[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75HPRCTZZMY7KP690P41RZS":3,"skill-same:01M75HPRCTZZMY7KP690P41RZS":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M75HPRCTZZMY7KP690P41RZS","perplexity-research",null,"Conduct deep research using Perplexity Agent API with web search, reasoning, and multi-model analysis. Use when the user needs current information, market research, trend analysis, investment insights, or comprehensive research on any topic requiring web search and reasoning capabilities.","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fhushenglang\u002Fperplexity-research\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: perplexity-research\nversion: 2.0.0\ndescription: Conduct deep research using Perplexity Agent API with web search, reasoning, and multi-model analysis. Use when the user needs current information, market research, trend analysis, investment insights, or comprehensive research on any topic requiring web search and reasoning capabilities.\n---\n\n# Perplexity Research\n\nResearch assistant powered by Perplexity Agent API with web search and reasoning capabilities.\n\n## Quick Start\n\nThe Perplexity client is available at `scripts\u002Fperplexity_client.py` in this skill folder.\n\n**Default model**: `openai\u002Fgpt-5.2` (GPT latest)\n\n**Key capabilities**:\n- Web search for current information\n- High reasoning effort for deep analysis\n- Multi-model comparison\n- Streaming responses\n- Cost tracking\n\n## Common Research Patterns\n\n### 1. Deep Research Query\n\nUse for comprehensive analysis requiring web search and reasoning:\n\n```python\n# Import from skill scripts folder\nimport sys\nfrom pathlib import Path\nsys.path.insert(0, str(Path(__file__).parent \u002F \"scripts\"))\nfrom perplexity_client import PerplexityClient\n\nclient = PerplexityClient()\nresult = client.research_query(\n    query=\"Your research question here\",\n    model=\"openai\u002Fgpt-5.2\",\n    reasoning_effort=\"high\",\n    max_tokens=2000\n)\n\nif \"error\" not in result:\n    print(result[\"answer\"])\n    print(f\"Tokens: {result['tokens']}, Cost: ${result['cost']}\")\n```\n\n### 2. Quick Web Search\n\nUse for time-sensitive or current information:\n\n```python\nresult = client.search_query(\n    query=\"Your question about current events\",\n    model=\"openai\u002Fgpt-5.2\",\n    max_tokens=1000\n)\n```\n\n### 3. Model Comparison\n\nUse when output quality is critical:\n\n```python\nresults = client.compare_models(\n    query=\"Your question\",\n    models=[\"openai\u002Fgpt-5.2\", \"anthropic\u002Fclaude-3-5-sonnet\", \"google\u002Fgemini-2.0-flash\"],\n    max_tokens=300\n)\n\nfor result in results:\n    if \"error\" not in result:\n        print(f\"\\n{result['model']}: {result['answer']}\")\n```\n\n### 4. Streaming for Long Responses\n\nUse for better UX with lengthy analysis:\n\n```python\nclient.stream_query(\n    query=\"Your question\",\n    model=\"openai\u002Fgpt-5.2\",\n    use_search=True,\n    max_tokens=2000\n)\n```\n\n## Research Workflow\n\nWhen conducting research:\n\n1. **Initial exploration**: Use `research_query()` with web search enabled\n2. **Validate findings**: Compare key insights across models with `compare_models()`\n3. **Deep dive**: Use streaming for detailed analysis on specific aspects\n4. **Cost-aware**: Monitor token usage and costs in results\n\n## Model Selection\n\n**Default: `openai\u002Fgpt-5.2`** (Latest GPT model)\n\nAlternative models:\n- `anthropic\u002Fclaude-3-5-sonnet` - Strong reasoning, balanced performance\n- `google\u002Fgemini-2.0-flash` - Fast, cost-effective\n- `meta\u002Fllama-3.3-70b` - Open source alternative\n\nSwitch models based on:\n- Quality needs (GPT-5.2 for best results)\n- Speed requirements (Gemini Flash for quick answers)\n- Cost constraints (compare costs in results)\n\n## Reasoning Effort Levels\n\nControl analysis depth with `reasoning_effort`:\n\n- `\"low\"` - Quick answers, minimal reasoning\n- `\"medium\"` - Balanced reasoning (default for most queries)\n- `\"high\"` - Deep analysis, comprehensive research (recommended for research)\n\n## Environment Setup\n\nEnsure `PERPLEXITY_API_KEY` is set:\n\n```bash\nexport PERPLEXITY_API_KEY='your_api_key_here'\n```\n\nOr create `.env` file in the skill's `scripts\u002F` directory:\n\n```\nPERPLEXITY_API_KEY=your_api_key_here\n```\n\n## Error Handling\n\nAll methods return error information:\n\n```python\nresult = client.research_query(\"Your question\")\n\nif \"error\" in result:\n    print(f\"Error: {result['error']}\")\n    # Handle error appropriately\nelse:\n    # Process successful result\n    print(result[\"answer\"])\n```\n\n## Cost Optimization\n\n- Use `max_tokens` to limit response length\n- Start with lower reasoning effort, increase if needed\n- Use `search_query()` instead of `research_query()` for simpler questions\n- Monitor costs via `result[\"cost\"]` field\n\n## Integration Examples\n\n### Investment Research\n\n```python\nclient = PerplexityClient()\n\n# Market analysis\nresult = client.research_query(\n    query=\"Analyze recent developments in AI chip market and key competitors\",\n    reasoning_effort=\"high\"\n)\n\n# Company deep dive\nresult = client.search_query(\n    query=\"Latest earnings report for NVIDIA Q4 2025\"\n)\n\n# Multi-model validation\nresults = client.compare_models(\n    query=\"What are the biggest risks in the semiconductor industry?\",\n    models=[\"openai\u002Fgpt-5.2\", \"anthropic\u002Fclaude-3-5-sonnet\"]\n)\n```\n\n### Trend Analysis\n\n```python\n# Current trends with web search\nresult = client.research_query(\n    query=\"Emerging trends in sustainable investing and ESG adoption rates\",\n    reasoning_effort=\"high\",\n    max_tokens=2000\n)\n\n# Stream for real-time updates\nclient.stream_query(\n    query=\"Latest developments in quantum computing commercialization\",\n    use_search=True\n)\n```\n\n### Multi-Turn Research\n\n```python\n# Build context across multiple queries\nmessages = [\n    {\"role\": \"user\", \"content\": \"What is the current state of fusion energy?\"},\n    {\"role\": \"assistant\", \"content\": \"...previous response...\"},\n    {\"role\": \"user\", \"content\": \"Which companies are leading in this space?\"}\n]\n\nresult = client.conversation(\n    messages=messages,\n    use_search=True\n)\n```\n\n## Best Practices\n\n1. **Default to research_query()** for most research tasks - it combines web search with high reasoning\n2. **Use streaming** for user-facing applications to show progress\n3. **Compare models** for critical decisions or when quality is paramount\n4. **Set reasonable max_tokens** - 1000 for summaries, 2000+ for deep analysis\n5. **Track costs** - access via `result[\"cost\"]` and `result[\"tokens\"]`\n6. **Handle errors gracefully** - always check for \"error\" key in results\n\n## API Reference\n\nSee [reference.md](reference.md) for complete API documentation, or `scripts\u002Fperplexity_client.py` for:\n- Full method signatures\n- Additional parameters\n- CLI usage examples\n- Implementation details\n\n## Command Line Usage\n\nRun from the skill directory:\n\n```bash\n# Research mode\npython scripts\u002Fperplexity_client.py research \"Your question\"\n\n# Web search\npython scripts\u002Fperplexity_client.py search \"Your question\"\n\n# Streaming\npython scripts\u002Fperplexity_client.py stream \"Your question\"\n\n# Compare models\npython scripts\u002Fperplexity_client.py compare \"Your question\"\n```\n","# Perplexity Research\n\nResearch assistant powered by Perplexity Agent API with web search and reasoning capabilities.\n\n## Quick Start\n\nThe Perplexity client is available at `scripts\u002Fperplexity_client.py` in this skill folder.\n\n**Default model**: `openai\u002Fgpt-5.2` (GPT latest)\n\n**Key capabilities**:\n- Web search for current information\n- High reasoning effort for deep analysis\n- Multi-model comparison\n- Streaming responses\n- Cost tracking\n\n## Common Research Patterns\n\n### 1. Deep Research Query\n\nUse for comprehensive analysis requiring web search and reasoning:\n\n```python\n# Import from skill scripts folder\nimport sys\nfrom pathlib import Path\nsys.path.insert(0, str(Path(__file__).parent \u002F \"scripts\"))\nfrom perplexity_client import PerplexityClient\n\nclient = PerplexityClient()\nresult = client.research_query(\n    query=\"Your research question here\",\n    model=\"openai\u002Fgpt-5.2\",\n    reasoning_effort=\"high\",\n    max_tokens=2000\n)\n\nif \"error\" not in result:\n    print(result[\"answer\"])\n    print(f\"Tokens: {result['tokens']}, Cost: ${result['cost']}\")\n```\n\n### 2. Quick Web Search\n\nUse for time-sensitive or current information:\n\n```python\nresult = client.search_query(\n    query=\"Your question about current events\",\n    model=\"openai\u002Fgpt-5.2\",\n    max_tokens=1000\n)\n```\n\n### 3. Model Comparison\n\nUse when output quality is critical:\n\n```python\nresults = client.compare_models(\n    query=\"Your question\",\n    models=[\"openai\u002Fgpt-5.2\", \"anthropic\u002Fclaude-3-5-sonnet\", \"google\u002Fgemini-2.0-flash\"],\n    max_tokens=300\n)\n\nfor result in results:\n    if \"error\" not in result:\n        print(f\"\\n{result['model']}: {result['answer']}\")\n```\n\n### 4. Streaming for Long Responses\n\nUse for better UX with lengthy analysis:\n\n```python\nclient.stream_query(\n    query=\"Your question\",\n    model=\"openai\u002Fgpt-5.2\",\n    use_search=True,\n    max_tokens=2000\n)\n```\n\n## Research Workflow\n\nWhen conducting research:\n\n1. **Initial exploration**: Use `research_query()` with web search enabled\n2. **Validate findings**: Compare key insights across models with `compare_models()`\n3. **Deep dive**: Use streaming for detailed analysis on specific aspects\n4. **Cost-aware**: Monitor token usage and costs in results\n\n## Model Selection\n\n**Default: `openai\u002Fgpt-5.2`** (Latest GPT model)\n\nAlternative models:\n- `anthropic\u002Fclaude-3-5-sonnet` - Strong reasoning, balanced performance\n- `google\u002Fgemini-2.0-flash` - Fast, cost-effective\n- `meta\u002Fllama-3.3-70b` - Open source alternative\n\nSwitch models based on:\n- Quality needs (GPT-5.2 for best results)\n- Speed requirements (Gemini Flash for quick answers)\n- Cost constraints (compare costs in results)\n\n## Reasoning Effort Levels\n\nControl analysis depth with `reasoning_effort`:\n\n- `\"low\"` - Quick answers, minimal reasoning\n- `\"medium\"` - Balanced reasoning (default for most queries)\n- `\"high\"` - Deep analysis, comprehensive research (recommended for research)\n\n## Environment Setup\n\nEnsure `PERPLEXITY_API_KEY` is set:\n\n```bash\nexport PERPLEXITY_API_KEY='your_api_key_here'\n```\n\nOr create `.env` file in the skill's `scripts\u002F` directory:\n\n```\nPERPLEXITY_API_KEY=your_api_key_here\n```\n\n## Error Handling\n\nAll methods return error information:\n\n```python\nresult = client.research_query(\"Your question\")\n\nif \"error\" in result:\n    print(f\"Error: {result['error']}\")\n    # Handle error appropriately\nelse:\n    # Process successful result\n    print(result[\"answer\"])\n```\n\n## Cost Optimization\n\n- Use `max_tokens` to limit response length\n- Start with lower reasoning effort, increase if needed\n- Use `search_query()` instead of `research_query()` for simpler questions\n- Monitor costs via `result[\"cost\"]` field\n\n## Integration Examples\n\n### Investment Research\n\n```python\nclient = PerplexityClient()\n\n# Market analysis\nresult = client.research_query(\n    query=\"Analyze recent developments in AI chip market and key competitors\",\n    reasoning_effort=\"high\"\n)\n\n# Company deep dive\nresult = client.search_query(\n    query=\"Latest earnings report for NVIDIA Q4 2025\"\n)\n\n# Multi-model validation\nresults = client.compare_models(\n    query=\"What are the biggest risks in the semiconductor industry?\",\n    models=[\"openai\u002Fgpt-5.2\", \"anthropic\u002Fclaude-3-5-sonnet\"]\n)\n```\n\n### Trend Analysis\n\n```python\n# Current trends with web search\nresult = client.research_query(\n    query=\"Emerging trends in sustainable investing and ESG adoption rates\",\n    reasoning_effort=\"high\",\n    max_tokens=2000\n)\n\n# Stream for real-time updates\nclient.stream_query(\n    query=\"Latest developments in quantum computing commercialization\",\n    use_search=True\n)\n```\n\n### Multi-Turn Research\n\n```python\n# Build context across multiple queries\nmessages = [\n    {\"role\": \"user\", \"content\": \"What is the current state of fusion energy?\"},\n    {\"role\": \"assistant\", \"content\": \"...previous response...\"},\n    {\"role\": \"user\", \"content\": \"Which companies are leading in this space?\"}\n]\n\nresult = client.conversation(\n    messages=messages,\n    use_search=True\n)\n```\n\n## Best Practices\n\n1. **Default to research_query()** for most research tasks - it combines web search with high reasoning\n2. **Use streaming** for user-facing applications to show progress\n3. **Compare models** for critical decisions or when quality is paramount\n4. **Set reasonable max_tokens** - 1000 for summaries, 2000+ for deep analysis\n5. **Track costs** - access via `result[\"cost\"]` and `result[\"tokens\"]`\n6. **Handle errors gracefully** - always check for \"error\" key in results\n\n## API Reference\n\nSee [reference.md](reference.md) for complete API documentation, or `scripts\u002Fperplexity_client.py` for:\n- Full method signatures\n- Additional parameters\n- CLI usage examples\n- Implementation details\n\n## Command Line Usage\n\nRun from the skill directory:\n\n```bash\n# Research mode\npython scripts\u002Fperplexity_client.py research \"Your question\"\n\n# Web search\npython scripts\u002Fperplexity_client.py search \"Your question\"\n\n# Streaming\npython scripts\u002Fperplexity_client.py stream \"Your question\"\n\n# Compare models\npython scripts\u002Fperplexity_client.py compare \"Your question\"\n```\n",{"name":5,"version":24,"description":7},"2.0.0","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fhushenglang\u002Fperplexity-research",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill perplexity-research",{"tool":40,"command":41},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill perplexity-research",{"tool":43,"command":44},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill perplexity-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fhushenglang\u002Fperplexity-research\u002FSKILL.md",true,[],[49,57,64,71,78,85],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":56},"01M778GGXG2VQ0YF31W2MKGMQZ","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\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":56},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":56},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":56},"01M778FQQNSEYA3HJKZBPQ4M9Z","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\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":56},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":56},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]