern docs in docs/solutions/ by reviewing, updating, consolidating, replacing, or deleting them against the current codebase. Use after refactors, migrations, dependency upgrades, or when a retrieved learning feels outdated or wrong. Also use when reviewing docs/solutions/ for accuracy, when a recently solved problem contradicts an existing learning, when pattern docs no longer reflect current code, or when multiple docs seem to cover the same topic and might benefit from consolidation.
Document a recently solved problem to compound your team's knowledge or update CONCEPTS.md, the project's shared domain vocabulary.
| name | hkt-memory |
| description | 生产级长期记忆系统 v5.0，支持 L2→L1/L0 自动分层与智能摘要提取 |
| triggers | ["memory","recall","store","retrieve"] |
自动分层存储：L2 写入后触发 L1/L0 生成
核心闭环：存储 → 分层提取 → 检索
| 触发条件 | 动作 |
|---|---|
| 用户要求“记住/存档/沉淀”偏好、决策、约束 | 执行 store --layer all，自动写入三层 |
| 需要回忆历史上下文 | 执行 retrieve --layer all |
| 需要按主题聚合信息 | 执行 store/retrieve --topic <topic> |
| 需要全量重建索引与摘要 | 执行 sync --full |
| 需要检查健康状态 | 执行 stats |
cd .claude/skills/hkt-memory
bash install.sh
uv run scripts/hkt_memory_v5.py store \
--content "用户偏好使用 Python" \
--title "开发偏好" \
--topic "preferences" \
--layer all
uv run scripts/hkt_memory_v5.py retrieve \
--query "Python 偏好" \
--layer all
uv run scripts/hkt_memory_v5.py store --content "..." --layer all
uv run scripts/hkt_memory_v5.py retrieve --query "..." --layer all
uv run scripts/hkt_memory_v5.py sync --full
uv run scripts/hkt_memory_v5.py stats
uv run scripts/hkt_memory_v5.py test
## 记忆集成 (HKT-Memory v5.0)
对话前检索:
uv run scripts/hkt_memory_v5.py retrieve --query "<当前话题>" --layer all --limit 3
对话后存储:
uv run scripts/hkt_memory_v5.py store --content "<关键决策>" --title "<标题>" --layer all
当前版本: v5.0