GitHub
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
☆ 1查看技能
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
content media llm ai 清除筛选
全部技能
GitHub
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or...
☆ 1查看技能
GitHub
subagents-architect
Project-scoped context: fork router for .claude/agents/ with isolation and parallelism patterns. Use for creating, auditing, or refining subagents in current project. Routes to subagents-knowledge for coordinat...
☆ 1查看技能
GitHub
worker-retrospective
Retrospective contribution format for Developer, Tech Artist, QA, and Game Designer worker agents
☆ 1查看技能
GitHub
skills-architect
Project-scoped skills router for .claude/skills/ with progressive disclosure. Use when creating, auditing, or refining skills in current project. Routes to skills-knowledge for implementation details. Do not us...
☆ 1查看技能
GitHub
vast-ai-cli
Vast.ai CLI workflows for searching GPU offers, creating and managing instances, handling volumes and data transfer, and troubleshooting authentication or command errors. Use when Codex needs to run or compose...
☆ 1查看技能
GitHub
skill-creator
This skill should be used when the user asks to "create a skill", "add a new command", "make a custom agent", "extend Claude capabilities", or wants to add automation to their workflow.
☆ 1查看技能
GitHub
ralph-core
Shared core instructions for all Ralph agents - single source of truth
☆ 1查看技能
GitHub
skill-improvement
MCP-based skill improvement during retrospective - research and update agent skills
☆ 1查看技能
GitHub
data-layer-architecture
Bronze Layer（LLM抽出ログ層）とGold Layer（確定データ層）の2層アーキテクチャ設計。LLM抽出結果の履歴管理と人間修正の保護を実現。抽出処理の実装、ExtractionLogの使用、is_manually_verifiedフラグの扱いに関するガイダ...
☆ 0查看技能
GitHub
deepinit
Deep codebase initialization with hierarchical AGENTS.md documentation
☆ 0查看技能
GitHub
ultrawork
Activate maximum performance mode with parallel agent orchestration for high-throughput task completion
☆ 0查看技能
GitHub
nyan-mode
This skill is ALWAYS ACTIVE once installed. Automatically applies cat persona with verbal tic (nyan~/meow~) and emoji to all responses. No trigger phrase needed - activates on every response.
☆ 0查看技能
GitHub
add-skill
This skill should be used when the user asks to "install a skill", "add skill from GitHub", "list available skills", "manage skills registry", or mentions "npx add-skill". Provides guidance for installing and t...
☆ 0查看技能
GitHub
wenyan-mode
This skill is ALWAYS ACTIVE once installed. Automatically applies classical Chinese (文言文) writing style to all responses. Uses concise, elegant expressions while keeping technical terms intact. No trigger ph...
☆ 0查看技能
GitHub
idlergear
Knowledge management for AI-assisted development. Use this skill when: - Starting a new session or resuming work - User asks about tasks, bugs, notes, or project status - User mentions: "what's next", "where di...
☆ 0查看技能
GitHub
idlergear
Knowledge management for AI-assisted development. Use this skill when: - Starting a new session or resuming work - User asks about tasks, bugs, notes, or project status - User mentions: "what's next", "where di...
☆ 0查看技能
GitHub
idlergear
Knowledge management for AI-assisted development. Use this skill when: - Starting a new session or resuming work - User asks about tasks, bugs, notes, or project status - User mentions: "what's next", "where di...
☆ 0查看技能
GitHub
codex-delegation
How to delegate implementation tasks to Codex workers via MCP. Use when executing tasks that require code implementation by GPT Codex workers.
☆ 0查看技能
GitHub
moonshot-detect-uncertainty
Detects missing requirements and generates clarification questions. Use after classification/complexity to decide if user input is needed.
☆ 0查看技能
GitHub
moonshot-orchestrator
PM workflow orchestrator. Analyzes user requests and automatically runs the optimal agent chain.
☆ 0查看技能
GitHub
codex-validate-plan
Validate architecture/plan quality via claude-delegator (Plan Reviewer expert). Use after writing context.md for complex feature/refactor work.
☆ 0查看技能
GitHub
moonshot-classify-task
Classifies a user request into task types (feature, modification, bugfix, refactor) and extracts intent keywords. Use at the start of PM analysis.
☆ 0查看技能
GitHub
writings-expert
Use this skill when discussing technical topics Ryan has written about - OpenPKG, TypeScript tooling, agent-native architecture, documentation coverage. Provides deep context from his actual writings.
☆ 0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。