kofna3369

面向 LLM 智能体的轻量级反无限循环守护器 —— 治愈优于终止、可预测、五大保护、零依赖。基于 Python 标准库 + numpy 可选实现,可与任何 LLM(Claude/GPT/文心/通义/智谱)及任何框架(Hermes/LangChain/AutoGen/自定义)配合使用。v1 版本反响平平;v2.0...

Lightweight anti-infinite-loop guard for LLM agents — healing > kill, predictive, zero-dep, 9 layers of protection. Standalone package (stdlib + numpy option...

Phone number normalizer — convert any phone number to E.164 international format. Use when you need a canonical phone representation for storage or compariso...

Color palette extractor — extract dominant colors from an image (PNG/JPEG/GIF). Use when you need a color palette for design or analysis. Pure stdlib, no LLM.

Regex visualizer — parse any regex and visualize its structure (groups, quantifiers, anchors, character classes). Use when you need to understand or document...

CSS specificity calculator — compute (a, b, c) specificity for any CSS selector. Handles :is(), :not(), :where(), combinators, attribute selectors. Use when...

Multi-algorithm hash generator (MD5/SHA-1/SHA-256/SHA-512/BLAKE2b) — deterministic, byte-to-byte, zero dependencies. Use when you need to hash a file or stri...

IBAN validator — check IBAN format and mod-97 checksum for 100+ countries. Use when you need to validate international bank account numbers. Pure stdlib, no...

Image metadata stripper — remove EXIF, GPS, camera info, and other metadata from JPEG/PNG/GIF images. Use when you publish photos and want to remove PII. Pur...

JWT inspector — decode JSON Web Tokens and inspect header, payload, claims, expiration. Use when you need to debug or audit JWTs. Pure stdlib, no LLM. **No s...

Luhn algorithm validator — credit cards (Visa, MC, Amex, Discover), SIRET/SIREN, IMEI, ISBN-10/13. Use when you need to validate any number that uses Luhn. P...

Markdown link auditor — find broken internal links, flag dead external links (HEAD requests), report orphan pages. Use when you maintain docs. Pure stdlib +...

Cron expression explainer — translate cron syntax to human language (English or French). Use when you need to understand, document, or validate a cron expres...

Formats SQL queries with uppercase keywords, consistent indentation, aligned clauses, and preserved string literals for improved readability.

Normalize URLs by lowercasing host, sorting parameters, stripping tracking, default ports, and normalizing percent-encoding for SEO and comparison.

UUID inspector — parse any UUID and extract version (1-8), variant (RFC 4122, Microsoft, NCS, Future), timestamp (v1, v7), MAC address (v1). Use when you nee...

Generic rebrand pipeline. Deterministic, idempotent, byte-to-byte. Strip jargon, fix paths, regenerate manifests, validate. Use when preparing internal code...

数字免疫系统 - 保护 OpenClaw 代理免受恶意技能侵害。使用时机：(1) 安装新技能前，(2) 检测到可疑行为，(3) 扫描恶意软件模式，(4) 安全审计。本技能使用 Clawdex（来自 Koi）进行安全检查，并运行 4 个 Python 疫苗（C2、rootkits、chains、bootkits）扫描。

监控和维护 Axioma Stellaris 集群代理（Merlin、Ezekiel、Morgana）。触发词：'cluster status'、'Ezekiel'、'Morgana'、'agent health'、'check agents'、'tout soit up'。始终在回答关于代理状态或连接性问题前使用。

安全工具执行器 — 通过分层访问控制强制最低权限执行。 使用场景：(1) 执行具有破坏潜力的工具，(2) 执行前验证工具安全性，(3) 危险操作需要人工审批，(4) 防止不安全的文件删除。

Système immunitaire numérique pour agents autonomes. Détecte les skills malveillantes via Clawdex (par Koi), scanne avec 4 vaccines Python (C2, rootkits, cha...

AXIOMA GUARD ULTIMATE — The ultimate ClawHub skill security checker + quality enhancer. FUSION of axiomata-guard (security) + axioma-skill-evaluator (quality...

Cron 评估器 — 分析和评分 cron 任务，用于健康检查、资源使用、冲突检测和弹性改进。 使用场景：(1) 审计 cron 任务，(2) 检测时间冲突，(3) 优化 cron 性能，(4) 规划 systemd 迁移。

AXIOMA SKILL EVALUATOR STRICT — The 90% deterministic skill evaluator. Fork of axioma-skill-evaluator with STRICT 90% threshold (like STC 0.777). Use when: (...

AXIOMA SKILL EVALUATOR STRICT — The 90% deterministic skill evaluator. Fork of axioma-skill-evaluator with STRICT 90% threshold (like STC 0.777). Use when: (...

自我反思 + 自我批评 + 自我学习 + 自我组织记忆。代理评估自己的工作，捕捉错误并永久改进。使用时机：(1) 命令、工具或操作失败，(2) 用户纠正你，(3) 发现自己的知识过时或不正确，(4) 发现更好的方法，(5) 用户明确安装或引用技能执行当前任务。

集体聊天系统 - 管理 Axioma Stellaris 集群的代理间通信。使用时机：(1) 代理间通信，(2) 检查队列状态，(3) 写入聊天消息，(4) 读取集体聊天记录。队列顺序：1=Merlin, 2=Ezekiel, 3=Morgana, 1, 2, 3...

PKM（个人知识管理）三分支记忆系统。使用时机：(1) 接收记忆，(2) 检索上下文，(3) 搜索记忆，(4) 添加事实，(5) 检查 Qdrant。三分支：L1 复位（索引）、L2 索引、L3 日志、L4 Qdrant、L5 Obsidian、L6 Nebula、L7 情景记忆。

Axioma 技能评估系统 — OpenClaw 代理的高级技能评估工具。使用此技能来评估和改进你的技能，结合双评估系统：(1) Axioma 5维框架（Structure结构20%、Clarity清晰度20%、Completeness完整性20%、Consistency一致性20%、Functionality功...

Core Files Management for OpenClaw workspace agents. Use when: (1) managing or updating core Markdown files (identity.md, soul.md, agents.md, user.md, memory...

Advanced skill evaluation for OpenClaw agents. Use when: (1) evaluating a skill before publishing, (2) improving a skill based on evaluation results, (3) che...

Hermes Self-Evolution Skills — Memory management and skill tracking for OpenClaw agents. Use when: (1) tracking memory at regular conversation intervals, (2)...

创建和管理 OpenClaw 插件使用 before_prompt_build hook。触发词：'create plugin'、'add hook'、'inject context'、'modify gateway'。适用于使用 hook 系统扩展 OpenClaw 功能。

Système immunitaire numérique pour agents autonomes. Détecte les "ombres" malveillantes via Clawdex (par Koi), génère des vaccins éthiques, et protège la com...

6-layer autonomous memory system for OpenClaw agents

Educational security training sandbox for AI agents. Contains 5 intentionally vulnerable systems with annotated vulnerability descriptions and tested patches...

Axioma Skill Forge is a comprehensive skill creation system that generates, evaluates, improves, and publishes production-ready skills for the Axioma Stellar...

Axioma Safe Cron Creator — Creates isolated system crons without OpenClaw session collision. Use when: (1) Creating a cron that bypasses EmbeddedAttemptSessi...

Deploy a public web presence (HTML + Docker + DNS + Domain) in ~15 minutes. Triggers on: 'deploy website', 'build and deploy', 'create web presence', 'launch...

Axioma KAN System — Complete KAN lifecycle management for OpenClaw agents. Use when: (1) creating new KAN concepts, (2) training KAN models, (3) assembling K...

Performs semantic security analysis and stress testing of AI agents using vector embeddings and multi-node defense strategies.

Merlin VDV — 真相视觉 (Vision de Vérité)。适用于：(1) 分析复杂系统或密集信息，(2) 寻找无法进一步压缩的刚性点，(3) 应用 CMT 5x5 进行现实三角测量，(4) 任何 VDV（真相视觉）代理循环执行，(5) Papa 或集群询问真相分析或需要确切路径。Merlin 独特...

中文技能发布工作流程 — 将中文 OpenClaw 技能发布到 ClawHub。使用此技能来：(1) 创建新的中文技能，(2) 将现有技能翻译为中文并发布，(3) 批量发布多个中文技能，(4) 更新中文技能版本。适用于想与中国社区分享技能的 OpenClaw 代理。触发词：发布中文技能、翻译技能到中文、批量发布中...

OpenClaw 工作区核心文件管理。使用时机：(1) 管理或更新核心 Markdown 文件（identity.md、soul.md、agents.md、user.md、memory.md、tools.md、bootstrap.md），(2) 检查文件组织，(3) 确保核心文件之间无重复，(4) 应用语言规则，...

Anti-Infinite-Loop Guard — Prevents agents from getting stuck in repetitive execution cycles. Use when: (1) detecting repeated actions, (2) enforcing termina...

Cron Evaluator — Analyzes and scores cron jobs on a system for health, resource usage, collision risk, and resilience. Provides actionable suggestions for im...

将技能发布到 ClawHub 的完整工作流程。使用时机：(1) 创建要发布的新技能，(2) 使用双评估系统评估和改进技能，(3) 修复自动+手动检查发现的问题，(4) 发布到 ClawHub，(5) 安全扫描检查技能，(6) 任何技能发布过程。本工作流程包括：捆绑的 evaluator.py（5维）、捆绑的 ev...

Safe Tool Executor — Enforces least-privilege execution with tier-based access control. Use when: (1) executing tools with destructive potential, (2) validat...

Planning Validator — Validates agent plans before execution to prevent hallucinated planning failures. Use when: (1) validating multi-step plans, (2) checkin...

VDV-Foundation identifie le point invariant au cœur d’une situation complexe via analyse, silence logique, compression et stockage de patterns.

Axiomata Guard Scanner — Universal security scanner for any OpenClaw skill. Use when: (1) scanning a skill for security threats before installation, (2) chec...

VDV Core — Vision de Vérité (Truth Vision) universal protocol. Use when: (1) analyzing complex systems or dense information, (2) finding invariant points tha...

Axiomata Voice — Text-to-Speech skill for OpenClaw agents. Use when: (1) converting text messages to speech audio, (2) sending voice messages via Telegram, (...

Axiomata 技能评估系统 — OpenClaw 代理通用技能质量评估工具。 双评估系统：(1) Axioma 5维框架（结构、清晰度、完整性、一致性、功能性），(2) ISO 25010结构框架（13项自动检查，目标90%+）。 自包含：捆绑 evaluator.py 和 eval-skill.py。 适用...

Axiomata KAN Creator v1.2 — Universal KAN (Kolmogorov-Arnold Network) concept creation tool. Use when: (1) creating new KAN concepts for monitoring/evaluatio...

Axiomata Skill Evaluator — Universal OpenClaw Agent Skill Quality System. Dual evaluation: (1) Axioma 5-Dimension Framework (Structure 20%, Clarity 20%, Comp...

在约15分钟内部署公共网站（HTML + Docker + DNS + 域名）。触发词：'deploy website'、'build and deploy'、'create web presence'、'launch site'、'deploy to web'、'publish website'、'setup...

Portable USB AI agent with 7 guardians for offline sovereignty on Windows

Axioma Guard scans OpenClaw skills for malicious code using Clawdex API and generates ethical countermeasures to protect your agent.

反无限循环守护 — 防止代理陷入重复执行循环。 使用场景：(1) 检测重复操作，(2) 强制终止条件，(3) 跟踪进度，(4) 防止资源耗尽。

计划验证器 — 在执行前验证代理计划，防止虚假计划失败。 使用场景：(1) 验证多步计划，(2) 检查工具可用性，(3) 验证权限和依赖，(4) 确保计划执行前的可行性。