content media llm ai AI 技能

发现 content media llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。

分类目录: content media llm ai

最近收录最多 Forks 编辑推荐更多筛选

content media llm ai 清除筛选

GitHub

claude-agent-sdk

daishiman

Claude Agent SDK（@anthropic-ai/claude-agent-sdk）および直接Anthropic SDK（@anthropic-ai/sdk）を使用したエージェント統合の実装を専門とするスキル。 query() API、Hooksシステム、Permission Control、Electron統合、...

☆ 5查看技能

GitHub

role-prompting

daishiman

AIエージェント・システムロール・ペルソナのための役割プロンプト設計スキル。責務分離、専門家思考様式の適用、効果的なプロンプト構造化の指針を提供する。 Anchors: • The Pragmatic Programmer (Andrew Hunt, David Tho...

☆ 5查看技能

GitHub

chain-of-thought-reasoning

daishiman

推論パターンを選択し、根拠サマリーを短く提示するためのプロンプト設計スキル。自己一貫性の比較、推論パターンの適用、説明の明確化を通じて、再現性の高い結論を導く。 Anchors: • The Pragmatic Programmer / 適用: 手...

☆ 5查看技能

GitHub

prompt-testing-evaluation

daishiman

プロンプトのテスト、評価、反復改善を専門とするスキル。A/Bテスト、評価メトリクス、自動化されたプロンプト品質保証により、本番環境で信頼性の高いプロンプトを実現します。 Anchors: • Test-Driven Development: By Exam...

☆ 5查看技能

GitHub

prompt-injection-defense

daishiman

AIシステムへのプロンプトインジェクション攻撃を防ぎ、入力検証とコンテキスト分離の設計指針を提供するスキル。 Anchors: • OWASP LLM Top 10 / 適用: LLMセキュリティ脅威モデリング / 目的: インジェクション攻撃の分類と...

☆ 5查看技能

GitHub

session-management

daishiman

Claude Codeセッションの状態管理、コンテキスト保持、会話履歴の効率的な運用を支援するスキル。長時間セッションでのコンテキスト消費最適化、セッション再開時の状態復元、マルチタスク切り替え時の状態保存・復元を提供...

☆ 5查看技能

GitHub

ai-search-optimization

dirnbauer

Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) strategies for AI-powered search visibility in ChatGPT, Perplexity, Google AI Overviews, and other AI search platforms.

☆ 5查看技能

GitHub

recursive-arena

lollipopkit

Orchestrates recursive iterations using the multi-model battle as the generator each round. Use when user wants recursive refinement plus model battles, multi-LLM consensus, or says "recursive arena".

☆ 5查看技能

GitHub

recursive

lollipopkit

Master Recursive Reasoning - orchestrate complex problem solving by decomposing tasks and delegating to specialized sub-agents. Use when facing multi-step problems that benefit from planning, execution, and ver...

☆ 5查看技能

GitHub

multi-model

lollipopkit

Multi-model battle for iterative (recursive) refinement. Rotates models every iteration and has other models judge/critique. Use when user asks to "battle models", "compare models", "multi-LLM", or wants iterat...

☆ 5查看技能

GitHub

investigate

zewelor

Deep analytical investigation mode using Bayesian reasoning, superforecasting techniques, and rigorous hypothesis testing. Combines methods from Kahneman, Tetlock, Peirce, and Feynman. Use when user invokes /in...

☆ 5查看技能

GitHub

skill-name

ZhanlinCui

"[What this skill does]. Use when [trigger scenarios]."

☆ 5查看技能

GitHub

librarian

aidanmorgan

Semantic documentation architect. Analyzes PROSE CONTENT to organize by concept affinity, eliminate contradictions in explanations, and consolidate scattered ideas.

☆ 5查看技能

GitHub

bonfire

aidanmorgan

Generate an orchestrator prompt from a plan file and assume the coordinator role. Creates plan directory with state and event log files.

☆ 5查看技能

GitHub

orchestration

motlin

Coordinates other skills and agents. ALWAYS use this skill on startup.

☆ 5查看技能

GitHub

conversation-style

motlin

Conversation style guidelines. Use when responding to the user.

☆ 5查看技能

GitHub

offline-claude-code-guide

motlin

Offline Claude Code documentation fallback. Use when the user asks about Claude Code features, capabilities, or configuration and the built-in claude-code-guide subagent fails due to network issues or proxy blo...

☆ 5查看技能

GitHub

llm-context

motlin

Guidelines for working with LLM context stored in the .llm/ directory.

☆ 5查看技能

GitHub

api-design-patterns

AsyrafHussin

RESTful API design, error handling, versioning, and best practices. Use when designing APIs, reviewing endpoints, implementing error responses, or setting up API structure. Triggers on "design API", "review API...

☆ 5查看技能

GitHub

coach

netresearch

Self-improving learning system that detects friction signals and proposes rule updates. This skill should be used when Claude needs to learn from mistakes, when users repeatedly correct behavior, when tool fail...

☆ 5查看技能

GitHub

clix-personalization

clix-so

Helps developers author and debug Clix personalization templates (Liquid-style) for message content, deep links/URLs, and audience targeting. Use when the user mentions personalization variables, Liquid, templa...

☆ 5查看技能

GitHub

clix-skill-creator

clix-so

Helps authors create new Clix agent skills by first researching the latest Clix SDK + docs via the Clix MCP Server, then generating a complete skill folder (SKILL.md, references, scripts, examples) aligned with...

☆ 5查看技能

GitHub

ml-benchmark

jiunbae

ML 모델 벤치마크 및 평가 실행. "벤치마크", "모델 평가", "성능 테스트", "inference 속도" 요청 시 활성화됩니다.

☆ 5查看技能

GitHub

multi-llm-agent

jiunbae

여러 LLM(OpenAI, Gemini, Ollama 등)을 통합하여 멀티 에이전트 협업을 수행합니다. 역할 분담, 토론/합의, 체인 파이프라인, 병렬 처리 등 다양한 협업 패턴을 지원하며, 사용 시점에 시나리오를 동적으로 구성할 수 있습니...

☆ 5查看技能

默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。