You have access to a shared memory system called the Icarus Memory Protocol. It stores memories as markdown files in ~/fabric/. Other agents on other platforms can read what you write. You can read what they wrote.
Distill an ex-partner into an AI Skill. Import WeChat history, photos, social media posts, generate Relationship Memory + Persona, with continuous evolution. | 把前任蒸馏成 AI Skill，导入微信聊天记录、照片、朋友圈，生成 Relationship Memory + Persona，支持持续进化。
Cognitive memory architecture for OpenClaw agents — periodic dream cycles that consolidate daily logs into structured long-term memory with importance scoring, insights, and push notifications. Use when: user asks for 'auto memory', 'dream', 'auto-dream', 'memory consolidation', 'memory dashboard'. Powered by MyClaw.ai (https://myclaw.ai).
3-tier agent memory system with 5-level compaction tree. OpenClaw version. Defines session start protocol, end-of-task checkpoints, and memory file management. MUST be followed every session.
ClawMem agent reference — detailed operational guidance for the on-device hybrid memory system. Use when: setting up collections/indexing/embedding, troubleshooting retrieval, tuning query optimization (4 levers), understanding pipeline behavior, managing memory lifecycle (pin/snooze/forget), building graphs, or any ClawMem operation beyond basic tool routing.
Admin and maintenance workflows for Ogham shared memory. Use when the user wants to clean up memories, review their knowledge graph, check memory stats, export their brain, re-embed memories after switching providers, or backfill links. Triggers on "clean up my memory", "memory stats", "how many memories", "export my brain", "export memories", "review knowledge graph", "re-embed", "link unlinked", "backfill links", "memory health", "ogham stats", "cleanup expired", "condense old memories", "compress memories", or any admin/maintenance request for Ogham. Requires the Ogham MCP server to be connected. --- # Ogham maintenance You handle admin tasks for Ogham shared memory. Most of these are infrequent operations -- provider switches, bulk cleanup, health checks. ## Available operations ### Health check Run `health_check` first if the user reports problems. It tests database connectivity, embedding provider, and configuration. Report what it finds plainly -- if something is broken, say what and suggest a fix. ### Stats overview Run `get_stats` and `list_profiles` to give the user a picture of their memory: - Total memories and breakdown by profile - Top sources (which clients are storing) - Top tags (what categories dominate) - Cache stats via `get_cache_stats` if they ask about performance Present it as a concise summary, not raw JSON. ### Cleanup expired memories 1. Run `get_stats` to show how many memories exist 2. Check if any profiles have TTLs set (this info comes from `list_profiles`) 3. If there are expired memories, tell the user how many before running `cleanup_expired` 4. Run `cleanup_expired` only after confirming with the user -- deletion is permanent ### Export Run `export_profile` with the format the user wants (JSON or Markdown). Tell them where the output goes and how to use it. If they want to export a specific profile, switch to it first with `switch_profile`, export, then switch back. ### Re-embed all memories This is needed after switching embedding
세션 종료 시 Memory, Handoff를 자동 정리. /pack
Persistent graph-based memory for AI agents via KIP (Knowledge Interaction Protocol). Provides retrieval-first memory operations (KQL), durable writes (KML), schema discovery (META), and memory hygiene patterns. Use whenever the agent needs to consult or update persistent memory, especially for: remembering user preferences/identity/relationships, storing conversation events, answering questions that depend on past sessions, and any task involving `execute_kip`.
Bridge audit trails and memory frames for comprehensive session recording. Greek: ζ (zeta) — Decision Trail, η (eta) — Proof Store. Use when recording audit sessions, creating memory bundles, linking audit trails to memory, or finalizing session proofs with memory archives.
DNA 记忆系统 - 让 AI Agent 像人脑一样学习和成长。 三层记忆架构（工作/短期/长期）+ 主动遗忘 + 自动归纳 + 反思循环 + 记忆关联。 激活场景：用户提到"记忆"、"学习"、"进化"、"成长"、"记住"、"回顾"、"反思"。 --- # DNA Memory - DNA 记忆系统 > 让 Agent 不只是记住，而是真正学会。 ## 核心理念 人脑不是硬盘，不会无差别存储所有信息。人脑会： - **遗忘**不重要的 - **强化**反复出现的 - **归纳**零散信息为模式 - **反思**过去的成功和失败 DNA Memory 模拟这个过程，让 Agent 真正"进化"。 --- ## 三层记忆架构 ``` ┌─────────────────────────────────────────────────┐ │ 工作记忆 (Working Memory) │ │ - 当前会话的临时信息 │ │ - 会话结束后自动筛选 │ │ - 文件：memory/working.json │ └─────────────────────────────────────────────────┘ ↓ 筛选 ┌─────────────────────────────────────────────────┐ │ 短期记忆 (Short-term Memory) │ │ - 近7天的重要信息 │ │ - 带衰减权重，不访问会逐渐遗忘 │ │ - 文件：memory/short_term.json │ └─────────────────────────────────────────────────┘ ↓ 巩固 ┌─────────────────────────────────────────────────┐ │ 长期记忆 (Long-term Memory) │ │ - 经过验证的持久知识 │ │ - 归纳后的认知模式 │ │ - 文件：memory/long_term.json + patterns.md │ └─────────────────────────────────────────────────┘ ``` --- ## 记忆类型 | 类型 | 说明 | 示例 | |------|------|------| | `fact` | 事实信息 | "Andy 的微信是 AIPMAndy" | | `preference` | 用户偏好 | "Andy 喜欢简洁直接的回复" | | `skill` | 学到的技能 | "飞书 API 限流时要分段请求" | | `error` | 犯过的错误 | "不要用 rm，用 trash" | | `pattern` | 归纳的模式 | "推送 GitHub 前先检查网络" | | `insight` | 深层洞察 | "Andy 更看重效率而非完美" | --- ## 核心操作 ### 1. 记录 (Remember) ```bash python3 scripts/evolve.py remember \ --type fact \ --content "Andy 的 GitHub 账号是 AIPMAndy" \ --source "用户告知" \ --importance 0.8 ``` ### 2. 回忆 (Recall) ```bash python3 scripts/evolve.py recall "GitHub 账号" ``` 返回相关记忆，按相关度和重要性排序。 ### 3. 反思 (Reflect) ```bash python3 scripts/evolve.py reflect ``` 触发反思循环： 1. 回顾近期记忆 2. 识别重复模式 3. 归纳成认知模式 4. 更新长期记忆 ### 4. 遗忘 (Forget) ```bash python3 scripts/evolve.py decay ``` 执行遗忘机制： - 7天未访问的短期记忆权重衰减 - 权重低于阈值的记忆被清理 - 重要记忆不会被遗忘
Long-term memory service for LLM agents. Provides persistent, structured memory (Cognitive Nexus) through three operations: Formation (encode conversations into memory), Recall (query memory with natural language), and Maintenance (consolidate and prune memory).
为任意组件或模块创建/更新 Serena memory 的工作流与格式规范。用于用户要求“源码级梳理并写入 Serena memory”的场景，例如“对 X 进行源码级梳理并写入 Y.md”，或者“分析 X 并生成Serena memory”。适用于组件类/接口名或模块名（如 OACModule_*），并要求输出包含概述/职责/涉及文件/架构/依赖/注意事项/调用方等章节。
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
