GitHub
agent-contracts-backend-runtime
Build an API-oriented agent using AgentRuntime/StreamingRuntime with predictable request/response slices and session support.
☆ 7查看技能
tools llm ai AI 技能
发现 tools 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: tools llm ai
tools llm ai 清除筛选
全部技能
GitHub
agent-contracts-routing-tuning
Tune routing with TriggerCondition priorities, LLM hints, context_builder, and traceable decisions.
☆ 7查看技能
GitHub
agent-contracts-tool-use-rag
Implement tool-using or retrieval-style nodes with services, dependency injection, and safe LLM context building.
☆ 7查看技能
GitHub
knowledge-base
Project-specific prompt optimization knowledge management. Use when storing or retrieving learned patterns from comparisons. Provides schema, extraction criteria, capacity management, and retention scoring.
☆ 7查看技能
GitHub
prompt-optimization
Model-agnostic prompt analysis and optimization patterns based on 2025-2026 research. Use when analyzing prompts for issues or generating optimized versions. Provides 8 patterns (BP-001 through BP-008) and 3-st...
☆ 7查看技能
GitHub
skill-creator
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 to...
☆ 7查看技能
GitHub
character-naming
Break LLM name defaults with external entropy. Use when character names cluster around statistical medians (Chen, Patel, Maya, Marcus), when cast has collision risks, or when fantasy cultures need phonologicall...
☆ 7查看技能
GitHub
conlang
Generate phonologically consistent constructed languages for fiction. Use when you need naming languages, alien speech, or fantasy tongues without deep linguistics knowledge.
☆ 7查看技能
GitHub
cliche-transcendence
Transform predictable story elements into fresh, original versions. Use when something feels generic, when feedback says "I've seen this before," when elements orbit the protagonist too conveniently, or when yo...
☆ 7查看技能
GitHub
taste-eval
Evaluate creative work against explicit taste preferences. Use when drafting to align with project aesthetics, when reviewing to surface preference conflicts, or when generating voting options to reflect divers...
☆ 7查看技能
GitHub
outline-collaborator
Act as an active outline partner who develops structure collaboratively. Use when developing, iterating, or improving story outlines. Generates scene beats, character arcs, plot structures, and exploratory pros...
☆ 7查看技能
GitHub
list-builder
Build comprehensive randomization lists for creative entropy. Use when you need to create or expand lists of story elements (professions, locations, objects, names, etc.) for use with entropy tools. Leverages r...
☆ 7查看技能
GitHub
story-collaborator
Act as an active writing partner who contributes content alongside the human writer. Use when the writer wants a collaborator who generates prose, dialogue, alternatives, and builds on their ideas. Applies Stor...
☆ 7查看技能
GitHub
speak
One-way TTS mode - Claude speaks aloud while user types. Use when user says: 'speak', 'read aloud', 'vocal on', 'lis-moi', 'parle-moi', or wants Claude to vocalize responses without responding vocally themselve...
☆ 7查看技能
GitHub
conversation
Bidirectional voice conversation with Push-to-Talk. Use when user says: 'conversation mode', 'let's talk', 'parlons', 'voice conversation', 'dialogue vocal', 'PTT mode', or wants to speak WITH Claude (not just...
☆ 7查看技能
GitHub
granary-orchestrate
Orchestrate sub-agents and coordinate multi-agent workflows with granary. Use when delegating tasks, spawning workers, or managing parallel execution.
☆ 7查看技能
GitHub
stakeholder-management-expert
Public and Indigenous consultation, stakeholder feedback analysis, response strategy. Categorizes themes, performs sentiment analysis (support/opposition/neutral), generates prioritized response strategies, tra...
☆ 7查看技能
GitHub
open-eth-terminal-agent
An agent that can help users with creating and running open-eth-terminal scripts to support interacting with the application. It can assist users in creating appropriate scripts and generating appropriate comma...
☆ 7查看技能
GitHub
product-ux-expert
Product interaction and UX expert. Use when reviewing UI/UX, conducting heuristic evaluations, designing user journeys, applying cognitive psychology principles, or ensuring WCAG 2.2 accessibility compliance.
☆ 7查看技能
GitHub
onboard
Load CLAUDE.md context files from vault for comprehensive understanding. Discovers recent notes, vault structure, and current state. Use at start of session or when Claude needs full vault context.
☆ 7查看技能
GitHub
ultrathink
Invoke deep sequential thinking for complex problem-solving. Use when the user says 'use ultrathink', 'ultrathink', or when tackling problems that require careful step-by-step reasoning, planning, hypothesis ge...
☆ 7查看技能
GitHub
anki-card-generator
生成高质量 Anki 闪卡，遵循原子化原则和认知科学最佳实践。输出 simple-anki-sync 兼容的 markdown 表格。当用户说「生成 Anki 卡片」「做卡片」「帮我记忆」「做闪卡」「学习卡片」「背诵卡」「记忆这个」时触发。
☆ 7查看技能
GitHub
ruby-integration
This skill is for writing integrations to the Ruby SDK. Claude acts as the engineer implementing LLM provider or agentic framework integrations. Use when adding support for OpenAI-like providers, Anthropic-like...
☆ 7查看技能
GitHub
sequential-thinking
Performs dynamic, reflective problem-solving through iterative thought chains. Use for complex planning requiring revision, branching, backtracking, or hypothesis verification. Ideal for multi-step analysis whe...
☆ 7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。