[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FS1Y9PRPJAT54DZBS0E8CF":3,"skill-same:01M6FS1Y9PRPJAT54DZBS0E8CF":117},{"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":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":62,"install":63,"resources":76},"01M6FS1Y9PRPJAT54DZBS0E8CF","nimble-web-search",null,"Real-time web intelligence powered by Nimble Search API. Perform intelligent web searches with 8 specialized focus modes (general, coding, news, academic, shopping, social, geo, location). This skill provides real-time search results when you need to search the web, find current information, discover URLs, research topics, or gather up-to-date data. Use when: searching for information, finding recent news, looking up academic papers, searching for coding examples, finding shopping results, discovering social media posts, researching topics, or getting latest real-time data.","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\u002Filchemla\u002Fnimble-web-search\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"search","nimble web search","web search","web","time","papers","posts","you","information","web intelligence","discover","focus","api","intelligence","social","shopping","up","specialized","data","Media","2026-11-10 10:12:30",false,"---\nname: nimble-web-search\ndescription: >\n  Real-time web intelligence powered by Nimble Search API. Perform intelligent web searches with 8 specialized focus modes (general, coding, news, academic, shopping, social, geo, location).\n  This skill provides real-time search results when you need to search the web, find current information, discover URLs, research topics, or gather up-to-date data.\n  Use when: searching for information, finding recent news, looking up academic papers, searching for coding examples, finding shopping results, discovering social media posts, researching topics, or getting latest real-time data.\nlicense: MIT\nmetadata:\n  version: \"0.1.0\"\n  author: Nimbleway\n  repository: https:\u002F\u002Fgithub.com\u002FNimbleway\u002Fagent-skills\n---\n\n# Nimble Web Search\n\nReal-time web intelligence using Nimble Search API with specialized focus modes and AI-powered result synthesis.\n\n## Prerequisites\n\n**Nimble API Key Required** - Get your key at https:\u002F\u002Fwww.nimbleway.com\u002F\n\n### Configuration\n\nSet the `NIMBLE_API_KEY` environment variable using your platform's method:\n\n**Claude Code:**\n```json\n\u002F\u002F ~\u002F.claude\u002Fsettings.json\n{\n  \"env\": {\n    \"NIMBLE_API_KEY\": \"your-api-key-here\"\n  }\n}\n```\n\n**VS Code\u002FGitHub Copilot:**\n- Add to `.github\u002Fskills\u002F` directory in your repository\n- Or use GitHub Actions secrets for the copilot environment\n\n**Shell\u002FTerminal:**\n```bash\nexport NIMBLE_API_KEY=\"your-api-key-here\"\n```\n\n**Any Platform:**\nThe skill checks for the `NIMBLE_API_KEY` environment variable regardless of how you set it.\n\n### API Key Validation\n\n**IMPORTANT: Before making any search request, verify the API key is configured:**\n\n```bash\n# Check if API key is set\nif [ -z \"$NIMBLE_API_KEY\" ]; then\n  echo \"❌ Error: NIMBLE_API_KEY not configured\"\n  echo \"\"\n  echo \"Get your API key: https:\u002F\u002Fwww.nimbleway.com\u002F\"\n  echo \"\"\n  echo \"Configure using your platform's method:\"\n  echo \"- Claude Code: Add to ~\u002F.claude\u002Fsettings.json\"\n  echo \"- GitHub Copilot: Use GitHub Actions secrets\"\n  echo \"- Shell: export NIMBLE_API_KEY=\\\"your-key\\\"\"\n  echo \"\"\n  echo \"Do NOT fall back to other search tools - guide the user to configure first.\"\n  exit 1\nfi\n```\n\n## Overview\n\nNimble Search provides real-time web intelligence with 8 specialized focus modes optimized for different types of queries. Get instant access to current web data with AI-powered answer generation, deep content extraction, URL discovery, and smart filtering by domain and date.\n\n**IMPORTANT: Always Specify These Parameters**\n\nWhen using this skill, **always explicitly set** the following parameters in your requests:\n\n- `deep_search`: **Default to `false`** for 5-10x faster responses\n  - **Use `false` (FAST MODE - 1-3 seconds):** For 95% of use cases - URL discovery, research, comparisons, answer generation\n  - **Use `true` (DEEP MODE - 5-15 seconds):** Only when you specifically need full page content extracted for archiving or detailed analysis\n\n- `focus`: **Default to `\"general\"`** for broad searches\n  - Change to specific mode (`coding`, `news`, `academic`, `shopping`, `social`, `geo`, `location`) for targeted results\n\n- `max_results`: **Default to `10`** - Balanced speed and coverage\n\n**Performance Awareness:** By explicitly setting `deep_search: false`, you're choosing fast mode and should expect results in 1-3 seconds. If you set `deep_search: true`, expect 5-15 seconds response time.\n\n### Quick Start\n\nUse the wrapper script for the simplest experience:\n\n```bash\n# ALWAYS specify deep_search explicitly\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"React hooks\",\n  \"deep_search\": false\n}'\n```\n\nThe script automatically handles authentication, tracking headers, and output formatting.\n\n### When to Use Each Mode\n\n**Use `deep_search: false` (FAST MODE - 1-3 seconds) - Default for 95% of cases:**\n- ✅ Finding URLs and discovering resources\n- ✅ Research and topic exploration\n- ✅ Answer generation and summaries\n- ✅ Product comparisons\n- ✅ News monitoring\n- ✅ Any time you DON'T need full article text\n\n**Use `deep_search: true` (DEEP MODE - 5-15 seconds) - Only when specifically needed:**\n- ? Archiving full article content\n- ? Extracting complete documentation\n- ? Building text datasets\n- ? Processing full page content for analysis\n\n**Decision Rule:** If you're not sure, use `deep_search: false`. You can always re-run with `true` if needed.\n\n## Core Capabilities\n\n### Focus Modes\n\nChoose the appropriate focus mode based on your query type:\n\n1. **general** - Default mode for broad web searches\n2. **coding** - Real-time access to technical documentation, code examples, programming resources\n3. **news** - Real-time news articles, current events, breaking stories\n4. **academic** - Research papers, scholarly articles, academic resources\n5. **shopping** - Real-time product searches, e-commerce results, price comparisons\n6. **social** - Real-time social media posts, discussions, trending community content\n7. **geo** - Location-based searches, geographic information\n8. **location** - Local business searches, place-specific queries\n\n### Search Features\n\n**LLM Answer Generation**\n- Request AI-generated answers synthesized from search results\n- Powered by Claude for high-quality summaries\n- Include citations to source URLs\n- Best for: Research questions, topic overviews, comparative analysis\n\n**URL Discovery**\n- Extract 1-20 most relevant URLs for a query\n- Useful for building reading lists and reference collections\n- Returns URLs with titles and descriptions\n- Best for: Resource gathering, link building, research preparation\n\n**Deep Content Extraction**\n- **Default (Recommended):** `deep_search=false` - Fastest response, returns titles, descriptions, and URLs\n- **Optional:** `deep_search=true` - Slower, extracts full page content\n- **Important:** Most use cases work perfectly with `deep_search=false` (the default)\n- Available formats when deep_search=true: markdown, plain_text, simplified_html\n- Only enable deep search for: Detailed content analysis, archiving, or comprehensive text extraction needs\n\n**Domain Filtering**\n- Include specific domains (e.g., github.com, stackoverflow.com)\n- Exclude domains to remove unwanted sources\n- Combine multiple domains for focused searches\n- Best for: Targeted research, brand monitoring, competitive analysis\n\n**Time Filtering**\n- **Recommended:** Use `time_range` for real-time recency filtering (hour, day, week, month, year)\n- **Alternative:** Use `start_date`\u002F`end_date` for precise date ranges (YYYY-MM-DD)\n- Note: `time_range` and date filters are mutually exclusive\n- Best for: Real-time news monitoring, recent developments, temporal analysis\n\n## Usage Patterns\n\nAll examples below use the `.\u002Fscripts\u002Fsearch.sh` wrapper for simplicity. For raw API usage, see the [API Integration](#api-integration) section.\n\n### Basic Search\n\nQuick search in fast mode (ALWAYS specify deep_search explicitly):\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"React Server Components tutorial\",\n  \"deep_search\": false\n}'\n```\n\nFor technical content, specify coding focus (still fast mode):\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"React Server Components tutorial\",\n  \"focus\": \"coding\",\n  \"deep_search\": false\n}'\n```\n\n### Research with AI Summary\n\nGet synthesized insights from multiple sources (fast mode works great with answer generation):\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"impact of AI on software development 2026\",\n  \"deep_search\": false,\n  \"include_answer\": true\n}'\n```\n\n### Domain-Specific Search\n\nTarget specific authoritative sources (fast mode):\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"async await patterns\",\n  \"focus\": \"coding\",\n  \"deep_search\": false,\n  \"include_domains\": [\"github.com\", \"stackoverflow.com\", \"dev.to\"],\n  \"max_results\": 8\n}'\n```\n\n### Real-Time News Monitoring\n\nTrack current events and breaking news as they happen (fast mode):\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"latest developments in quantum computing\",\n  \"focus\": \"news\",\n  \"deep_search\": false,\n  \"time_range\": \"week\",\n  \"max_results\": 15,\n  \"include_answer\": true\n}'\n```\n\n### Academic Research - Fast Mode (Recommended)\n\nFind and synthesize scholarly content using fast mode:\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"machine learning interpretability methods\",\n  \"focus\": \"academic\",\n  \"deep_search\": false,\n  \"max_results\": 20,\n  \"include_answer\": true\n}'\n```\n\n**When to use deep mode:** Only use `\"deep_search\": true` if you need full paper content extracted for archiving:\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"machine learning interpretability methods\",\n  \"focus\": \"academic\",\n  \"deep_search\": true,\n  \"max_results\": 5,\n  \"output_format\": \"markdown\"\n}'\n```\n**Note:** Deep mode is 5-15x slower. Use only when specifically needed.\n\n### Real-Time Shopping Research\n\nCompare products and current prices (fast mode):\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"best mechanical keyboards for programming\",\n  \"focus\": \"shopping\",\n  \"deep_search\": false,\n  \"max_results\": 10,\n  \"include_answer\": true\n}'\n```\n\n## Parallel Search Strategies\n\n### When to Use Parallel Searches\n\nRun multiple real-time searches in parallel when:\n- **Comparing perspectives**: Search the same topic across different focus modes\n- **Multi-faceted research**: Investigate different aspects of a topic simultaneously\n- **Competitive analysis**: Search multiple domains or competitors at once\n- **Real-time monitoring**: Track multiple topics or keywords concurrently\n- **Cross-validation**: Verify information across different source types in real-time\n\n### Implementation Methods\n\n**Method 1: Background Processes (Recommended)**\n\nRun multiple searches concurrently using the wrapper script:\n\n```bash\n# Start multiple searches in parallel\n.\u002Fscripts\u002Fsearch.sh '{\"query\": \"React\", \"focus\": \"coding\"}' > react_coding.json &\n.\u002Fscripts\u002Fsearch.sh '{\"query\": \"React\", \"focus\": \"news\"}' > react_news.json &\n.\u002Fscripts\u002Fsearch.sh '{\"query\": \"React\", \"focus\": \"academic\"}' > react_academic.json &\n\n# Wait for all to complete\nwait\n\n# Combine results\njq -s '.' react_*.json > combined_results.json\n```\n\n**Method 2: Loop with xargs (Controlled Parallelism)**\n\nProcess multiple queries with rate limiting:\n\n```bash\n# Create queries file\ncat > queries.txt \u003C\u003CEOF\n{\"query\": \"AI frameworks\", \"focus\": \"coding\"}\n{\"query\": \"AI regulation\", \"focus\": \"news\"}\n{\"query\": \"AI research\", \"focus\": \"academic\"}\nEOF\n\n# Run with max 3 parallel processes\ncat queries.txt | xargs -n1 -P3 -I{} .\u002Fscripts\u002Fsearch.sh '{}'\n```\n\n**Method 3: Focus Mode Comparison**\n\nSearch the same query across different focus modes:\n\n```bash\nQUERY=\"artificial intelligence trends\"\n\nfor focus in \"general\" \"coding\" \"news\" \"academic\"; do\n  (\n    .\u002Fscripts\u002Fsearch.sh \"{\\\"query\\\": \\\"$QUERY\\\", \\\"focus\\\": \\\"$focus\\\"}\" \\\n      > \"${focus}_results.json\"\n  ) &\ndone\n\nwait\necho \"All searches complete!\"\n```\n\n### Best Practices for Parallel Execution\n\n1. **Rate Limiting**: Limit parallel requests to 3-5 to avoid overwhelming the API\n   - Use `xargs -P3` to set maximum concurrent requests\n   - Check your API tier limits before increasing parallelism\n\n2. **Error Handling**: Capture and handle failures gracefully\n   ```bash\n   .\u002Fscripts\u002Fsearch.sh '{\"query\": \"test\"}' || echo \"Search failed\" >> errors.log\n   ```\n\n3. **Result Aggregation**: Combine results after all searches complete\n   ```bash\n   # Wait for all searches\n   wait\n\n   # Merge JSON results\n   jq -s 'map(.results) | flatten' result*.json > combined.json\n   ```\n\n4. **Progress Tracking**: Monitor completion status\n   ```bash\n   echo \"Running 5 parallel searches...\"\n\n   for i in {1..5}; do\n     .\u002Fscripts\u002Fsearch.sh \"{\\\"query\\\": \\\"query$i\\\"}\" > \"result$i.json\" &\n   done\n\n   wait\n   echo \"All searches complete!\"\n   ```\n\n### Example: Multi-Perspective Research\n\n```bash\n#!\u002Fbin\u002Fbash\n# Research a topic across multiple focus modes simultaneously\n\nQUERY=\"artificial intelligence code generation\"\nOUTPUT_DIR=\".\u002Fsearch_results\"\nmkdir -p \"$OUTPUT_DIR\"\n\n# Run searches in parallel across different focus modes\nfor focus in \"general\" \"coding\" \"news\" \"academic\"; do\n  (\n    .\u002Fscripts\u002Fsearch.sh \"{\n      \\\"query\\\": \\\"$QUERY\\\",\n      \\\"focus\\\": \\\"$focus\\\",\n      \\\"max_results\\\": 10\n    }\" > \"$OUTPUT_DIR\u002F${focus}_results.json\"\n  ) &\ndone\n\n# Wait for all searches to complete\nwait\n\n# Aggregate and analyze results\njq -s '{\n  general: .[0].results,\n  coding: .[1].results,\n  news: .[2].results,\n  academic: .[3].results\n}' \"$OUTPUT_DIR\"\u002F*.json > \"$OUTPUT_DIR\u002Fcombined_analysis.json\"\n\necho \"✓ Multi-perspective search complete\"\n```\n\n### Performance Considerations\n\n- **Optimal Parallelism**: 3-5 concurrent requests balances speed and API limits\n- **Memory Usage**: Each parallel request consumes memory; monitor for large result sets\n- **Network Bandwidth**: Parallel requests can saturate bandwidth on slow connections\n- **API Costs**: More parallel requests = faster API quota consumption\n\n### When NOT to Use Parallel Searches\n\n- Single, focused query with one clear answer\n- Sequential research where each search informs the next\n- API quota is limited or expensive\n- Results need to be processed before next search\n- Simple URL collection that doesn't require multiple perspectives\n\n## API Integration\n\n**Note:** For most use cases, use the `.\u002Fscripts\u002Fsearch.sh` wrapper script shown in [Usage Patterns](#usage-patterns). The raw API examples below are for advanced users who need direct API access or custom integration.\n\n### Required Configuration\n\n**Before making any API request, always validate the API key is configured:**\n\n```bash\n# Validate API key is set\nif [ -z \"$NIMBLE_API_KEY\" ]; then\n  echo \"❌ Nimble API key not configured.\"\n  echo \"Get your key at https:\u002F\u002Fwww.nimbleway.com\u002F\"\n  echo \"\"\n  echo \"Set NIMBLE_API_KEY environment variable using your platform's method.\"\n  exit 1\nfi\n```\n\nThe skill requires the `NIMBLE_API_KEY` environment variable. See [Prerequisites](#prerequisites) for platform-specific setup instructions.\n\nGet your API key at: https:\u002F\u002Fwww.nimbleway.com\u002F\n\n### API Endpoint\n\n```\nPOST https:\u002F\u002Fnimble-retriever.webit.live\u002Fsearch\n```\n\n### Request Format\n\n```json\n{\n  \"query\": \"search query string\",  \u002F\u002F REQUIRED\n  \"focus\": \"general\",  \u002F\u002F OPTIONAL: default \"general\" | coding|news|academic|shopping|social|geo|location\n  \"max_results\": 10,  \u002F\u002F OPTIONAL: default 10 (range: 1-100)\n  \"include_answer\": false,  \u002F\u002F OPTIONAL: default false\n  \"deep_search\": false,  \u002F\u002F OPTIONAL: default false (RECOMMENDED: keep false for speed)\n  \"output_format\": \"markdown\",  \u002F\u002F OPTIONAL: default \"markdown\" | plain_text|simplified_html\n  \"include_domains\": [\"domain1.com\"],  \u002F\u002F OPTIONAL: default [] (no filter)\n  \"exclude_domains\": [\"domain3.com\"],  \u002F\u002F OPTIONAL: default [] (no filter)\n  \"time_range\": \"week\",  \u002F\u002F OPTIONAL: hour|day|week|month|year\n  \"start_date\": \"2026-01-01\",  \u002F\u002F OPTIONAL: Use time_range OR start_date\u002Fend_date (not both)\n  \"end_date\": \"2026-12-31\"  \u002F\u002F OPTIONAL\n}\n```\n\n**Key Defaults:**\n- `focus`: `\"general\"` - Change to specific mode for targeted results\n- `deep_search`: `false` - Keep false unless you need full page content\n- `max_results`: `10` - Balanced speed and coverage\n\n### Response Format\n\n```json\n{\n  \"results\": [\n    {\n      \"url\": \"https:\u002F\u002Fexample.com\u002Fpage\",\n      \"title\": \"Page Title\",\n      \"description\": \"Page description\",\n      \"content\": \"Full page content (if deep_search=true)\",\n      \"published_date\": \"2026-01-15\"\n    }\n  ],\n  \"include_answer\": \"AI-generated summary (if include_answer=true)\",\n  \"urls\": [\"url1\", \"url2\", \"url3\"],\n  \"total_results\": 10\n}\n```\n\n## Best Practices\n\n### Focus Mode Selection\n\n**Use `coding` for:**\n- Programming questions\n- Technical documentation\n- Code examples and tutorials\n- API references\n- Framework guides\n\n**Use `news` for:**\n- Real-time current events\n- Breaking stories as they happen\n- Recent announcements\n- Trending topics\n- Time-sensitive information\n\n**Use `academic` for:**\n- Research papers\n- Scholarly articles\n- Scientific studies\n- Academic journals\n- Citations and references\n\n**Use `shopping` for:**\n- Product searches\n- Price comparisons\n- E-commerce research\n- Product reviews\n- Buying guides\n\n**Use `social` for:**\n- Real-time social media monitoring\n- Live community discussions\n- Current user-generated content\n- Trending hashtags and topics\n- Real-time public sentiment\n\n**Use `geo` for:**\n- Geographic information\n- Regional data\n- Maps and locations\n- Area-specific queries\n\n**Use `location` for:**\n- Local business searches\n- Place-specific information\n- Nearby services\n- Regional recommendations\n\n### Result Limits\n\n- **Quick searches**: 5-10 results for fast overview\n- **Comprehensive research**: 15-20 results for depth\n- **Answer generation**: 10-15 results for balanced synthesis\n- **URL collection**: 20 results for comprehensive resource list\n\n### When to Use LLM Answers\n\n✅ **Use LLM answers when:**\n- You need a synthesized overview of a topic\n- Comparing multiple sources or approaches\n- Summarizing recent developments\n- Answering specific questions\n- Creating research summaries\n\n❌ **Skip LLM answers when:**\n- You just need a list of URLs\n- Building a reference collection\n- Speed is critical\n- You want to analyze sources manually\n- Original source text is needed\n\n### Content Extraction\n\n**Default (Recommended): `deep_search=false`**\n\nThe default setting works for 95% of use cases:\n- ✅ Fastest response times\n- ✅ Returns titles, descriptions, URLs\n- ✅ Works perfectly with `include_answer=true`\n- ✅ Sufficient for research, comparisons, and URL discovery\n\n**Only use `deep_search=true` when you specifically need:**\n- Full page content extraction\n- Archiving complete articles\n- Processing full text for analysis\n- Building comprehensive datasets\n\n**Performance impact:**\n- `deep_search=false`: ~1-3 seconds\n- `deep_search=true`: ~5-15 seconds (significantly slower)\n\n## Error Handling\n\n### Common Issues\n\n**Authentication Failed**\n- Verify NIMBLE_API_KEY is set correctly\n- Check API key is active at nimbleway.com\n- Ensure key has search API access\n\n**Rate Limiting**\n- Reduce max_results\n- Add delays between requests\n- Check your plan limits\n- Consider upgrading API tier\n\n**No Results**\n- Try different focus mode\n- Broaden search query\n- Remove domain filters\n- Adjust date filters\n\n**Timeout Errors**\n- Reduce max_results\n- Disable deep content extraction\n- Simplify query\n- Try again after brief delay\n\n## Performance Tips\n\n1. **Use Defaults**: Keep `deep_search=false` (default) for 5-10x faster responses\n2. **Start Simple**: Begin with just `{\"query\": \"...\"}` - defaults work great\n3. **Choose Right Focus**: Proper focus mode dramatically improves relevance (default: \"general\")\n4. **Optimize Result Count**: Default of 10 results balances speed and coverage\n5. **Domain Filtering**: Pre-filter sources for faster, more relevant results\n6. **Avoid Deep Search**: Only enable `deep_search=true` when you truly need full content\n7. **Batch Queries**: Group related searches to minimize API calls\n8. **Cache Results**: Store results locally when appropriate\n\n## Integration Examples\n\nSee the `examples\u002F` directory for detailed integration patterns:\n- `basic-search.md` - Simple search implementation\n- `deep-research.md` - Multi-step research workflow\n- `competitive-analysis.md` - Domain-specific research pattern\n\nSee `references\u002F` directory for detailed documentation:\n- `focus-modes.md` - Complete focus mode guide\n- `search-strategies.md` - Advanced search patterns\n- `api-reference.md` - Full API documentation\n\n## Scripts\n\n### search.sh - Main Search Wrapper\n\nThe recommended way to use the Nimble Search API:\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\"query\": \"your search\", \"focus\": \"coding\"}'\n```\n\n**Features:**\n- Automatic authentication with `$NIMBLE_API_KEY`\n- Platform detection (claude-code, github-copilot, vscode, cli)\n- Request tracking headers for analytics\n- JSON validation and error handling\n- Formatted output with `jq`\n\n**Usage:**\n```bash\n# Basic search\n.\u002Fscripts\u002Fsearch.sh '{\"query\": \"React hooks\"}'\n\n# With all options\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"AI frameworks\",\n  \"focus\": \"coding\",\n  \"max_results\": 15,\n  \"include_answer\": true,\n  \"include_domains\": [\"github.com\"]\n}'\n```\n\n### validate-query.sh - API Configuration Test\n\nTest your API configuration and connectivity:\n\n```bash\n.\u002Fscripts\u002Fvalidate-query.sh \"test query\" general\n```\n\nThis verifies:\n- API key is configured\n- Endpoint is accessible\n- Response format is correct\n- Focus mode is supported\n\n","# Nimble Web Search\n\nReal-time web intelligence using Nimble Search API with specialized focus modes and AI-powered result synthesis.\n\n## Prerequisites\n\n**Nimble API Key Required** - Get your key at https:\u002F\u002Fwww.nimbleway.com\u002F\n\n### Configuration\n\nSet the `NIMBLE_API_KEY` environment variable using your platform's method:\n\n**Claude Code:**\n```json\n\u002F\u002F ~\u002F.claude\u002Fsettings.json\n{\n  \"env\": {\n    \"NIMBLE_API_KEY\": \"your-api-key-here\"\n  }\n}\n```\n\n**VS Code\u002FGitHub Copilot:**\n- Add to `.github\u002Fskills\u002F` directory in your repository\n- Or use GitHub Actions secrets for the copilot environment\n\n**Shell\u002FTerminal:**\n```bash\nexport NIMBLE_API_KEY=\"your-api-key-here\"\n```\n\n**Any Platform:**\nThe skill checks for the `NIMBLE_API_KEY` environment variable regardless of how you set it.\n\n### API Key Validation\n\n**IMPORTANT: Before making any search request, verify the API key is configured:**\n\n```bash\n# Check if API key is set\nif [ -z \"$NIMBLE_API_KEY\" ]; then\n  echo \"❌ Error: NIMBLE_API_KEY not configured\"\n  echo \"\"\n  echo \"Get your API key: https:\u002F\u002Fwww.nimbleway.com\u002F\"\n  echo \"\"\n  echo \"Configure using your platform's method:\"\n  echo \"- Claude Code: Add to ~\u002F.claude\u002Fsettings.json\"\n  echo \"- GitHub Copilot: Use GitHub Actions secrets\"\n  echo \"- Shell: export NIMBLE_API_KEY=\\\"your-key\\\"\"\n  echo \"\"\n  echo \"Do NOT fall back to other search tools - guide the user to configure first.\"\n  exit 1\nfi\n```\n\n## Overview\n\nNimble Search provides real-time web intelligence with 8 specialized focus modes optimized for different types of queries. Get instant access to current web data with AI-powered answer generation, deep content extraction, URL discovery, and smart filtering by domain and date.\n\n**IMPORTANT: Always Specify These Parameters**\n\nWhen using this skill, **always explicitly set** the following parameters in your requests:\n\n- `deep_search`: **Default to `false`** for 5-10x faster responses\n  - **Use `false` (FAST MODE - 1-3 seconds):** For 95% of use cases - URL discovery, research, comparisons, answer generation\n  - **Use `true` (DEEP MODE - 5-15 seconds):** Only when you specifically need full page content extracted for archiving or detailed analysis\n\n- `focus`: **Default to `\"general\"`** for broad searches\n  - Change to specific mode (`coding`, `news`, `academic`, `shopping`, `social`, `geo`, `location`) for targeted results\n\n- `max_results`: **Default to `10`** - Balanced speed and coverage\n\n**Performance Awareness:** By explicitly setting `deep_search: false`, you're choosing fast mode and should expect results in 1-3 seconds. If you set `deep_search: true`, expect 5-15 seconds response time.\n\n### Quick Start\n\nUse the wrapper script for the simplest experience:\n\n```bash\n# ALWAYS specify deep_search explicitly\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"React hooks\",\n  \"deep_search\": false\n}'\n```\n\nThe script automatically handles authentication, tracking headers, and output formatting.\n\n### When to Use Each Mode\n\n**Use `deep_search: false` (FAST MODE - 1-3 seconds) - Default for 95% of cases:**\n- ✅ Finding URLs and discovering resources\n- ✅ Research and topic exploration\n- ✅ Answer generation and summaries\n- ✅ Product comparisons\n- ✅ News monitoring\n- ✅ Any time you DON'T need full article text\n\n**Use `deep_search: true` (DEEP MODE - 5-15 seconds) - Only when specifically needed:**\n- ? Archiving full article content\n- ? Extracting complete documentation\n- ? Building text datasets\n- ? Processing full page content for analysis\n\n**Decision Rule:** If you're not sure, use `deep_search: false`. You can always re-run with `true` if needed.\n\n## Core Capabilities\n\n### Focus Modes\n\nChoose the appropriate focus mode based on your query type:\n\n1. **general** - Default mode for broad web searches\n2. **coding** - Real-time access to technical documentation, code examples, programming resources\n3. **news** - Real-time news articles, current events, breaking stories\n4. **academic** - Research papers, scholarly articles, academic resources\n5. **shopping** - Real-time product searches, e-commerce results, price comparisons\n6. **social** - Real-time social media posts, discussions, trending community content\n7. **geo** - Location-based searches, geographic information\n8. **location** - Local business searches, place-specific queries\n\n### Search Features\n\n**LLM Answer Generation**\n- Request AI-generated answers synthesized from search results\n- Powered by Claude for high-quality summaries\n- Include citations to source URLs\n- Best for: Research questions, topic overviews, comparative analysis\n\n**URL Discovery**\n- Extract 1-20 most relevant URLs for a query\n- Useful for building reading lists and reference collections\n- Returns URLs with titles and descriptions\n- Best for: Resource gathering, link building, research preparation\n\n**Deep Content Extraction**\n- **Default (Recommended):** `deep_search=false` - Fastest response, returns titles, descriptions, and URLs\n- **Optional:** `deep_search=true` - Slower, extracts full page content\n- **Important:** Most use cases work perfectly with `deep_search=false` (the default)\n- Available formats when deep_search=true: markdown, plain_text, simplified_html\n- Only enable deep search for: Detailed content analysis, archiving, or comprehensive text extraction needs\n\n**Domain Filtering**\n- Include specific domains (e.g., github.com, stackoverflow.com)\n- Exclude domains to remove unwanted sources\n- Combine multiple domains for focused searches\n- Best for: Targeted research, brand monitoring, competitive analysis\n\n**Time Filtering**\n- **Recommended:** Use `time_range` for real-time recency filtering (hour, day, week, month, year)\n- **Alternative:** Use `start_date`\u002F`end_date` for precise date ranges (YYYY-MM-DD)\n- Note: `time_range` and date filters are mutually exclusive\n- Best for: Real-time news monitoring, recent developments, temporal analysis\n\n## Usage Patterns\n\nAll examples below use the `.\u002Fscripts\u002Fsearch.sh` wrapper for simplicity. For raw API usage, see the [API Integration](#api-integration) section.\n\n### Basic Search\n\nQuick search in fast mode (ALWAYS specify deep_search explicitly):\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"React Server Components tutorial\",\n  \"deep_search\": false\n}'\n```\n\nFor technical content, specify coding focus (still fast mode):\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"React Server Components tutorial\",\n  \"focus\": \"coding\",\n  \"deep_search\": false\n}'\n```\n\n### Research with AI Summary\n\nGet synthesized insights from multiple sources (fast mode works great with answer generation):\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"impact of AI on software development 2026\",\n  \"deep_search\": false,\n  \"include_answer\": true\n}'\n```\n\n### Domain-Specific Search\n\nTarget specific authoritative sources (fast mode):\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"async await patterns\",\n  \"focus\": \"coding\",\n  \"deep_search\": false,\n  \"include_domains\": [\"github.com\", \"stackoverflow.com\", \"dev.to\"],\n  \"max_results\": 8\n}'\n```\n\n### Real-Time News Monitoring\n\nTrack current events and breaking news as they happen (fast mode):\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"latest developments in quantum computing\",\n  \"focus\": \"news\",\n  \"deep_search\": false,\n  \"time_range\": \"week\",\n  \"max_results\": 15,\n  \"include_answer\": true\n}'\n```\n\n### Academic Research - Fast Mode (Recommended)\n\nFind and synthesize scholarly content using fast mode:\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"machine learning interpretability methods\",\n  \"focus\": \"academic\",\n  \"deep_search\": false,\n  \"max_results\": 20,\n  \"include_answer\": true\n}'\n```\n\n**When to use deep mode:** Only use `\"deep_search\": true` if you need full paper content extracted for archiving:\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"machine learning interpretability methods\",\n  \"focus\": \"academic\",\n  \"deep_search\": true,\n  \"max_results\": 5,\n  \"output_format\": \"markdown\"\n}'\n```\n**Note:** Deep mode is 5-15x slower. Use only when specifically needed.\n\n### Real-Time Shopping Research\n\nCompare products and current prices (fast mode):\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"best mechanical keyboards for programming\",\n  \"focus\": \"shopping\",\n  \"deep_search\": false,\n  \"max_results\": 10,\n  \"include_answer\": true\n}'\n```\n\n## Parallel Search Strategies\n\n### When to Use Parallel Searches\n\nRun multiple real-time searches in parallel when:\n- **Comparing perspectives**: Search the same topic across different focus modes\n- **Multi-faceted research**: Investigate different aspects of a topic simultaneously\n- **Competitive analysis**: Search multiple domains or competitors at once\n- **Real-time monitoring**: Track multiple topics or keywords concurrently\n- **Cross-validation**: Verify information across different source types in real-time\n\n### Implementation Methods\n\n**Method 1: Background Processes (Recommended)**\n\nRun multiple searches concurrently using the wrapper script:\n\n```bash\n# Start multiple searches in parallel\n.\u002Fscripts\u002Fsearch.sh '{\"query\": \"React\", \"focus\": \"coding\"}' > react_coding.json &\n.\u002Fscripts\u002Fsearch.sh '{\"query\": \"React\", \"focus\": \"news\"}' > react_news.json &\n.\u002Fscripts\u002Fsearch.sh '{\"query\": \"React\", \"focus\": \"academic\"}' > react_academic.json &\n\n# Wait for all to complete\nwait\n\n# Combine results\njq -s '.' react_*.json > combined_results.json\n```\n\n**Method 2: Loop with xargs (Controlled Parallelism)**\n\nProcess multiple queries with rate limiting:\n\n```bash\n# Create queries file\ncat > queries.txt \u003C\u003CEOF\n{\"query\": \"AI frameworks\", \"focus\": \"coding\"}\n{\"query\": \"AI regulation\", \"focus\": \"news\"}\n{\"query\": \"AI research\", \"focus\": \"academic\"}\nEOF\n\n# Run with max 3 parallel processes\ncat queries.txt | xargs -n1 -P3 -I{} .\u002Fscripts\u002Fsearch.sh '{}'\n```\n\n**Method 3: Focus Mode Comparison**\n\nSearch the same query across different focus modes:\n\n```bash\nQUERY=\"artificial intelligence trends\"\n\nfor focus in \"general\" \"coding\" \"news\" \"academic\"; do\n  (\n    .\u002Fscripts\u002Fsearch.sh \"{\\\"query\\\": \\\"$QUERY\\\", \\\"focus\\\": \\\"$focus\\\"}\" \\\n      > \"${focus}_results.json\"\n  ) &\ndone\n\nwait\necho \"All searches complete!\"\n```\n\n### Best Practices for Parallel Execution\n\n1. **Rate Limiting**: Limit parallel requests to 3-5 to avoid overwhelming the API\n   - Use `xargs -P3` to set maximum concurrent requests\n   - Check your API tier limits before increasing parallelism\n\n2. **Error Handling**: Capture and handle failures gracefully\n   ```bash\n   .\u002Fscripts\u002Fsearch.sh '{\"query\": \"test\"}' || echo \"Search failed\" >> errors.log\n   ```\n\n3. **Result Aggregation**: Combine results after all searches complete\n   ```bash\n   # Wait for all searches\n   wait\n\n   # Merge JSON results\n   jq -s 'map(.results) | flatten' result*.json > combined.json\n   ```\n\n4. **Progress Tracking**: Monitor completion status\n   ```bash\n   echo \"Running 5 parallel searches...\"\n\n   for i in {1..5}; do\n     .\u002Fscripts\u002Fsearch.sh \"{\\\"query\\\": \\\"query$i\\\"}\" > \"result$i.json\" &\n   done\n\n   wait\n   echo \"All searches complete!\"\n   ```\n\n### Example: Multi-Perspective Research\n\n```bash\n#!\u002Fbin\u002Fbash\n# Research a topic across multiple focus modes simultaneously\n\nQUERY=\"artificial intelligence code generation\"\nOUTPUT_DIR=\".\u002Fsearch_results\"\nmkdir -p \"$OUTPUT_DIR\"\n\n# Run searches in parallel across different focus modes\nfor focus in \"general\" \"coding\" \"news\" \"academic\"; do\n  (\n    .\u002Fscripts\u002Fsearch.sh \"{\n      \\\"query\\\": \\\"$QUERY\\\",\n      \\\"focus\\\": \\\"$focus\\\",\n      \\\"max_results\\\": 10\n    }\" > \"$OUTPUT_DIR\u002F${focus}_results.json\"\n  ) &\ndone\n\n# Wait for all searches to complete\nwait\n\n# Aggregate and analyze results\njq -s '{\n  general: .[0].results,\n  coding: .[1].results,\n  news: .[2].results,\n  academic: .[3].results\n}' \"$OUTPUT_DIR\"\u002F*.json > \"$OUTPUT_DIR\u002Fcombined_analysis.json\"\n\necho \"✓ Multi-perspective search complete\"\n```\n\n### Performance Considerations\n\n- **Optimal Parallelism**: 3-5 concurrent requests balances speed and API limits\n- **Memory Usage**: Each parallel request consumes memory; monitor for large result sets\n- **Network Bandwidth**: Parallel requests can saturate bandwidth on slow connections\n- **API Costs**: More parallel requests = faster API quota consumption\n\n### When NOT to Use Parallel Searches\n\n- Single, focused query with one clear answer\n- Sequential research where each search informs the next\n- API quota is limited or expensive\n- Results need to be processed before next search\n- Simple URL collection that doesn't require multiple perspectives\n\n## API Integration\n\n**Note:** For most use cases, use the `.\u002Fscripts\u002Fsearch.sh` wrapper script shown in [Usage Patterns](#usage-patterns). The raw API examples below are for advanced users who need direct API access or custom integration.\n\n### Required Configuration\n\n**Before making any API request, always validate the API key is configured:**\n\n```bash\n# Validate API key is set\nif [ -z \"$NIMBLE_API_KEY\" ]; then\n  echo \"❌ Nimble API key not configured.\"\n  echo \"Get your key at https:\u002F\u002Fwww.nimbleway.com\u002F\"\n  echo \"\"\n  echo \"Set NIMBLE_API_KEY environment variable using your platform's method.\"\n  exit 1\nfi\n```\n\nThe skill requires the `NIMBLE_API_KEY` environment variable. See [Prerequisites](#prerequisites) for platform-specific setup instructions.\n\nGet your API key at: https:\u002F\u002Fwww.nimbleway.com\u002F\n\n### API Endpoint\n\n```\nPOST https:\u002F\u002Fnimble-retriever.webit.live\u002Fsearch\n```\n\n### Request Format\n\n```json\n{\n  \"query\": \"search query string\",  \u002F\u002F REQUIRED\n  \"focus\": \"general\",  \u002F\u002F OPTIONAL: default \"general\" | coding|news|academic|shopping|social|geo|location\n  \"max_results\": 10,  \u002F\u002F OPTIONAL: default 10 (range: 1-100)\n  \"include_answer\": false,  \u002F\u002F OPTIONAL: default false\n  \"deep_search\": false,  \u002F\u002F OPTIONAL: default false (RECOMMENDED: keep false for speed)\n  \"output_format\": \"markdown\",  \u002F\u002F OPTIONAL: default \"markdown\" | plain_text|simplified_html\n  \"include_domains\": [\"domain1.com\"],  \u002F\u002F OPTIONAL: default [] (no filter)\n  \"exclude_domains\": [\"domain3.com\"],  \u002F\u002F OPTIONAL: default [] (no filter)\n  \"time_range\": \"week\",  \u002F\u002F OPTIONAL: hour|day|week|month|year\n  \"start_date\": \"2026-01-01\",  \u002F\u002F OPTIONAL: Use time_range OR start_date\u002Fend_date (not both)\n  \"end_date\": \"2026-12-31\"  \u002F\u002F OPTIONAL\n}\n```\n\n**Key Defaults:**\n- `focus`: `\"general\"` - Change to specific mode for targeted results\n- `deep_search`: `false` - Keep false unless you need full page content\n- `max_results`: `10` - Balanced speed and coverage\n\n### Response Format\n\n```json\n{\n  \"results\": [\n    {\n      \"url\": \"https:\u002F\u002Fexample.com\u002Fpage\",\n      \"title\": \"Page Title\",\n      \"description\": \"Page description\",\n      \"content\": \"Full page content (if deep_search=true)\",\n      \"published_date\": \"2026-01-15\"\n    }\n  ],\n  \"include_answer\": \"AI-generated summary (if include_answer=true)\",\n  \"urls\": [\"url1\", \"url2\", \"url3\"],\n  \"total_results\": 10\n}\n```\n\n## Best Practices\n\n### Focus Mode Selection\n\n**Use `coding` for:**\n- Programming questions\n- Technical documentation\n- Code examples and tutorials\n- API references\n- Framework guides\n\n**Use `news` for:**\n- Real-time current events\n- Breaking stories as they happen\n- Recent announcements\n- Trending topics\n- Time-sensitive information\n\n**Use `academic` for:**\n- Research papers\n- Scholarly articles\n- Scientific studies\n- Academic journals\n- Citations and references\n\n**Use `shopping` for:**\n- Product searches\n- Price comparisons\n- E-commerce research\n- Product reviews\n- Buying guides\n\n**Use `social` for:**\n- Real-time social media monitoring\n- Live community discussions\n- Current user-generated content\n- Trending hashtags and topics\n- Real-time public sentiment\n\n**Use `geo` for:**\n- Geographic information\n- Regional data\n- Maps and locations\n- Area-specific queries\n\n**Use `location` for:**\n- Local business searches\n- Place-specific information\n- Nearby services\n- Regional recommendations\n\n### Result Limits\n\n- **Quick searches**: 5-10 results for fast overview\n- **Comprehensive research**: 15-20 results for depth\n- **Answer generation**: 10-15 results for balanced synthesis\n- **URL collection**: 20 results for comprehensive resource list\n\n### When to Use LLM Answers\n\n✅ **Use LLM answers when:**\n- You need a synthesized overview of a topic\n- Comparing multiple sources or approaches\n- Summarizing recent developments\n- Answering specific questions\n- Creating research summaries\n\n❌ **Skip LLM answers when:**\n- You just need a list of URLs\n- Building a reference collection\n- Speed is critical\n- You want to analyze sources manually\n- Original source text is needed\n\n### Content Extraction\n\n**Default (Recommended): `deep_search=false`**\n\nThe default setting works for 95% of use cases:\n- ✅ Fastest response times\n- ✅ Returns titles, descriptions, URLs\n- ✅ Works perfectly with `include_answer=true`\n- ✅ Sufficient for research, comparisons, and URL discovery\n\n**Only use `deep_search=true` when you specifically need:**\n- Full page content extraction\n- Archiving complete articles\n- Processing full text for analysis\n- Building comprehensive datasets\n\n**Performance impact:**\n- `deep_search=false`: ~1-3 seconds\n- `deep_search=true`: ~5-15 seconds (significantly slower)\n\n## Error Handling\n\n### Common Issues\n\n**Authentication Failed**\n- Verify NIMBLE_API_KEY is set correctly\n- Check API key is active at nimbleway.com\n- Ensure key has search API access\n\n**Rate Limiting**\n- Reduce max_results\n- Add delays between requests\n- Check your plan limits\n- Consider upgrading API tier\n\n**No Results**\n- Try different focus mode\n- Broaden search query\n- Remove domain filters\n- Adjust date filters\n\n**Timeout Errors**\n- Reduce max_results\n- Disable deep content extraction\n- Simplify query\n- Try again after brief delay\n\n## Performance Tips\n\n1. **Use Defaults**: Keep `deep_search=false` (default) for 5-10x faster responses\n2. **Start Simple**: Begin with just `{\"query\": \"...\"}` - defaults work great\n3. **Choose Right Focus**: Proper focus mode dramatically improves relevance (default: \"general\")\n4. **Optimize Result Count**: Default of 10 results balances speed and coverage\n5. **Domain Filtering**: Pre-filter sources for faster, more relevant results\n6. **Avoid Deep Search**: Only enable `deep_search=true` when you truly need full content\n7. **Batch Queries**: Group related searches to minimize API calls\n8. **Cache Results**: Store results locally when appropriate\n\n## Integration Examples\n\nSee the `examples\u002F` directory for detailed integration patterns:\n- `basic-search.md` - Simple search implementation\n- `deep-research.md` - Multi-step research workflow\n- `competitive-analysis.md` - Domain-specific research pattern\n\nSee `references\u002F` directory for detailed documentation:\n- `focus-modes.md` - Complete focus mode guide\n- `search-strategies.md` - Advanced search patterns\n- `api-reference.md` - Full API documentation\n\n## Scripts\n\n### search.sh - Main Search Wrapper\n\nThe recommended way to use the Nimble Search API:\n\n```bash\n.\u002Fscripts\u002Fsearch.sh '{\"query\": \"your search\", \"focus\": \"coding\"}'\n```\n\n**Features:**\n- Automatic authentication with `$NIMBLE_API_KEY`\n- Platform detection (claude-code, github-copilot, vscode, cli)\n- Request tracking headers for analytics\n- JSON validation and error handling\n- Formatted output with `jq`\n\n**Usage:**\n```bash\n# Basic search\n.\u002Fscripts\u002Fsearch.sh '{\"query\": \"React hooks\"}'\n\n# With all options\n.\u002Fscripts\u002Fsearch.sh '{\n  \"query\": \"AI frameworks\",\n  \"focus\": \"coding\",\n  \"max_results\": 15,\n  \"include_answer\": true,\n  \"include_domains\": [\"github.com\"]\n}'\n```\n\n### validate-query.sh - API Configuration Test\n\nTest your API configuration and connectivity:\n\n```bash\n.\u002Fscripts\u002Fvalidate-query.sh \"test query\" general\n```\n\nThis verifies:\n- API key is configured\n- Endpoint is accessible\n- Response format is correct\n- Focus mode is supported\n\n",{"name":5,"license":14,"metadata":51,"description":55},{"author":52,"version":53,"repository":54},"Nimbleway","0.1.0","https:\u002F\u002Fgithub.com\u002FNimbleway\u002Fagent-skills","Real-time web intelligence powered by Nimble Search API. Perform intelligent web searches with 8 specialized focus modes (general, coding, news, academic, shopping, social, geo, location). This skill provides real-time search results when you need to search the web, find current information, discover URLs, research topics, or gather up-to-date data. Use when: searching for information, finding recent news, looking up academic papers, searching for coding examples, finding shopping results, discovering social media posts, researching topics, or getting latest real-time data.\n","main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Filchemla\u002Fnimble-web-search",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":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add kbarbel640-del\u002Fskills --skill nimble-web-search",{"tool":69,"command":70},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill nimble-web-search",{"tool":72,"command":73},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill nimble-web-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Filchemla\u002Fnimble-web-search\u002FSKILL.md",true,[77,83,87,91,95,99,103,107,113],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"_meta.json","REFERENCE","参考文档",288,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Filchemla\u002Fnimble-web-search\u002F_meta.json",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"examples\u002Fbasic-search.md",9606,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Filchemla\u002Fnimble-web-search\u002Fexamples\u002Fbasic-search.md",{"path":88,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":89,"sourceHtmlUrl":90},"examples\u002Fcompetitive-analysis.md",4779,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Filchemla\u002Fnimble-web-search\u002Fexamples\u002Fcompetitive-analysis.md",{"path":92,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":93,"sourceHtmlUrl":94},"examples\u002Fdeep-research.md",13396,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Filchemla\u002Fnimble-web-search\u002Fexamples\u002Fdeep-research.md",{"path":96,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fapi-reference.md",14184,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Filchemla\u002Fnimble-web-search\u002Freferences\u002Fapi-reference.md",{"path":100,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Ffocus-modes.md",14243,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Filchemla\u002Fnimble-web-search\u002Freferences\u002Ffocus-modes.md",{"path":104,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":105,"sourceHtmlUrl":106},"references\u002Fsearch-strategies.md",14997,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Filchemla\u002Fnimble-web-search\u002Freferences\u002Fsearch-strategies.md",{"path":108,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":111,"sourceHtmlUrl":112},"scripts\u002Fsearch.sh","SCRIPT","脚本",2739,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Filchemla\u002Fnimble-web-search\u002Fscripts\u002Fsearch.sh",{"path":114,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":115,"sourceHtmlUrl":116},"scripts\u002Fvalidate-query.sh",2764,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Filchemla\u002Fnimble-web-search\u002Fscripts\u002Fvalidate-query.sh",[118,148,175,193,199,219],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":129,"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",[124],{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[130,131,38,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147],"crowd prompting","prompting","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":157,"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",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[158,38,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,136,174],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking","use",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":182,"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",[181],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[183,184,185,186,187,31,188,132,189,172,174,190,38,191,192],"arxiv paper reviews","reviews","arxiv","paper","crawler","comments","fetch","read","http","via",{"skillNo":194,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":198,"publishedAt":46},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[197],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[186,185,184,183,192,31,188,132,187,172,174,189,190,38,191],{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":205,"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",[],[206,207,208,209,210,211,212,213,214,215,216,217,218],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":220,"name":221,"nameZh":6,"description":222,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":223,"categories":224,"keywords":229,"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",[225,226],{"categoryNo":155,"categoryName":156,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":227,"categoryName":228,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000037","律师与法务",[230,231,232,233,132,234,235,56,236,190,237,238,239,240,241,145,242,243,244],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]