[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FZB5ZP3NP1DNMW6MYKEY4Z":3,"skill-same:01M6FZB5ZP3NP1DNMW6MYKEY4Z":80},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M6FZB5ZP3NP1DNMW6MYKEY4Z","prompt-engineering",null,"Master prompt engineering for AI models: LLMs, image generators, video models.\nTechniques: chain-of-thought, few-shot, system prompts, negative prompts.\nModels: Claude, GPT-4, Gemini, FLUX, Veo, Stable Diffusion prompting.\nUse for: better AI outputs, consistent results, complex tasks, optimization.\nTriggers: prompt engineering, how to prompt, better prompts, prompt tips,\nprompting guide, llm prompting, image prompt, ai prompting, prompt optimization,\nprompt template, prompt structure, effective prompts, prompt techniques","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fokaris\u002Fprompt-engineering\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"prompt engineering","engineering","prompt","guide","Prompt Optimization","ai models","few-shot","chain-of-thought","how to","chain","flux","structure","master","image","template","Bash","how","Video","tasks","llms","2026-11-10 10:12:30",false,"---\nname: prompt-engineering\ndescription: |\n  Master prompt engineering for AI models: LLMs, image generators, video models.\n  Techniques: chain-of-thought, few-shot, system prompts, negative prompts.\n  Models: Claude, GPT-4, Gemini, FLUX, Veo, Stable Diffusion prompting.\n  Use for: better AI outputs, consistent results, complex tasks, optimization.\n  Triggers: prompt engineering, how to prompt, better prompts, prompt tips,\n  prompting guide, llm prompting, image prompt, ai prompting, prompt optimization,\n  prompt template, prompt structure, effective prompts, prompt techniques\nallowed-tools: Bash(infsh *)\n---\n\n# Prompt Engineering Guide\n\nMaster prompt engineering for AI models via [inference.sh](https:\u002F\u002Finference.sh) CLI.\n\n## Quick Start\n\n```bash\ncurl -fsSL https:\u002F\u002Fcli.inference.sh | sh && infsh login\n\n# Well-structured LLM prompt\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"You are a senior software engineer. Review this code for security vulnerabilities:\\n\\n```python\\nuser_input = request.args.get(\\\"query\\\")\\nresult = db.execute(f\\\"SELECT * FROM users WHERE name = {user_input}\\\")\\n```\\n\\nProvide specific issues and fixes.\"\n}'\n```\n\n## LLM Prompting\n\n### Basic Structure\n\n```\n[Role\u002FContext] + [Task] + [Constraints] + [Output Format]\n```\n\n### Role Prompting\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"You are an expert data scientist with 15 years of experience in machine learning. Explain gradient descent to a beginner, using simple analogies.\"\n}'\n```\n\n### Task Clarity\n\n```bash\n# Bad: vague\n\"Help me with my code\"\n\n# Good: specific\n\"Debug this Python function that should return the sum of even numbers from a list, but returns 0 for all inputs:\n\ndef sum_evens(numbers):\n    total = 0\n    for n in numbers:\n        if n % 2 == 0:\n            total += n\n        return total\n\nIdentify the bug and provide the corrected code.\"\n```\n\n### Chain-of-Thought\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Solve this step by step:\\n\\nA store sells apples for $2 each and oranges for $3 each. If someone buys 5 fruits and spends $12, how many of each fruit did they buy?\\n\\nThink through this step by step before giving the final answer.\"\n}'\n```\n\n### Few-Shot Examples\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Convert these sentences to formal business English:\\n\\nExample 1:\\nInput: gonna send u the report tmrw\\nOutput: I will send you the report tomorrow.\\n\\nExample 2:\\nInput: cant make the meeting, something came up\\nOutput: I apologize, but I will be unable to attend the meeting due to an unforeseen circumstance.\\n\\nNow convert:\\nInput: hey can we push the deadline back a bit?\"\n}'\n```\n\n### Output Format Specification\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Analyze the sentiment of these customer reviews. Return a JSON array with objects containing \\\"text\\\", \\\"sentiment\\\" (positive\u002Fnegative\u002Fneutral), and \\\"confidence\\\" (0-1).\\n\\nReviews:\\n1. \\\"Great product, fast shipping!\\\"\\n2. \\\"Meh, its okay I guess\\\"\\n3. \\\"Worst purchase ever, total waste of money\\\"\\n\\nReturn only valid JSON, no explanation.\"\n}'\n```\n\n### Constraint Setting\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Summarize this article in exactly 3 bullet points. Each bullet must be under 20 words. Focus only on actionable insights, not background information.\\n\\n[article text]\"\n}'\n```\n\n## Image Generation Prompting\n\n### Basic Structure\n\n```\n[Subject] + [Style] + [Composition] + [Lighting] + [Technical]\n```\n\n### Subject Description\n\n```bash\n# Bad: vague\n\"a cat\"\n\n# Good: specific\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"A fluffy orange tabby cat with green eyes, sitting on a vintage leather armchair\"\n}'\n```\n\n### Style Keywords\n\n```bash\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"Portrait photograph of a woman, shot on Kodak Portra 400 film, soft natural lighting, shallow depth of field, nostalgic mood, analog photography aesthetic\"\n}'\n```\n\n### Composition Control\n\n```bash\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"Wide establishing shot of a cyberpunk city skyline at night, rule of thirds composition, neon signs in foreground, towering skyscrapers in background, rain-slicked streets\"\n}'\n```\n\n### Quality Keywords\n\n```\nphotorealistic, 8K, ultra detailed, sharp focus, professional,\nmasterpiece, high quality, best quality, intricate details\n```\n\n### Negative Prompts\n\n```bash\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"Professional headshot portrait, clean background\",\n  \"negative_prompt\": \"blurry, distorted, extra limbs, watermark, text, low quality, cartoon, anime\"\n}'\n```\n\n## Video Prompting\n\n### Basic Structure\n\n```\n[Shot Type] + [Subject] + [Action] + [Setting] + [Style]\n```\n\n### Camera Movement\n\n```bash\ninfsh app run google\u002Fveo-3-1-fast --input '{\n  \"prompt\": \"Slow tracking shot following a woman walking through a sunlit forest, golden hour lighting, shallow depth of field, cinematic, 4K\"\n}'\n```\n\n### Action Description\n\n```bash\ninfsh app run google\u002Fveo-3-1-fast --input '{\n  \"prompt\": \"Close-up of hands kneading bread dough on a wooden surface, flour dust floating in morning light, slow motion, cozy baking aesthetic\"\n}'\n```\n\n### Temporal Keywords\n\n```\nslow motion, timelapse, real-time, smooth motion,\ncontinuous shot, quick cuts, frozen moment\n```\n\n## Advanced Techniques\n\n### System Prompts\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"system\": \"You are a helpful coding assistant. Always provide code with comments. If you are unsure about something, say so rather than guessing.\",\n  \"prompt\": \"Write a Python function to validate email addresses using regex.\"\n}'\n```\n\n### Structured Output\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Extract information from this text and return as JSON:\\n\\n\\\"John Smith, CEO of TechCorp, announced yesterday that the company raised $50 million in Series B funding. The round was led by Venture Partners.\\\"\\n\\nSchema:\\n{\\n  \\\"person\\\": string,\\n  \\\"title\\\": string,\\n  \\\"company\\\": string,\\n  \\\"event\\\": string,\\n  \\\"amount\\\": string,\\n  \\\"investor\\\": string\\n}\"\n}'\n```\n\n### Iterative Refinement\n\n```bash\n# Start broad\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"A castle on a hill\"\n}'\n\n# Add specifics\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"A medieval stone castle on a grassy hill\"\n}'\n\n# Add style\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"A medieval stone castle on a grassy hill, dramatic sunset sky, fantasy art style, epic composition\"\n}'\n\n# Add technical\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"A medieval stone castle on a grassy hill, dramatic sunset sky, fantasy art style by Greg Rutkowski, epic composition, 8K, highly detailed\"\n}'\n```\n\n### Multi-Turn Reasoning\n\n```bash\n# First: analyze\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Analyze this business problem: Our e-commerce site has a 70% cart abandonment rate. List potential causes.\"\n}'\n\n# Second: prioritize\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Given these causes of cart abandonment: [previous output], rank them by likely impact and ease of fixing. Format as a priority matrix.\"\n}'\n\n# Third: action plan\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"For the top 3 causes identified, provide specific A\u002FB tests we can run to validate and fix each issue.\"\n}'\n```\n\n## Model-Specific Tips\n\n### Claude\n\n- Excels at nuanced instructions\n- Responds well to role-playing\n- Good at following complex constraints\n- Prefers explicit output formats\n\n### GPT-4\n\n- Strong at code generation\n- Works well with examples\n- Good structured output\n- Responds to \"let's think step by step\"\n\n### FLUX\n\n- Detailed subject descriptions\n- Style references work well\n- Lighting keywords important\n- Negative prompts supported\n\n### Veo\n\n- Camera movement keywords\n- Cinematic language works well\n- Action descriptions important\n- Include temporal context\n\n## Common Mistakes\n\n| Mistake | Problem | Fix |\n|---------|---------|-----|\n| Too vague | Unpredictable output | Add specifics |\n| Too long | Model loses focus | Prioritize key info |\n| Conflicting | Confuses model | Remove contradictions |\n| No format | Inconsistent output | Specify format |\n| No examples | Unclear expectations | Add few-shot |\n\n## Prompt Templates\n\n### Code Review\n\n```\nReview this [language] code for:\n1. Bugs and logic errors\n2. Security vulnerabilities\n3. Performance issues\n4. Code style\u002Fbest practices\n\nCode:\n[code]\n\nFor each issue found, provide:\n- Line number\n- Issue description\n- Severity (high\u002Fmedium\u002Flow)\n- Suggested fix\n```\n\n### Content Writing\n\n```\nWrite a [content type] about [topic].\n\nAudience: [target audience]\nTone: [formal\u002Fcasual\u002Fprofessional]\nLength: [word count]\nKey points to cover:\n1. [point 1]\n2. [point 2]\n3. [point 3]\n\nInclude: [specific elements]\nAvoid: [things to exclude]\n```\n\n### Image Generation\n\n```\n[Subject with details], [setting\u002Fbackground], [lighting type],\n[art style or photography style], [composition], [quality keywords]\n```\n\n## Related Skills\n\n```bash\n# Video prompting guide\nnpx skills add inference-sh\u002Fagent-skills@video-prompting-guide\n\n# LLM models\nnpx skills add inference-sh\u002Fagent-skills@llm-models\n\n# Image generation\nnpx skills add inference-sh\u002Fagent-skills@ai-image-generation\n\n# Full platform skill\nnpx skills add inference-sh\u002Fagent-skills@inference-sh\n```\n\nBrowse all apps: `infsh app list`\n","# Prompt Engineering Guide\n\nMaster prompt engineering for AI models via [inference.sh](https:\u002F\u002Finference.sh) CLI.\n\n## Quick Start\n\n```bash\ncurl -fsSL https:\u002F\u002Fcli.inference.sh | sh && infsh login\n\n# Well-structured LLM prompt\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"You are a senior software engineer. Review this code for security vulnerabilities:\\n\\n```python\\nuser_input = request.args.get(\\\"query\\\")\\nresult = db.execute(f\\\"SELECT * FROM users WHERE name = {user_input}\\\")\\n```\\n\\nProvide specific issues and fixes.\"\n}'\n```\n\n## LLM Prompting\n\n### Basic Structure\n\n```\n[Role\u002FContext] + [Task] + [Constraints] + [Output Format]\n```\n\n### Role Prompting\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"You are an expert data scientist with 15 years of experience in machine learning. Explain gradient descent to a beginner, using simple analogies.\"\n}'\n```\n\n### Task Clarity\n\n```bash\n# Bad: vague\n\"Help me with my code\"\n\n# Good: specific\n\"Debug this Python function that should return the sum of even numbers from a list, but returns 0 for all inputs:\n\ndef sum_evens(numbers):\n    total = 0\n    for n in numbers:\n        if n % 2 == 0:\n            total += n\n        return total\n\nIdentify the bug and provide the corrected code.\"\n```\n\n### Chain-of-Thought\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Solve this step by step:\\n\\nA store sells apples for $2 each and oranges for $3 each. If someone buys 5 fruits and spends $12, how many of each fruit did they buy?\\n\\nThink through this step by step before giving the final answer.\"\n}'\n```\n\n### Few-Shot Examples\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Convert these sentences to formal business English:\\n\\nExample 1:\\nInput: gonna send u the report tmrw\\nOutput: I will send you the report tomorrow.\\n\\nExample 2:\\nInput: cant make the meeting, something came up\\nOutput: I apologize, but I will be unable to attend the meeting due to an unforeseen circumstance.\\n\\nNow convert:\\nInput: hey can we push the deadline back a bit?\"\n}'\n```\n\n### Output Format Specification\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Analyze the sentiment of these customer reviews. Return a JSON array with objects containing \\\"text\\\", \\\"sentiment\\\" (positive\u002Fnegative\u002Fneutral), and \\\"confidence\\\" (0-1).\\n\\nReviews:\\n1. \\\"Great product, fast shipping!\\\"\\n2. \\\"Meh, its okay I guess\\\"\\n3. \\\"Worst purchase ever, total waste of money\\\"\\n\\nReturn only valid JSON, no explanation.\"\n}'\n```\n\n### Constraint Setting\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Summarize this article in exactly 3 bullet points. Each bullet must be under 20 words. Focus only on actionable insights, not background information.\\n\\n[article text]\"\n}'\n```\n\n## Image Generation Prompting\n\n### Basic Structure\n\n```\n[Subject] + [Style] + [Composition] + [Lighting] + [Technical]\n```\n\n### Subject Description\n\n```bash\n# Bad: vague\n\"a cat\"\n\n# Good: specific\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"A fluffy orange tabby cat with green eyes, sitting on a vintage leather armchair\"\n}'\n```\n\n### Style Keywords\n\n```bash\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"Portrait photograph of a woman, shot on Kodak Portra 400 film, soft natural lighting, shallow depth of field, nostalgic mood, analog photography aesthetic\"\n}'\n```\n\n### Composition Control\n\n```bash\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"Wide establishing shot of a cyberpunk city skyline at night, rule of thirds composition, neon signs in foreground, towering skyscrapers in background, rain-slicked streets\"\n}'\n```\n\n### Quality Keywords\n\n```\nphotorealistic, 8K, ultra detailed, sharp focus, professional,\nmasterpiece, high quality, best quality, intricate details\n```\n\n### Negative Prompts\n\n```bash\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"Professional headshot portrait, clean background\",\n  \"negative_prompt\": \"blurry, distorted, extra limbs, watermark, text, low quality, cartoon, anime\"\n}'\n```\n\n## Video Prompting\n\n### Basic Structure\n\n```\n[Shot Type] + [Subject] + [Action] + [Setting] + [Style]\n```\n\n### Camera Movement\n\n```bash\ninfsh app run google\u002Fveo-3-1-fast --input '{\n  \"prompt\": \"Slow tracking shot following a woman walking through a sunlit forest, golden hour lighting, shallow depth of field, cinematic, 4K\"\n}'\n```\n\n### Action Description\n\n```bash\ninfsh app run google\u002Fveo-3-1-fast --input '{\n  \"prompt\": \"Close-up of hands kneading bread dough on a wooden surface, flour dust floating in morning light, slow motion, cozy baking aesthetic\"\n}'\n```\n\n### Temporal Keywords\n\n```\nslow motion, timelapse, real-time, smooth motion,\ncontinuous shot, quick cuts, frozen moment\n```\n\n## Advanced Techniques\n\n### System Prompts\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"system\": \"You are a helpful coding assistant. Always provide code with comments. If you are unsure about something, say so rather than guessing.\",\n  \"prompt\": \"Write a Python function to validate email addresses using regex.\"\n}'\n```\n\n### Structured Output\n\n```bash\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Extract information from this text and return as JSON:\\n\\n\\\"John Smith, CEO of TechCorp, announced yesterday that the company raised $50 million in Series B funding. The round was led by Venture Partners.\\\"\\n\\nSchema:\\n{\\n  \\\"person\\\": string,\\n  \\\"title\\\": string,\\n  \\\"company\\\": string,\\n  \\\"event\\\": string,\\n  \\\"amount\\\": string,\\n  \\\"investor\\\": string\\n}\"\n}'\n```\n\n### Iterative Refinement\n\n```bash\n# Start broad\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"A castle on a hill\"\n}'\n\n# Add specifics\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"A medieval stone castle on a grassy hill\"\n}'\n\n# Add style\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"A medieval stone castle on a grassy hill, dramatic sunset sky, fantasy art style, epic composition\"\n}'\n\n# Add technical\ninfsh app run falai\u002Fflux-dev --input '{\n  \"prompt\": \"A medieval stone castle on a grassy hill, dramatic sunset sky, fantasy art style by Greg Rutkowski, epic composition, 8K, highly detailed\"\n}'\n```\n\n### Multi-Turn Reasoning\n\n```bash\n# First: analyze\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Analyze this business problem: Our e-commerce site has a 70% cart abandonment rate. List potential causes.\"\n}'\n\n# Second: prioritize\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"Given these causes of cart abandonment: [previous output], rank them by likely impact and ease of fixing. Format as a priority matrix.\"\n}'\n\n# Third: action plan\ninfsh app run openrouter\u002Fclaude-sonnet-45 --input '{\n  \"prompt\": \"For the top 3 causes identified, provide specific A\u002FB tests we can run to validate and fix each issue.\"\n}'\n```\n\n## Model-Specific Tips\n\n### Claude\n\n- Excels at nuanced instructions\n- Responds well to role-playing\n- Good at following complex constraints\n- Prefers explicit output formats\n\n### GPT-4\n\n- Strong at code generation\n- Works well with examples\n- Good structured output\n- Responds to \"let's think step by step\"\n\n### FLUX\n\n- Detailed subject descriptions\n- Style references work well\n- Lighting keywords important\n- Negative prompts supported\n\n### Veo\n\n- Camera movement keywords\n- Cinematic language works well\n- Action descriptions important\n- Include temporal context\n\n## Common Mistakes\n\n| Mistake | Problem | Fix |\n|---------|---------|-----|\n| Too vague | Unpredictable output | Add specifics |\n| Too long | Model loses focus | Prioritize key info |\n| Conflicting | Confuses model | Remove contradictions |\n| No format | Inconsistent output | Specify format |\n| No examples | Unclear expectations | Add few-shot |\n\n## Prompt Templates\n\n### Code Review\n\n```\nReview this [language] code for:\n1. Bugs and logic errors\n2. Security vulnerabilities\n3. Performance issues\n4. Code style\u002Fbest practices\n\nCode:\n[code]\n\nFor each issue found, provide:\n- Line number\n- Issue description\n- Severity (high\u002Fmedium\u002Flow)\n- Suggested fix\n```\n\n### Content Writing\n\n```\nWrite a [content type] about [topic].\n\nAudience: [target audience]\nTone: [formal\u002Fcasual\u002Fprofessional]\nLength: [word count]\nKey points to cover:\n1. [point 1]\n2. [point 2]\n3. [point 3]\n\nInclude: [specific elements]\nAvoid: [things to exclude]\n```\n\n### Image Generation\n\n```\n[Subject with details], [setting\u002Fbackground], [lighting type],\n[art style or photography style], [composition], [quality keywords]\n```\n\n## Related Skills\n\n```bash\n# Video prompting guide\nnpx skills add inference-sh\u002Fagent-skills@video-prompting-guide\n\n# LLM models\nnpx skills add inference-sh\u002Fagent-skills@llm-models\n\n# Image generation\nnpx skills add inference-sh\u002Fagent-skills@ai-image-generation\n\n# Full platform skill\nnpx skills add inference-sh\u002Fagent-skills@inference-sh\n```\n\nBrowse all apps: `infsh app list`\n",{"name":5,"description":51,"allowed-tools":52},"Master prompt engineering for AI models: LLMs, image generators, video models.\nTechniques: chain-of-thought, few-shot, system prompts, negative prompts.\nModels: Claude, GPT-4, Gemini, FLUX, Veo, Stable Diffusion prompting.\nUse for: better AI outputs, consistent results, complex tasks, optimization.\nTriggers: prompt engineering, how to prompt, better prompts, prompt tips,\nprompting guide, llm prompting, image prompt, ai prompting, prompt optimization,\nprompt template, prompt structure, effective prompts, prompt techniques\n","Bash(infsh *)","main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fokaris\u002Fprompt-engineering",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add kbarbel640-del\u002Fskills --skill prompt-engineering",{"tool":66,"command":67},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill prompt-engineering",{"tool":69,"command":70},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill prompt-engineering","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fokaris\u002Fprompt-engineering\u002FSKILL.md",true,[74],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"_meta.json","REFERENCE","参考文档",288,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fokaris\u002Fprompt-engineering\u002F_meta.json",[81,112,137,158,164,184],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":92,"publishedAt":46},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":119,"publishedAt":46},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[118],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[120,95,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,100,136],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking","use",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":146,"publishedAt":46},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[143],{"categoryNo":144,"categoryName":145,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[147,148,149,150,151,152,153,96,154,134,136,155,95,156,157],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":159,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":163,"publishedAt":46},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[162],{"categoryNo":144,"categoryName":145,"taxonomyType":20,"taxonomyTypeDesc":21},[150,149,148,147,157,152,153,96,151,134,136,154,155,95,156],{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":170,"publishedAt":46},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[171,172,173,174,175,176,177,178,179,180,181,182,183],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":194,"publishedAt":46},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[190,191],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":192,"categoryName":193,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000037","律师与法务",[195,196,197,198,96,199,200,53,201,155,202,203,204,205,206,109,207,208,209],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]