发现 Skills

The English Lesson Planning Skill is a production-grade Hermes Skill designed for teachers' lesson preparation. Grade, semester, unit, knowledge points and difficulty are passed in as parameters. Workflow: teacher_english_lesson_planning.run.

Use this skill when the user asks to 'test for directory traversal', 'exploit path traversal vulnerabilities', 'read arbitrary files through web applications', 'find LFI vulnerabilities', or 'access files outside web root'. It provides comprehensive file path traversal attack and testing methodologies.

Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".

Collaborate with Codex (GPT-5.2) via named sessions. Trigger: user asks to work with Codex, use Codex, ask Codex, involve Codex, etc. CRITICAL: Use subcodex CLI via Bash, NOT the Task subagent tool.

Ontology-based entity discovery and validation for mnemonic memories. Define custom namespaces, entity types, traits, and relationships. Triggers: "entity discovery", "validate ontology", "define namespaces", "resolve entity references", "list ontologies", "show namespaces", "entity types", "entity relationships", "traits", "discovery patterns", "cognitive memory types"

Track, analyze, and optimize sports betting activity across sportsbooks. Manage accounts, log bets of all types (straight, parlay, teaser, round robin, futures, props), settle outcomes, surface cognitive biases, and query live odds — all through a REST API designed for AI agents.

Generate and review Java code using patterns and best practices from Joshua Bloch's "Effective Java" (3rd Edition). Use this skill whenever the user asks about Java best practices, API design, object creation patterns, generics, enums, lambdas, streams, concurrency, serialization, method design, exception handling, or writing clean, maintainable Java code. Trigger on phrases like "Effective Java", "Java best practices", "builder pattern", "static factory", "defensive copy", "immutable class", "enum type", "generics", "bounded wildcard", "PECS", "stream pipeline", "optional", "thread safety", "serialization proxy", "checked exception", "try-with-resources", "composition over inheritance", "method reference", "functional interface", or "Java API design."

Expert knowledge of the Skyline HTTP API for managing multi-port gateway devices with SMS, MMS, call handling, and eSIM capabilities. Use when working with SMS/MMS sending and receiving, device command control, call and SMS statistics, port status monitoring, eSIM management, IMEI/SIM number configuration, and building automation scripts for Skyline devices. Helps explain API endpoints, write scripts, debug responses, and guide through multi-step operations. Credentials load from environment variables (SK_HOST, SK_USERNAME, SK_PASSWORD, SK_PORT).

博主技能：输入抖音博主链接，选择深度（萃取/提纯/精馏/全馏），自动下载视频→OCR+视觉分析→提炼创作心法。

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

自更新 skills。记录用户反馈，更新方法论和规则。触发词：更新规则、记录反馈、改进skill

A quick-start guide for IT teams at any level of government who just received ChatGPT access | Part of naiba-openai-work-assistant

Blind-box toy / designer toy series design generator. Supports character consistency assurance, pose diversity, rich scene backgrounds, and professional lighting. Use cases: when a user wants to design a blind-box series, collectible designer toys, plush charms, or acrylic standees. Keywords: blind box design, designer toy, vinyl figure, collectible toy, chibi, character anchor points, group and single-character consistency

Apply published, peer-reviewed polygenic score weights from the PGS Catalog to target genotypes, with multi-trait scoring and ancestry-stratified reporting. Use when you need PRS without re-fitting weights from raw GWAS summary statistics.

Next.js 15 애플리케이션을 위한 프론트엔드 개발 가이드라인. React 19, TypeScript, Shadcn/ui, Tailwind CSS를 사용한 모던 패턴. Server Components, Client Components, App Router, 파일 구조, Shadcn/ui 컴포넌트, 성능 최적화, TypeScript 모범 사례 포함. 컴포넌트, 페이지, 기능 생성, 데이터 페칭, 스타일링, 라우팅, 프론트엔드 코드 작업 시 사용.

Generate branded banners and publish Markdown articles to X (Twitter) Articles editor. Use when user wants to publish an article to X, generate a banner image, or convert markdown for publishing. Handles: banner generation (fal.ai + HTML/Playwright), markdown parsing into sequential steps, and step-by-step browser automation.

Fast X Intelligence CLI (Rust) — search, analyze, and engage on X/Twitter from the terminal. Use when: (1) user says 'x research', 'search x for', 'search twitter for', 'what are people saying about', 'what's twitter saying', 'check x for', 'x search', 'search x', (2) user wants real-time monitoring with 'watch', (3) user needs AI-powered analysis with Grok ('analyze', 'sentiment'), (4) user needs intelligence reports ('report'), (5) user wants to track followers ('diff'), (6) user needs trending topics ('trends'). Also supports: bookmarks, likes, following (OAuth), x-search, collections, CSV/JSON/JSONL export. Non-goals: Not for posting tweets, not for DMs, not for enterprise features.

Design phishing and social engineering simulations with explicit authorization and measurable outcomes.

Correlate scanner results with CVE and exploit intelligence and prioritize by CVSS and exploitability.

Scaffolds Python configuration infrastructure: Pydantic models, YAML loading, environment variable overrides. Use when creating config systems, adding config fields, or migrating from hardcoded values to validated config. Recognizes: "config-builder", "add config", "pydantic config", "yaml config", "env vars", "configuration management", "validated settings", "config infrastructure"

pytest patterns, fixtures, mocking, parametrize, and property-based testing. Use when writing tests, improving coverage, or setting up test infrastructure. Recognizes: "testing-patterns", "write tests", "pytest patterns", "how to mock", "test fixtures", "parametrize", "property-based testing", "test organization", "improve coverage", "hypothesis tests"

Execute the implementation planning workflow using the plan template to generate design artifacts. Produces research, data models, API contracts, and blueprint.md.

Use the Nutrient DWS API to process, convert, OCR, extract, edit, sign, and fill forms in documents. Supports PDF, DOCX, XLSX, PPTX, HTML, and image formats.

Scoring framework for test-kitchen cookoff and omakase-off. Invoked at Phase 4 to evaluate implementations using 5-criteria scoring. Do not invoke directly - called by cookoff/omakase-off.