Agent skills for AI coding assistants (Antigravity)
概览
Give your AI assistant deep understanding of the plugin's architecture, retrieval pipeline, and configuration system — enabling efficient maintenance and feature development of this OpenClaw long-term memory plugin. This is an — a structured knowledge package designed for AI coding assistants to maintain and upgrade the memory-lancedb-pro OpenClaw plugin. When an AI coding assistant loads this skill, it gains comprehensive understanding of the plugin, including: - 🏗️ — Responsibilities, exports, and relationships of all 12 source files - 🔍 — RRF fusion, cross-encoder reranking, exact math formulas for 6 scoring stages - 💾 — LanceDB schema, FTS indexing, CRUD operation implementations - 🔐 — 5 scope types, access control logic - 🛠️ — Step-by-step guides for 7 common development scenarios - 🐛 — Installation, configuration, retrieval quality tuning, development pitfalls Clone this repo into the Antigravity skills directory: The skill auto-triggers when you work on: 1.
README
What Is This?
This is an Agent Skill — a structured knowledge package designed for AI coding assistants to maintain and upgrade the memory-lancedb-pro OpenClaw plugin.
When an AI coding assistant loads this skill, it gains comprehensive understanding of the plugin, including:
- 🏗️ Plugin Architecture — Responsibilities, exports, and relationships of all 12 source files
- 🔍 Retrieval Pipeline — RRF fusion, cross-encoder reranking, exact math formulas for 6 scoring stages
- 💾 Storage Layer — LanceDB schema, FTS indexing, CRUD operation implementations
- 🔐 Scope System — 5 scope types, access control logic
- 🛠️ Development Workflows — Step-by-step guides for 7 common development scenarios
- 🐛 Troubleshooting — Installation, configuration, retrieval quality tuning, development pitfalls
File Structure
memory-lancedb-pro-skill/
├── SKILL.md # Main skill file (architecture, workflows, design decisions)
├── references/
│ ├── retrieval_pipeline.md # Retrieval pipeline deep dive
│ ├── storage_and_schema.md # Storage layer & data model
│ ├── embedding_system.md # Embedding system (providers, caching, task-aware)
│ ├── plugin_lifecycle.md # Plugin lifecycle & configuration
│ ├── scope_system.md # Multi-scope isolation system
│ ├── tools_and_cli.md # Agent tools & CLI commands
│ └── troubleshooting.md # Common issues & troubleshooting
├── README.md # This file
└── README_CN.md # 中文 README
How to Use
Option A: As an Antigravity Agent Skill (Recommended)
Clone this repo into the Antigravity skills directory:
git clone https://github.com/win4r/memory-lancedb-pro-skill.git \
~/.gemini/antigravity/skills/memory-lancedb-pro
The skill auto-triggers when you work on:
- Developing new features or fixing bugs in memory-lancedb-pro
- Modifying the retrieval pipeline (vector search, BM25, RRF fusion, reranking, scoring stages)
- Adding or changing embedding providers
- Updating scope/access control logic
- Modifying agent tools or CLI commands
- Troubleshooting memory quality issues (noise, duplicates, low recall)
- Working on the JSONL session distillation pipeline
- Migrating data between memory backends
- Understanding the plugin’s architecture to plan enhancements
Option B: As Standalone Reference Documentation
Read SKILL.md and the files under references/ directly for complete technical details about the plugin.
Knowledge Coverage
| Domain | Coverage |
|---|---|
| Retrieval Pipeline | RRF fusion formula, 3 rerank provider adapters, exact formulas for Recency Boost / Importance Weight / Length Norm / Time Decay / Hard Min / MMR scoring stages |
| Storage Layer | LanceDB table schema, FTS index creation with race condition handling, vector/BM25 search impl, full CRUD API signatures |
| Embedding System | 4 provider configs (Jina/OpenAI/Gemini/Ollama), task-aware API, LRU cache (256 entries, 30min TTL), model dimension lookup table |
| Plugin Lifecycle | Component init order, 3 lifecycle hook implementations (auto-recall/auto-capture/session memory), service registration, daily backup |
| Scope System | 5 scope types, default vs explicit access control, complete ScopeManager API |
| Tools & CLI | 6 agent tool parameter tables, all CLI command examples, 2 JSONL distillation approaches |
| Troubleshooting | 12 common issues with solutions, retrieval quality tuning knobs, development pitfalls (Arrow Vectors, config inconsistencies, env var timing) |
Design Philosophy
This skill follows the progressive disclosure principle:
- SKILL.md (~10KB) serves as overview and router — always loaded
- 7 reference files (~45KB) loaded on-demand — only when the AI needs a deep dive into a specific subsystem
- Total: ~55KB of structured technical documentation covering 1,400+ lines of distilled knowledge
License
MIT
推荐工具
换一个关键词，或者移除筛选条件。
安装
npx skillfish add win4r/memory-lancedb-pro-skill