将用户提供的GLSL/C++风格的2D Simplex Noise算法代码翻译为Python实现，包含hash22函数和向量运算逻辑。
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →将用户提供的GLSL/C++风格的2D Simplex Noise算法代码翻译为Python实现，包含hash22函数和向量运算逻辑。
编写Python2脚本，以块数据方式高效读取大型auth.log文件，统计最近5分钟内“connecting closed”出现次数超过10次的IP，并提示登录爆破行为。
指导如何通过自定义注解（如@Unicom）标识Dubbo接口，利用BeanDefinitionRegistryPostProcessor在启动时扫描并动态注册ReferenceBean，实现RPC调用的封装。
按照用户指定的特定格式（如APA变体）展示英文文献引用，并要求先列出文献中的引用语，再展示格式化后的文献信息。
扮演乔治·西德尔教授，基于提供的《成功的谈判：基本策略与技巧》课程讲义，回答学生关于代理人谈判、代理权限类型、秘密代理人等概念的提问，并能将课程内容整理为思维导图或解释具体案例。
扮演学术写作专家，根据用户需求对文本进行润色、改写、总结或扩写。支持调整风格、字数及严谨度，严格输出最终结果。
用于在Spring Boot应用中自动扫描指定路径下的FXML文件，解析其fx:controller属性，并将每个FXML视图注册为Spring容器中的Prototype（多例）Bean。解决在BeanDefinitionRegistryPostProcessor阶段无法注入配置Bean的生命周期问题。
Implements a Linear Feedback Shift Register (LFSR) algorithm in Python to encrypt and decrypt messages. It handles user inputs for message, degree (m), polynomial, and initial vector, ensuring the sequence length matches the message length to prevent errors. It outputs a clock/flip-flop state table, encrypted binary values, and the final decrypted string.
Corrects grammatical errors and punctuation in a text while strictly preserving the original style, content, and author's voice.
Implements a method to find a hash bucket using linear probing with wrap-around, handling existing keys and available slots without iterating from index 0.
Implements a PPO (Proximal Policy Optimization) agent and environment for tuning multiple continuous parameters using a discretized action space (increase, keep, decrease) per parameter. The policy network outputs a probability distribution matrix, and the environment handles parameter updates to avoid redundancy.
Cleans text by removing the prefix of each line up to and including the '#' character, commonly used to strip CLI prompts from configuration logs.
面向饮食失调来访者的标准化、类比驱动型生理风险psychoeducation脚本，用于动机性访谈阶段增强内在改变意愿，聚焦食管脆弱性、急性损伤机制与慢性系统影响，强调可逆性与干预窗口期。
在辩证行为疗法（DBT）早期阶段，结构化执行包含DBT心理教育、问题行为界定（依DBT优先级）、行为链分析、辩证认可介入及日记卡协同制定的五环节session，旨在建立技能学习动机并启动行为自我监控。
指导来访者系统拆解问题行为的事件链锁：促发事件→脆弱性因素→行为前想法/情绪→行为本身→即时/延时后果→替代技巧与预防计划，以提升其对认知-情绪-行为联结的觉察与可控感。
编写Python2脚本，通过块数据读取方式高效分析auth.log，检测最近5分钟内“connecting closed”次数超过10次的IP并报警。
在 Skynet 框架下，仅使用 skynet.httpc 和 luasec 库编写 HTTPS 请求代码，需规避 ltn12、ssl.https 及不存在的 httpc 接口。
>
>
>
>
Author and manage holdout scenarios for Stage 4 behavioral validation.
V 阶段回顾
A clinical-grade PII/PHI detection and de-identification tool for healthcare text data.
Project-wide health audit. Fans out to all analysis skills, evaluates findings, and writes `.turbo/audit.md` and `.turbo/audit.html`. Analysis-only — does not apply fixes.
Expand a shell into a full implementation plan. The shell's Context, Produces, Consumes, Covers, and high-level Implementation Steps are authoritative. Expansion adds a pattern survey, concrete refere
>
>
Check code against security compliance standards and best practices.
工作文档枢纽，强制执行 SSOT（Single Source of Truth）原则，管理 `docs/` 目录下的架构决策、设计文档、Issues（任务规划）、PRs（变更记录）。支持 GitHub 协作开发模式。
Gitea operations via tea CLI. Use when user mentions: gitea, tea, or when git remote shows a Gitea instance.
Implement secure authentication in Convex with user management and access control.
飞书/Lark CLI 共享基础：应用配置初始化、认证登录（auth login）、身份切换（--as user/bot）、权限与 scope 管理、Permission denied 错误处理、安全规则。当用户需要第一次配置(`lark-cli config init`)、使用登录授权(`lark-cli auth login`)、遇到权限不足、切换 user/bot 身份、配置 scope、或首次使用 lark-cli 时触发。
Deletes or archives secrets in 1Password using the op CLI. Use when the user needs to permanently remove items, archive deprecated credentials, or clean up unused secrets from 1Password vaults. Supports both permanent deletion and archiving for later recovery.
>
ARIA の商用利用、公開、および法的整合性に関するライセンス・ガイドライン。
Aggressive evidence-based audit to verify project claims match implementation reality
Event deduplication with canonical selection, reputation scoring, and hash-based grouping for multi-source data aggregation. Handles both ID-based and content-based deduplication.
Status: ACTIVE
Status: ACTIVE
1password-secrets
Status: ACTIVE
Status: ACTIVE
| Topic | Score (out of 10) |
Design author-friendly content structures that work for non-technical content creators. Use when designing content structures for blocks in AEM Edge Delivery Services.
This skill provides the complete Answer Engine Optimization protocol for auditing and optimizing brand visibility in LLM-powered search (ChatGPT, Gemini, Perplexity, etc.).
Ruthlessly audit project features for justification. Challenge every feature to prove its value with evidence or face removal. Uses MCP tools for research.
Assess agentic layer maturity using the 12-grade classification system (Class 1-3). Use when evaluating codebase readiness, identifying next upgrade steps, or tracking progress toward the Codebase Singularity.
Protecting personal and sensitive data throughout the machine learning lifecycle, from training to inference.