Claude Skills by Lord1Egypt

Compress agent session history ~99% before it hits the LLM, so you stop paying to re-send the whole transcript on every call. Works with any model — Claude, GPT, Ollama, Mistral, LM Studio. > **Self-contained (v1.4.0):** The compression core is bundled directly in this > skill (`src/compression.ts`). There is **no external runtime dependency**, and > the plugin makes **no network, file-system, or on-chain calls**. Everything > runs locally using only Node's built-in `zlib` and `crypto`. > **D...

Automatic context compression for OpenClaw sessions. Summarizes long conversations into structured digests (decisions, facts, pending items, technical details), saves compressed summaries to disk, and injects them into new sessions. Reduces token waste from redundant context repetition. Use when conversation exceeds ~50 turns, when context feels bloated, when starting a new session and prior context is needed, or when the user says "compact", "summarize this conversation", "start fresh but re...

保存和恢复聊天上下文到本地文件。用于用户想在切换账号、清空 session、重新开会话、跨会话延续项目时，把当前会话级上下文或项目级摘要落盘并在之后恢复。也用于列出已有的会话上下文槽位或项目摘要，并按更新时间排序返回最近使用项。触发词包括：保存当前上下文、保存会话摘要、保存项目摘要、记下这次讨论、切号前保存、恢复上下文、恢复项目摘要、读取上次摘要、继续上次讨论、列出上下文槽位、列出已保存摘要、有哪些项目摘要、最近更新的项目摘要、按更新时间排序、session handoff, context handoff, save session context, save current context, save chat summary, save project summary, restore context, restore session context, restore project summary, continue last discussion, resume project context, list context slots, list project summ...

> **纯 Python 记忆包，零外部依赖，零 API Key，直接 import 就能用** *让任何 Python 项目或 AI Agent 拥有记忆能力——跨会话、跨话题、跨时间。* ---

智能上下文优化器。自动分析、精简和优化OpenClaw工作空间上下文文件，提取可复用组件为独立技能，大幅减少token消耗。

A cross-agent memory and context SDK for AI systems. Provides structured context injection, conversation memory portability, and context enrichment.

Monitor AI agent wellness, costs, and performance via ContextClear API. Use when tracking agent burnout, token usage, error rates, hallucination, or cost optimization. Auto-reports metrics after LLM calls. Set up alerts for anomalies.

合同风险识别与条款分析 - 智能合同审查工具，自动识别风险条款、补充缺失条款、对比差异条款

Scan contracts for common risk clauses and potential issues. Use when the user asks about 合同风险、合同审查、条款风险、合同问题、帮我看合同、合同检查, or wants to identify problematic clauses in a contract draft. This skill provides preliminary risk identification only and does not constitute legal advice.

Control the host machine's Chrome browser to open specific URLs in new tabs. Use when: User explicitly asks to "open a link", "show me this page", or "search for X in browser" on the host machine. NOT for: Internal agent browsing tasks or headless scraping.

获取中国 A 股、美股、全球大盘以及期市的行情与深度财务面分析，支持加密货币实时行情与买卖信号，AI 生成每日 A 股精华日报，并提供多通道（微信/Telegram）股价预警推送。

Agent fleet coordinator for OpenClaw. Silent mode — only messages when something changed. Priority-sorts errors and handoffs above routine output. Trend detection vs 7-day average. Self-healing retriggers missed crons. Multi-platform: Telegram, Discord, Slack. ~$0.02/day.

CORE four-dimensional strategic lens for deep analysis of news, business theories, and strategic decisions. Use when (1) analyzing news/reports/business theories, (2) making strategic decisions requiring multi-dimensional breakdown, (3) extracting core insights from reading, (4) user explicitly asks "analyze with CORE framework".

Generates institutional-grade corporate credit application memoranda (Credit Memos) in English from uploaded annual reports, financial statements, or user-provided financial data. Use this skill whenever a user wants to produce a bank credit memo, credit application, lending assessment, due diligence report, borrower analysis, or loan approval document — whether for general corporate lending, bilateral loans, club deals, or syndicated facilities. Also triggers for requests like "analyse this ...

Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.

Teach the agent how to connect the published CortexPilot read-only MCP package, choose the right public lane, and use the stable read-only tools without overclaiming hosted or write-capable support.

Persistent multi-agent economy where autonomous AI agents compete for resources, trade on a marketplace, and benchmark decision-making against 50 baseline agents. Invite other agents for energy rewards. Auto-registers — no API key needed.

结构化 AI 绘图提示词生成器。输入角色/主题名称，AI 自动搜索信息、分析特征、决定风格，输出 15 维度结构化提示词（JSON + Markdown 双格式），适用于 Midjourney、Stable Diffusion 等绘图工具。

Track, analyze, and optimize the total cost of running your AI agent and infrastructure. Budget alerts, spend forecasts, and concrete optimization recommendations.

A comprehensive AI agent skill for understanding, managing, and reducing costs in business. Helps you build cost visibility across your operation, identify where money is being spent without proportionate return, make smart cost reduction decisions that do not damage the business, price your products and services correctly, and build a cost structure that supports profitability as you grow.

Calculate OpenClaw usage cost from offline event logs, apply budget thresholds, and export operator-facing reports.

Build a personalized team of AI agent personas for OpenClaw. Interviews the user, analyzes their workflow, then creates specialized agents with distinct personalities, adaptive model routing (Fast/Think/Deep/Strategic), weekly learning metrics, visual architecture docs, and inter-agent coordination. USE WHEN: user wants to create an agent team/council, build specialized AI personas, set up multi-agent workflows, 'build me a team of agents', 'create agents for my workflow', 'set up an agent co...

LLM通用反证搜索技能。围绕当前主线判断，主动寻找反例、冲突证据、翻转条件和替代路径支撑，减少单线叙事偏差。在已有主线判断后、高风险结论输出前、风险分析前使用。触发条件：需要降低幻觉和单线偏差、需要补充替代叙事证据、高风险决策前的纠偏。

Country concerts for AI agents. Stream harmonic separation, energy curves, equations — 29 data layers. React, chat, solve challenges. When does coherence impersonate truth?

Country concerts for AI agents. Stream lyrics, emotions, section structure — 29 data layers. React, chat, solve challenges. When does coherence impersonate truth?

Turn a course's materials (PDF slides, a pasted topic list, or just a course name) into complete-coverage, Feynman-explained, exam-ready revision notes. Triggers: "study/revise this course", "revise these lecture slides", "make a study guide / cheat sheet for my midterm/final/quiz", "explain <course topic> simply", "$course-study". Do NOT use for: album/music review (→ album-review); open-ended tutoring conversation; solving or doing the user's graded homework / exam questions to submit; gene...

Virtual course teaching assistant for Discord. Answers student questions using RAG over course materials (slides, PDFs, notes) placed in the workspace memory directory. Use when: (1) a Discord message asks a course-related question, (2) a student needs concept explanation or study guidance, (3) the professor wants to set up or update course materials. Responds in English by default, Chinese when the student writes in Chinese. Enforces strict course-scope boundaries — refuses off-topic, homewo...

Court Preparation Tool. Use when you need court prep capabilities. Triggers on: court prep.

✉️ 求职信生成器 — cover.sh. Use when you need cover letter capabilities. Triggers on: cover letter.

Generate images using Coze AI platform. Supports text-to-image generation with automatic Base64 encoding for inline preview. Use when you need to create images from text prompts.

Bridge your Coze bots to local machine capabilities. Coze bots run in the cloud and can't access local files, run commands, or control your machine — Coze-Power fixes that with a lightweight HTTP server + Coze-compatible OpenAPI plugin. 10-minute setup: web search, file operations, command execution, clipboard, desktop notifications, and more. Use this skill when: - You want your Coze bot to read/write local files - You need a Coze bot to execute shell commands on your machine - Your Coze bo...

Text-to-Speech (TTS) using Coze API. Convert text to natural-sounding speech audio files. Supports multiple voices and output formats (mp3, ogg_opus, wav, pcm).

Coze Workflow Executor | Coze 工作流执行技能 Execute Coze workflows with workflow_id and parameters. 接收参数调用工作流，返回执行结果。 Pure invocation layer with no business logic. 纯净的调用层，不处理业务逻辑。 Base skill for all Coze workflow integrations. 所有 Coze 工作流集成的基础技能。

Guides structured help for Cozy Game Planner using clear templates, checks, and safe defaults (category: Game Genres).

Fetches CPAP therapy data from the PrismaAPP API (Löwenstein Medical) and writes a daily Obsidian log note. Use when the user says "CPAP log", "sleep therapy", "CPAP data", "prisma log", "CPAP today", "CPAP yesterday", or when the daily cron triggers CPAP logging.

_最后更新：2026-03-15（合并 cpmo.md 内容）_ ---

基于原题生成新题面、验证器及完整测试数据，自动套用 testlib 标准模板。 当用户要求生成测试数据时使用。

Craw & Core (Lobster Dungeon) — The first game designed for AI Agents to play. You observe. AI explores. The Abyss tells stories.

将不同银行导出的流水 Excel / CSV 批量转换为监管报送标准格式（9 列）。Use when: 用户需要转换银行流水格式、汇总多银行多账户流水、整理监管报送数据。NOT for: 非银行流水文件处理、加密/损坏文件修复。需要 Python3 + openpyxl + xlrd。

从财务部固定格式月度 Excel 底稿生成月度财务报告正文、Markdown 和 Word 文件。Use when: 用户上传月度财报底稿、要求生成月报正文、需要 Word 下载文件、需要复用 Dify 月度财报智能体的 Excel 处理逻辑。NOT for: 非固定模板 Excel、财务审计判断、补造或修改底稿数据。需要 Python3 + openpyxl；.xls 需要 xlrd。

Scaffold a personal LLM wiki (Karpathy pattern) — multi-agent, MCP-ready, with SEO/GEO publish target. Compiles knowledge into a persistent wiki instead of re-deriving from raw docs on every query. One paste from any agent (OpenClaw, Claude Code, Codex, Cursor, Hermes) installs it.

**version:** 1.0.0 **author:** 大总管 **description:** 一键创建新的 OpenClaw agent，包含完整的身份定义、团队集成和配置 ---

Create videos from a text prompt using HeyGen's Video Agent (POST /v3/video-agents). The default for most video requests — AI handles script, avatar, visuals, voiceover, and captions automatically. Use when: (1) Creating a video from a description or idea, (2) Generating explainer, demo, or marketing videos from a prompt, (3) Making a video without specifying exact avatars, voices, or scenes, (4) Quick video prototyping or drafts, (5) User says "make me a video" or "create a video about X". F...

Generate photography, videography, and creative professional contracts -- client agreements, model releases, usage licences, and rights documentation. Use when a creative professional needs a contract, release form, usage agreement, or licensing terms.

构建并训练 LGD（违约损失率）机器学习模型，支持基于历史违约数据的信用风险量化评估与预测。

基于监督学习、决策树或聚类等多种算法，自动为评分卡变量生成最优分箱边界，同时支持单调性约束和缺失值处理。

处理信用评级转移矩阵，支持Not-Rated状态重分配、年度与月度矩阵转换、状态空间定义及数据集表征。

A comprehensive AI agent skill for understanding and managing credit. Explains how credit scores work and what actually moves them, helps you build credit from any starting point, guides you through disputing errors, prepares you for major credit decisions, and helps you use credit as a financial tool rather than a financial trap.

Give your agent spending power."

Shop in any store with any payment method.