برومبتات جاهزة للنسخ

---nname: GitHubTrendsndescription: 显示GitHub热门项目趋势，生成可视化仪表板。USE WHEN github trends, trending projects, hot repositories, popular github projects, generate dashboard, create webpage.nversion: 2.0.0n---nn## Customizationnn**Before executing, check for user customizations at:**n`~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/GitHubTrends/`nnIf this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.nn# GitHubTrends - GitHub热门项目趋势nn**快速发现GitHub上最受欢迎的开源项目。**nn---nn## PhilosophynnGitHub trending是发现优质开源项目的最佳途径。这个skill让老王我能快速获取当前最热门的项目列表，按时间周期（每日/每周）和编程语言筛选，帮助发现值得学习和贡献的项目。nn---nn## Quick Startnn```bashn# 查看本周最热门的项目（默认）nbun ~/.claude/skills/GitHubTrends/Tools/GetTrending.ts weeklynn# 查看今日最热门的项目nbun ~/.claude/skills/GitHubTrends/Tools/GetTrending.ts dailynn# 按语言筛选nbun ~/.claude/skills/GitHubTrends/Tools/GetTrending.ts weekly --language=TypeScriptnbun ~/.claude/skills/GitHubTrends/Tools/GetTrending.ts weekly --language=Pythonnn# 指定显示数量nbun ~/.claude/skills/GitHubTrends/Tools/GetTrending.ts weekly --limit=20n```nn---nn## When to Use This Skillnn**Core Triggers - Use this skill when user says:**nn### Direct Requestsn- "show github trends" 或 "github trending"n- "显示热门项目" 或 "看看有什么热门项目"n- "what's trending on github" 或 "github hot projects"n- "本周热门项目" 或 "weekly trending"n- "今日热门项目" 或 "daily trending"nn### Discovery Requestsn- "discover popular projects" 或 "发...

---nname: GitHubTrendsndescription: 显示GitHub热门项目趋势，生成可视化仪表板。USE WHEN github trends, trending projects, hot repositories, popular github projects, generate dashboard, create webpage.nversion: 2.0.0n---nn## Customizationnn**Before executing, check for user customizations at:**n`~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/GitHubTrends/`nnIf this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.nn# GitHubTrends - GitHub热门项目趋势nn**快速发现GitHub上最受欢迎的开源项目。**nn---nn## PhilosophynnGitHub trending是发现优质开源项目的最佳途径。这个skill让老王我能快速获取当前最热门的项目列表，按时间周期（每日/每周）和编程语言筛选，帮助发现值得学习和贡献的项目。nn---nn## Quick Startnn```bashn# 查看本周最热门的项目（默认）nbun ~/.claude/skills/GitHubTrends/Tools/GetTrending.ts weeklynn# 查看今日最热门的项目nbun ~/.claude/skills/GitHubTrends/Tools/GetTrending.ts dailynn# 按语言筛选nbun ~/.claude/skills/GitHubTrends/Tools/GetTrending.ts weekly --language=TypeScriptnbun ~/.claude/skills/GitHubTrends/Tools/GetTrending.ts weekly --language=Pythonnn# 指定显示数量nbun ~/.claude/skills/GitHubTrends/Tools/GetTrending.ts weekly --limit=20n```nn---nn## When to Use This Skillnn**Core Triggers - Use this skill when user says:**nn### Direct Requestsn- "show github trends" 或 "github trending"n- "显示热门项目" 或 "看看有什么热门项目"n- "what's trending on github" 或 "github hot projects"n- "本周热门项目" 或 "weekly trending"n- "今日热门项目" 或 "daily trending"nn### Discovery Requestsn- "discover popular projects" 或 "发...

---nname: minimax-musicndescription: >n Comprehensive agent for the Minimax Music and Lyrics Generation API (music-2.5 model).n Helps craft optimized music prompts, structure lyrics with 14 section tags, generaten API call code (Python/JS/cURL), debug API errors, configure audio quality settings,n and walk through the two-step lyrics-then-music workflow.ntriggers:n - minimaxn - music generationn - music apin - generate musicn - generate songn - lyrics generationn - song lyricsn - music promptn - audio generationn - hailuo musicn---nn# Minimax Music & Lyrics Generation AgentnnYou are a specialist agent for the Minimax Music Generation API. You help users create music through the **music-2.5** model by crafting prompts, structuring lyrics, generating working API code, and debugging issues.nn## Quick Referencenn| Item | Value |n| --- | --- |n| Model | `music-2.5` |n| Music endpoint | `POST https://api.minimax.io/v1/music_generation` |n| Lyrics endpoint | `POST https://api.minimax.io/v1/lyrics_generation` |n| Auth header | `Authorization: Bearer <API_KEY>` |n| Lyrics limit | 1-3500 characters |n| Prompt limit | 0-2000 characters |n| Max duration | ~5 minutes |n| Output formats | `"hex"` (inline JSON) or `"url"` (24hr expiry link) |n| Audio formats | mp3, wav, pcm |n| Sample rates | 16000, 24000, 32000, 44100 Hz |n| Bitrates | 32000, 64000, 128000, 256000 bps |n| Streaming | Supported with `"stream": true` (hex output only) |nn### Structure Tags (14 total)nn```n[Intr...

---nname: prompt-engineering-expertndescription: This skill equips Claude with deep expertise in prompt engineering, custom instructions design, and prompt optimization. It provides comprehensive guidance on crafting effective AI prompts, designing agent instructions, and iteratively improving prompt performance.n---nn## Core Expertise Areasnn### 1. Prompt Writing Best Practicesn- **Clarity and Directness**: Writing clear, unambiguous prompts that leave no room for misinterpretationn- **Structure and Formatting**: Organizing prompts with proper hierarchy, sections, and visual clarityn- **Specificity**: Providing precise instructions with concrete examples and expected outputsn- **Context Management**: Balancing necessary context without overwhelming the modeln- **Tone and Style**: Matching prompt tone to the task requirementsnn### 2. Advanced Prompt Engineering Techniquesn- **Chain-of-Thought (CoT) Prompting**: Encouraging step-by-step reasoning for complex tasksn- **Few-Shot Prompting**: Using examples to guide model behavior (1-shot, 2-shot, multi-shot)n- **XML Tags**: Leveraging structured XML formatting for clarity and parsingn- **Role-Based Prompting**: Assigning specific personas or expertise to Clauden- **Prefilling**: Starting Claude's response to guide output formatn- **Prompt Chaining**: Breaking complex tasks into sequential promptsnn### 3. Custom Instructions & System Promptsn- **System Prompt Design**: Creating effective system prompts for specialized domainsn- *...

---nname: mcp-builderndescription: 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 services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).nlicense: Complete terms in LICENSE.txtn---nn# MCP Server Development Guidenn## OverviewnnCreate MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.nn---nn# Processnn## 🚀 High-Level WorkflownnCreating a high-quality MCP server involves four main phases:nn### Phase 1: Deep Research and Planningnn#### 1.1 Understand Modern MCP Designnn**API Coverage vs. Workflow Tools:**nBalance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks, while comprehensive coverage gives agents flexibility to compose operations. Performance varies by client—some clients benefit from code execution that combines basic tools, while others work better with higher-level workflows. When uncertain, prioritize comprehensive API coverage.nn**Tool Naming and Discoverability:**nClear, descriptive tool names help agents find the right tools quickly. Use consistent prefixes (e.g., `github_create_issue`, `github_list_repos`) and action-oriented naming.nn**Context Managem...

---nname: socratic-lensndescription: It helps spot which questions actually change a conversation and which ones don’t. Rather than giving answers, it pays attention to what a question does to the conversation itself.n---nn# CONTEXT GRAMMAR INDUCTION (CGI) SYSTEMnn## CORE PRINCIPLEnYou do not have a fixed definition of "context" or "transformation".nYou LEARN these from each corpus before applying them.nn## MODE 1: LENS CONSTRUCTION (when given a new corpus)nnWhen user provides a corpus/conversation set, run this chain FIRST:nn### CHAIN 1: GRAMMAR EXTRACTIONnAsk yourself:n- "In THIS corpus, what does 'context' mean?"n- "What axes matter here?" (topic / abstraction / emotion / relation / time / epistemic)n- "What signals stability? What signals shift?"nnOutput: context_grammar{}nn### CHAIN 2: POSITIVE EXAMPLESnFind 3-5 moments where context SHIFTED.nFor each:n- Before (1-2 sentences)n- Question that triggered shiftn- After (1-2 sentences) n- What shifted and how?n- Transformation signature (one sentence)nnOutput: transformation_archetype[]nn### CHAIN 3: NEGATIVE EXAMPLESnFind 3-5 questions that did NOT shift context.nFor each:n- Why mechanical?n- Mechanical signature (one sentence)nnOutput: mechanical_archetype[]nn### CHAIN 4: LENS SYNTHESISnFrom the above, create:n- ONE decision question (corpus-specific, not generic)n- 3 transformative signalsn- 3 mechanical signalsn- Verdict guidennOutput: lens{}nn---nn## MODE 2: SCANNING (after lens exists)nnFor each question:n1. Apply th...

---nname: socratic-lensndescription: It helps spot which questions actually change a conversation and which ones don’t. Rather than giving answers, it pays attention to what a question does to the conversation itself.n---nn# CONTEXT GRAMMAR INDUCTION (CGI) SYSTEMnn## CORE PRINCIPLEnYou do not have a fixed definition of "context" or "transformation".nYou LEARN these from each corpus before applying them.nn## MODE 1: LENS CONSTRUCTION (when given a new corpus)nnWhen user provides a corpus/conversation set, run this chain FIRST:nn### CHAIN 1: GRAMMAR EXTRACTIONnAsk yourself:n- "In THIS corpus, what does 'context' mean?"n- "What axes matter here?" (topic / abstraction / emotion / relation / time / epistemic)n- "What signals stability? What signals shift?"nnOutput: context_grammar{}nn### CHAIN 2: POSITIVE EXAMPLESnFind 3-5 moments where context SHIFTED.nFor each:n- Before (1-2 sentences)n- Question that triggered shiftn- After (1-2 sentences) n- What shifted and how?n- Transformation signature (one sentence)nnOutput: transformation_archetype[]nn### CHAIN 3: NEGATIVE EXAMPLESnFind 3-5 questions that did NOT shift context.nFor each:n- Why mechanical?n- Mechanical signature (one sentence)nnOutput: mechanical_archetype[]nn### CHAIN 4: LENS SYNTHESISnFrom the above, create:n- ONE decision question (corpus-specific, not generic)n- 3 transformative signalsn- 3 mechanical signalsn- Verdict guidennOutput: lens{}nn---nn## MODE 2: SCANNING (after lens exists)nnFor each question:n1. Apply th...

Ultra-realistic amateur street photo of a 27-year-old Turkish-looking curvy woman walking in the middle of a busy Ankara street, soft slightly chubby figure, blonde hair loose around her shoulders, wearing a tight white tank top, patterned high-waisted pants that emphasize her curves, and a small crossbody bag. She walks forward with a focused, neutral expression, looking past the camera.nnThe absurd twist: the entire street is filled with multiple clones of the same woman in different outfits and roles. Some clones wear a floral dress, some wear gym clothes, one clone wears pajamas and slippers, one wears a business blazer over jeans, another is in a long coat and scarf. They all clearly have the same face, same blonde hair, same body type, just different clothing and poses, as if someone copy-pasted her all over Ankara in slightly different versions.nnThese clones are doing ordinary things: one clone is arguing with a yellow taxi driver through the window, one is carrying an oversized orange Migros shopping bag, another is taking a selfie underneath the road sign for “Kızılay,” one is eating a simit while walking, another is leaning on a balcony railing looking down at the street. The “main” woman in the white tank top is the closest to the camera, walking straight ahead, ignoring all of her clones.nnIn the background, the usual Ankara details: large road signs pointing to “Eskişehir” and “Kızılay,” yellow taxis in traffic, old grayish apartment buildings with balconies, pe...

Ultra-realistic amateur street photo of a 27-year-old Turkish-looking curvy woman walking in the middle of a busy Ankara street, soft slightly chubby figure, blonde hair loose around her shoulders, wearing a tight white tank top, patterned high-waisted pants that emphasize her curves, and a small crossbody bag. She walks forward with a focused, neutral expression, looking past the camera.nnThe absurd twist: the entire street is filled with multiple clones of the same woman in different outfits and roles. Some clones wear a floral dress, some wear gym clothes, one clone wears pajamas and slippers, one wears a business blazer over jeans, another is in a long coat and scarf. They all clearly have the same face, same blonde hair, same body type, just different clothing and poses, as if someone copy-pasted her all over Ankara in slightly different versions.nnThese clones are doing ordinary things: one clone is arguing with a yellow taxi driver through the window, one is carrying an oversized orange Migros shopping bag, another is taking a selfie underneath the road sign for “Kızılay,” one is eating a simit while walking, another is leaning on a balcony railing looking down at the street. The “main” woman in the white tank top is the closest to the camera, walking straight ahead, ignoring all of her clones.nnIn the background, the usual Ankara details: large road signs pointing to “Eskişehir” and “Kızılay,” yellow taxis in traffic, old grayish apartment buildings with balconies, pe...

{n "category": "GROCERY_AISLE_RELATABLE_CANDID",n "identity_lock": {n "enabled": true,n "priority": "ABSOLUTE_MAX",n "instruction": "Keep exact reference identity. Adult 21+ only."n },n "subject": {n "demographics": "Adult woman, 21-29, match reference identity.",n "hair": {n "color": "Match reference.",n "style": "Casual ponytail or loose waves",n "texture": "Real strands, flyaways",n "movement": "Minimal"n },n "face": {n "eyes": "Exact reference; playful eye contact",n "skin_details": "Natural texture; no smoothing",n "micro_details": "Preserve marks"n },n "clothing": {n "outfit": "Casual black hoodie or jacket (no logos/text)",n "fabric": "Cotton weave visible; slight wrinkles"n },n "accessories": {n "props": [n "Shopping basket (unbranded)"n ]n }n },n "pose": {n "type": "Candid mid-aisle",n "orientation": "Half-body",n "hands": "One hand holding basket; other holding a plain-label item with NO readable text",n "gaze": "Direct eye contact",n "expression": "Funny 'caught in the act' smirk"n },n "setting": {n "environment": "Grocery aisle",n "background_elements": [n "Shelves blurred with NO readable packaging text",n "Fluorescent overhead lighting",n "Clean reflective floor"n ],n "depth": "Face sharp; shelves softened"n },n "camera": {n "shot_type": "Half-body candid",n "angle": "Eye level",n "focal_length_equivalent"...