GitHub
asr
Implement speech-to-text (ASR/automatic speech recognition) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to transcribe audio files, convert speech to text, build voice input featu...
☆ 24Voir le skill
Skills IA documentation llm ai
Découvrez les skills documentation llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: documentation llm ai
documentation llm ai Effacer les filtres
Explorer
GitHub
image-generation
Implement AI image generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to create images from text descriptions, generate visual content, create artwork, design assets, or buil...
☆ 24Voir le skill
GitHub
tts
Implement text-to-speech (TTS) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to convert text into natural-sounding speech, create audio content, build voice-enabled applications, o...
☆ 24Voir le skill
GitHub
llm
Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation feat...
☆ 24Voir le skill
GitHub
vlm
Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze images, describe visual content, or create applications that combine image understanding wit...
☆ 24Voir le skill
GitHub
web-search
Implement web search capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to search the web, retrieve current information, find relevant content, or build applications with real-time web...
☆ 24Voir le skill
GitHub
paw-review-critic
Critically assesses generated review comments for usefulness, accuracy, and appropriateness, adding assessment sections.
☆ 24Voir le skill
GitHub
audit
Detects hallucinations, timeline fabrications, and unverified assumptions in agent output. Use when reviewing sub-agent results, receiving research findings, validating claims that seem suspicious, or when outp...
☆ 24Voir le skill
GitHub
delegate
Quick delegation template for sub-agent prompts. Use when assigning work to a sub-agent, before invoking the Task tool, or when preparing prompts for specialized agents. Provides the WHERE-WHAT-WHY framework. F...
☆ 24Voir le skill
GitHub
scientific-thinking
Forces hypothesis-driven scientific reasoning for complex problems. Use when debugging strange behavior, investigating root causes, designing architecture, performing complex refactoring, or when initial attemp...
☆ 24Voir le skill
GitHub
prompt-annotation
Annotates agent prompts with structural XML tags for comprehension, gap detection, and skill extraction. Use when analyzing agent prompt structure, comparing agents across projects, or identifying reusable vs w...
☆ 24Voir le skill
GitHub
ui-skills
Opinionated constraints for building better interfaces with agents.
☆ 23Voir le skill
GitHub
plan-swarm
Refine plans through multi-agent expert discussion. Use when user says "get multiple expert opinions on this plan", "I want different perspectives on this approach", "have the agents discuss this strategy", "re...
☆ 23Voir le skill
GitHub
ai-organizer-ui-consolidation
Build a unified, ADHD-friendly web UI that consolidates 70+ CLI tools into a beautiful liquid glass interface for the AI File Organizer. Use when creating the complete frontend application that replaces all ter...
☆ 23Voir le skill
GitHub
agent-orchestrator-manager
Orchestrates multi-agent workflows by delegating ALL tasks to spawned subagents via /spawn command. Parallelizes independent work, supervises execution, tracks progress in UUID-based output directories, and gen...
☆ 23Voir le skill
GitHub
command-writer
Expert assistant for creating Claude Code custom slash commands. Guides command file structure, YAML frontmatter configuration, variable syntax, and best practices. Triggers on keywords: writing commands, creat...
☆ 23Voir le skill
GitHub
skill-writer
Expert assistant for authoring Claude Code skills. Creates precise SKILL.md files with proper YAML frontmatter, validates naming conventions, and applies official best practices. Triggers on keywords: writing s...
☆ 23Voir le skill
GitHub
ecosystem-guide
Guide to spences10's Claude Code ecosystem. Use when user asks which tool to use, how tools relate, or needs help choosing between MCP servers, skills, or CLIs.
☆ 23Voir le skill
GitHub
creating-skills
Guide for creating, testing, and deploying effective skills. Use when users want to create a new skill, update an existing skill, verify skills work before deployment, or extend Claude's capabilities with speci...
☆ 23Voir le skill
GitHub
pydantic-ai-testing
Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.
☆ 23Voir le skill
GitHub
pydantic-ai-common-pitfalls
Avoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior, or when reviewing agent implementations.
☆ 23Voir le skill
GitHub
pydantic-ai-dependency-injection
Implement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need database connections, API clients, user context, or any external resources.
☆ 23Voir le skill
GitHub
deepagents-code-review
Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configurat...
☆ 23Voir le skill
GitHub
receive-feedback
Process external code review feedback with technical rigor. Use when receiving feedback from another LLM, human reviewer, or CI tool. Verifies claims before implementing, tracks disposition.
☆ 23Voir le skill
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.