Guidance
Skill Verifiziert AktivControl LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
To provide developers with fine-grained control over LLM output, ensuring validity, structure, and reducing generation latency for tasks requiring precise formatting and multi-step reasoning.
Funktionen
- Constrained LLM output generation via regex and grammars
- Guaranteed valid JSON, XML, and code generation
- Token healing for natural continuations
- Support for multiple LLM backends (API and local)
- Pythonic control flow for multi-step workflows
- Selection constraints for fixed choices
Anwendungsfälle
- Generating valid JSON or XML outputs
- Enforcing specific data formats (emails, dates, phone numbers)
- Building structured agent workflows with decision trees
- Reducing LLM latency by constraining generation paths
- Creating reproducible LLM outputs through precise grammars
Nicht-Ziele
- Replacing the core LLM inference engine
- Providing a low-level interface for raw token generation
- Handling the execution of external tools (delegated to user code)
- Managing LLM agent orchestration beyond generation control
Execution
- info:Pinned dependenciesWhile dependencies are listed, specific version pinning and lockfiles are not explicitly detailed in the SKILL.md, relying on standard pip behavior.
Installation
Zuerst Marketplace hinzufügen
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs/plugin install AI-Research-SKILLs@ai-research-skillsQualitätspunktzahl
VerifiziertVertrauenssignale
Ähnliche Erweiterungen
Guidance
79Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
Teach Guidance
100Guide a person in becoming a better teacher and explainer. AI coaches content structuring, audience calibration, explanation clarity, Socratic questioning technique, feedback interpretation, and reflective practice for technical presentations, documentation, and mentoring. Use when a person needs to present technical content and wants preparation coaching, wants to write better documentation or tutorials, struggles to explain concepts across expertise levels, is mentoring a colleague, or is preparing for a talk or knowledge-sharing session.
Moyu (摸鱼)
100자동으로 과잉 엔지니어링 패턴을 탐지합니다: (1) 사용자가 명시적으로 요청하지 않은 코드나 파일을 수정하는 경우 (2) 요청되지 않은 새로운 추상화 레이어(클래스, 인터페이스, 팩토리, 래퍼)를 생성하는 경우 (3) 요청되지 않은 주석, 문서, JSDoc, 타입 어노테이션을 추가하는 경우 (4) 요청되지 않은 새로운 종속성을 도입하는 경우 (5) 최소한의 편집 대신 파일 전체를 다시 작성하는 경우 (6) diff 범위가 사용자의 요청을 명백히 초과하는 경우 (7) 사용자가 "너무 많아", "거기는 건드리지 마", "X만 변경해", "간단하게", "그만"과 같은 신호를 보내는 경우 (8) 발생할 수 없는 시나리오에 대한 오류 처리, 유효성 검사, 방어적 코드 추가 (9) 요청되지 않은 테스트, 설정 스캐폴딩, 문서 생성
Create Command
100Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
Write A Skill
100Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Openclaw
100Generieren Sie Bilder und Videos aus Text mit Multi-Provider-Routing – unterstützt GPT Image 2.0 (nahezu perfekte Textdarstellung), Nanobanana 2, Seedream 5.0, Midjourney V8.1 (vereinheitlicht fotorealistisch + Anime), Flux 2 Klein (günstige Entwürfe), Seedance 2.0 / Happyhorse 1.0 / Veo 3.1 Video und lokale ComfyUI-Workflows. Enthält 1.446 kuratierte Prompts und stilbewusste Prompt-Verbesserung. Verwenden Sie es, wenn Benutzer Bilder/Videos erstellen, Assets entwerfen, Fotos animieren, Prompts verbessern oder KI-Kunst-Workflows verwalten möchten. NICHT für: allgemeine Chats, Code-Generierung, Dokumentenerstellung, Videobearbeitung von vorhandenem Material, Audio/TTS oder Aufgaben, die nichts mit der Erstellung von KI-Bildern/Videos zu tun haben.