lobster-attachment-inject动态附件注入 — 在不修改system prompt的情况下注入动态内容。参考Claude Code的Attachment消息机制。
Install via ClawdBot CLI:
clawdbot install wangxiaofei860208-source/lobster-attachment-injectGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated May 23, 2026
Users mention specific tasks (e.g., 'debug this code'), which triggers the injection of skill descriptions from a registry, enabling the AI to selectively load and apply relevant skills without bloating the system prompt.
A user request involving multiple agents (e.g., 'plan and assign tasks') reads agent registry files to identify and delegate to appropriate agents, maintaining context across sessions with minimal token overhead.
In extended customer support chats, the system injects a compact registry of past memories and skills at session start, allowing dynamic updates without cache invalidation, reducing costs and improving response time.
An IDE plugin uses attachment injection to pull in relevant code review or testing skill descriptions only when the developer works on specific files, avoiding prompt pollution and preserving context.
Offer a premium API subscription that uses this attachment injection technique to reduce token consumption by up to 40%, passing cost savings to customers while maintaining response quality.
Create a marketplace where third-party skills are listed in registries; the platform charges a listing fee and takes a commission per activation (dynamic injection call), enabling granular monetization.
License the attachment injection middleware to enterprises running custom LLM instances, helping them reduce operational costs and improve responsiveness in multi-agent setups.
💬 Integration Tip
Start by generating registries for your existing skills and agents using the provided scripts, then modify your system prompt to include injection points for lightweight dynamic references.
Scored May 23, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.