[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78GPT01MS7V2H5FJR13XME3":3,"skill-same:01M78GPT01MS7V2H5FJR13XME3":68},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":13,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M78GPT01MS7V2H5FJR13XME3","searxng-search",null,"Free meta-search via SearXNG — aggregates results from 70+ search engines. Self-hosted or use a public instance. No API key needed. Falls back automatically when the web search toolset is unavailable.","RESousa01\u002Fbmad-runtime-dev","RESousa01","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F299151629?v=4","01M78G6P63PC4EAYPFT191W6C9","01M78G6P6QE3EY5S0SZRGWYBCS",0,"MIT","https:\u002F\u002Fgithub.com\u002FRESousa01\u002Fbmad-runtime-dev\u002Fblob\u002Fmain\u002Fbmad-runtime-lib\u002F_source_review\u002Fhermes-agent-main\u002Fhermes-agent-main\u002Foptional-skills\u002Fresearch\u002Fsearxng-search\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: searxng-search\ndescription: Free meta-search via SearXNG — aggregates results from 70+ search engines. Self-hosted or use a public instance. No API key needed. Falls back automatically when the web search toolset is unavailable.\nversion: 1.0.0\nauthor: hermes-agent\nlicense: MIT\nplatforms: [linux, macos]\nmetadata:\n  hermes:\n    tags: [search, searxng, meta-search, self-hosted, free, fallback]\n    related_skills: [duckduckgo-search, domain-intel]\n    fallback_for_toolsets: [web]\n---\n\n# SearXNG Search\n\nFree meta-search using [SearXNG](https:\u002F\u002Fsearxng.org\u002F) — a privacy-respecting, self-hosted search aggregator that queries 70+ search engines simultaneously.\n\n**No API key required** when using a public instance. Can also be self-hosted for full control. Automatically appears as a fallback when the main web search toolset (`FIRECRAWL_API_KEY`) is not configured.\n\n## Configuration\n\nSearXNG requires a `SEARXNG_URL` environment variable pointing to your SearXNG instance:\n\n```bash\n# Public instances (no setup required)\nSEARXNG_URL=https:\u002F\u002Fsearxng.example.com\n\n# Self-hosted SearXNG\nSEARXNG_URL=http:\u002F\u002Flocalhost:8888\n```\n\nIf no instance is configured, this skill is unavailable and the agent falls back to other search options.\n\n## Detection Flow\n\nCheck what is actually available before choosing an approach:\n\n```bash\n# Check if SEARXNG_URL is set and the instance is reachable\ncurl -s --max-time 5 \"${SEARXNG_URL}\u002Fsearch?q=test&format=json\" | head -c 200\n```\n\nDecision tree:\n1. If `SEARXNG_URL` is set and the instance responds, use SearXNG\n2. If `SEARXNG_URL` is unset or unreachable, fall back to other available search tools\n3. If the user wants SearXNG specifically, help them set up an instance or find a public one\n\n## Method 1: CLI via curl (Preferred)\n\nUse `curl` via `terminal` to call the SearXNG JSON API. This avoids assuming any particular Python package is installed.\n\n```bash\n# Text search (JSON output)\ncurl -s --max-time 10 \\\n  \"${SEARXNG_URL}\u002Fsearch?q=python+async+programming&format=json&engines=google,bing&limit=10\"\n\n# With Safesearch off\ncurl -s --max-time 10 \\\n  \"${SEARXNG_URL}\u002Fsearch?q=example&format=json&safesearch=0\"\n\n# Specific categories (general, news, science, etc.)\ncurl -s --max-time 10 \\\n  \"${SEARXNG_URL}\u002Fsearch?q=AI+news&format=json&categories=news\"\n```\n\n### Common CLI Flags\n\n| Flag | Description | Example |\n|------|-------------|---------|\n| `q` | Query string (URL-encoded) | `q=python+async` |\n| `format` | Output format: `json`, `csv`, `rss` | `format=json` |\n| `engines` | Comma-separated engine names | `engines=google,bing,ddg` |\n| `limit` | Max results per engine (default 10) | `limit=5` |\n| `categories` | Filter by category | `categories=news,science` |\n| `safesearch` | 0=none, 1=moderate, 2=strict | `safesearch=0` |\n| `time_range` | Filter: `day`, `week`, `month`, `year` | `time_range=week` |\n\n### Parsing JSON Results\n\n```bash\n# Extract titles and URLs from JSON\ncurl -s --max-time 10 \"${SEARXNG_URL}\u002Fsearch?q=fastapi&format=json&limit=5\" \\\n  | python3 -c \"\nimport json, sys\ndata = json.load(sys.stdin)\nfor r in data.get('results', []):\n    print(r.get('title',''))\n    print(r.get('url',''))\n    print(r.get('content','')[:200])\n    print()\n\"\n```\n\nReturns per result: `title`, `url`, `content` (snippet), `engine`, `parsed_url`, `img_src`, `thumbnail`, `author`, `published_date`\n\n## Method 2: Python API via `requests`\n\nUse the SearXNG REST API directly from Python with the `requests` library:\n\n```python\nimport os, requests, urllib.parse\n\nbase_url = os.environ.get(\"SEARXNG_URL\", \"\")\nif not base_url:\n    raise RuntimeError(\"SEARXNG_URL is not set\")\n\nquery = \"fastapi deployment guide\"\nparams = {\n    \"q\": query,\n    \"format\": \"json\",\n    \"limit\": 5,\n    \"engines\": \"google,bing\",\n}\n\nresp = requests.get(f\"{base_url}\u002Fsearch\", params=params, timeout=10)\nresp.raise_for_status()\ndata = resp.json()\n\nfor r in data.get(\"results\", []):\n    print(r[\"title\"])\n    print(r[\"url\"])\n    print(r.get(\"content\", \"\")[:200])\n    print()\n```\n\n## Method 3: searxng-data Python Package\n\nFor more structured access, install the `searxng-data` package:\n\n```bash\npip install searxng-data\n```\n\n```python\nfrom searxng_data import engines\n\n# List available engines\nprint(engines.list_engines())\n```\n\nNote: This package only provides engine metadata, not the search API itself.\n\n## Self-Hosting SearXNG\n\nTo run your own SearXNG instance:\n\n```bash\n# Using Docker\ndocker run -d -p 8888:8080 \\\n  -v $(pwd)\u002Fsearxng:\u002Fetc\u002Fsearxng \\\n  searxng\u002Fsearxng:latest\n\n# Then set\nSEARXNG_URL=http:\u002F\u002Flocalhost:8888\n```\n\nOr install via pip:\n```bash\npip install searxng\n# Edit \u002Fetc\u002Fsearxng\u002Fsettings.yml\nsearxng-run\n```\n\nPublic SearXNG instances are available at:\n- `https:\u002F\u002Fsearxng.example.com` (replace with any public instance)\n\n## Workflow: Search then Extract\n\nSearXNG returns titles, URLs, and snippets — not full page content. To get full page content, search first and then extract the most relevant URL with `web_extract`, browser tools, or `curl`.\n\n```bash\n# Search for relevant pages\ncurl -s \"${SEARXNG_URL}\u002Fsearch?q=fastapi+deployment&format=json&limit=3\"\n# Output: list of results with titles and URLs\n\n# Then extract the best URL with web_extract\n```\n\n## Limitations\n\n- **Instance availability**: If the SearXNG instance is down or unreachable, search fails. Always check `SEARXNG_URL` is set and the instance is reachable.\n- **No content extraction**: SearXNG returns snippets, not full page content. Use `web_extract`, browser tools, or `curl` for full articles.\n- **Rate limiting**: Some public instances limit requests. Self-hosting avoids this.\n- **Engine coverage**: Available engines depend on the SearXNG instance configuration. Some engines may be disabled.\n- **Results freshness**: Meta-search aggregates external engines — result freshness depends on those engines.\n\n## Troubleshooting\n\n| Problem | Likely Cause | What To Do |\n|---------|--------------|------------|\n| `SEARXNG_URL` not set | No instance configured | Use a public SearXNG instance or set up your own |\n| Connection refused | Instance not running or wrong URL | Check the URL is correct and the instance is running |\n| Empty results | Instance blocks the query | Try a different instance or self-host |\n| Slow responses | Public instance under load | Self-host or use a less-loaded public instance |\n| `json` format not supported | Old SearXNG version | Try `format=rss` or upgrade SearXNG |\n\n## Pitfalls\n\n- **Always set `SEARXNG_URL`**: Without it, the skill cannot function.\n- **URL-encode queries**: Spaces and special characters must be URL-encoded in curl, or use `urllib.parse.quote()` in Python.\n- **Use `format=json`**: The default format may not be machine-readable. Always request JSON explicitly.\n- **Set a timeout**: Always use `--max-time` or `timeout=` to avoid hanging on unreachable instances.\n- **Self-hosting is best**: Public instances may go down, rate-limit, or block. A self-hosted instance is reliable.\n\n## Instance Discovery\n\nIf `SEARXNG_URL` is not set and the user asks about SearXNG, help them either:\n1. Find a public SearXNG instance (search for \"public searxng instance\")\n2. Set up their own with Docker or pip\n\nPublic instances are listed at: https:\u002F\u002Fsearxng.org\u002F\n","# SearXNG Search\n\nFree meta-search using [SearXNG](https:\u002F\u002Fsearxng.org\u002F) — a privacy-respecting, self-hosted search aggregator that queries 70+ search engines simultaneously.\n\n**No API key required** when using a public instance. Can also be self-hosted for full control. Automatically appears as a fallback when the main web search toolset (`FIRECRAWL_API_KEY`) is not configured.\n\n## Configuration\n\nSearXNG requires a `SEARXNG_URL` environment variable pointing to your SearXNG instance:\n\n```bash\n# Public instances (no setup required)\nSEARXNG_URL=https:\u002F\u002Fsearxng.example.com\n\n# Self-hosted SearXNG\nSEARXNG_URL=http:\u002F\u002Flocalhost:8888\n```\n\nIf no instance is configured, this skill is unavailable and the agent falls back to other search options.\n\n## Detection Flow\n\nCheck what is actually available before choosing an approach:\n\n```bash\n# Check if SEARXNG_URL is set and the instance is reachable\ncurl -s --max-time 5 \"${SEARXNG_URL}\u002Fsearch?q=test&format=json\" | head -c 200\n```\n\nDecision tree:\n1. If `SEARXNG_URL` is set and the instance responds, use SearXNG\n2. If `SEARXNG_URL` is unset or unreachable, fall back to other available search tools\n3. If the user wants SearXNG specifically, help them set up an instance or find a public one\n\n## Method 1: CLI via curl (Preferred)\n\nUse `curl` via `terminal` to call the SearXNG JSON API. This avoids assuming any particular Python package is installed.\n\n```bash\n# Text search (JSON output)\ncurl -s --max-time 10 \\\n  \"${SEARXNG_URL}\u002Fsearch?q=python+async+programming&format=json&engines=google,bing&limit=10\"\n\n# With Safesearch off\ncurl -s --max-time 10 \\\n  \"${SEARXNG_URL}\u002Fsearch?q=example&format=json&safesearch=0\"\n\n# Specific categories (general, news, science, etc.)\ncurl -s --max-time 10 \\\n  \"${SEARXNG_URL}\u002Fsearch?q=AI+news&format=json&categories=news\"\n```\n\n### Common CLI Flags\n\n| Flag | Description | Example |\n|------|-------------|---------|\n| `q` | Query string (URL-encoded) | `q=python+async` |\n| `format` | Output format: `json`, `csv`, `rss` | `format=json` |\n| `engines` | Comma-separated engine names | `engines=google,bing,ddg` |\n| `limit` | Max results per engine (default 10) | `limit=5` |\n| `categories` | Filter by category | `categories=news,science` |\n| `safesearch` | 0=none, 1=moderate, 2=strict | `safesearch=0` |\n| `time_range` | Filter: `day`, `week`, `month`, `year` | `time_range=week` |\n\n### Parsing JSON Results\n\n```bash\n# Extract titles and URLs from JSON\ncurl -s --max-time 10 \"${SEARXNG_URL}\u002Fsearch?q=fastapi&format=json&limit=5\" \\\n  | python3 -c \"\nimport json, sys\ndata = json.load(sys.stdin)\nfor r in data.get('results', []):\n    print(r.get('title',''))\n    print(r.get('url',''))\n    print(r.get('content','')[:200])\n    print()\n\"\n```\n\nReturns per result: `title`, `url`, `content` (snippet), `engine`, `parsed_url`, `img_src`, `thumbnail`, `author`, `published_date`\n\n## Method 2: Python API via `requests`\n\nUse the SearXNG REST API directly from Python with the `requests` library:\n\n```python\nimport os, requests, urllib.parse\n\nbase_url = os.environ.get(\"SEARXNG_URL\", \"\")\nif not base_url:\n    raise RuntimeError(\"SEARXNG_URL is not set\")\n\nquery = \"fastapi deployment guide\"\nparams = {\n    \"q\": query,\n    \"format\": \"json\",\n    \"limit\": 5,\n    \"engines\": \"google,bing\",\n}\n\nresp = requests.get(f\"{base_url}\u002Fsearch\", params=params, timeout=10)\nresp.raise_for_status()\ndata = resp.json()\n\nfor r in data.get(\"results\", []):\n    print(r[\"title\"])\n    print(r[\"url\"])\n    print(r.get(\"content\", \"\")[:200])\n    print()\n```\n\n## Method 3: searxng-data Python Package\n\nFor more structured access, install the `searxng-data` package:\n\n```bash\npip install searxng-data\n```\n\n```python\nfrom searxng_data import engines\n\n# List available engines\nprint(engines.list_engines())\n```\n\nNote: This package only provides engine metadata, not the search API itself.\n\n## Self-Hosting SearXNG\n\nTo run your own SearXNG instance:\n\n```bash\n# Using Docker\ndocker run -d -p 8888:8080 \\\n  -v $(pwd)\u002Fsearxng:\u002Fetc\u002Fsearxng \\\n  searxng\u002Fsearxng:latest\n\n# Then set\nSEARXNG_URL=http:\u002F\u002Flocalhost:8888\n```\n\nOr install via pip:\n```bash\npip install searxng\n# Edit \u002Fetc\u002Fsearxng\u002Fsettings.yml\nsearxng-run\n```\n\nPublic SearXNG instances are available at:\n- `https:\u002F\u002Fsearxng.example.com` (replace with any public instance)\n\n## Workflow: Search then Extract\n\nSearXNG returns titles, URLs, and snippets — not full page content. To get full page content, search first and then extract the most relevant URL with `web_extract`, browser tools, or `curl`.\n\n```bash\n# Search for relevant pages\ncurl -s \"${SEARXNG_URL}\u002Fsearch?q=fastapi+deployment&format=json&limit=3\"\n# Output: list of results with titles and URLs\n\n# Then extract the best URL with web_extract\n```\n\n## Limitations\n\n- **Instance availability**: If the SearXNG instance is down or unreachable, search fails. Always check `SEARXNG_URL` is set and the instance is reachable.\n- **No content extraction**: SearXNG returns snippets, not full page content. Use `web_extract`, browser tools, or `curl` for full articles.\n- **Rate limiting**: Some public instances limit requests. Self-hosting avoids this.\n- **Engine coverage**: Available engines depend on the SearXNG instance configuration. Some engines may be disabled.\n- **Results freshness**: Meta-search aggregates external engines — result freshness depends on those engines.\n\n## Troubleshooting\n\n| Problem | Likely Cause | What To Do |\n|---------|--------------|------------|\n| `SEARXNG_URL` not set | No instance configured | Use a public SearXNG instance or set up your own |\n| Connection refused | Instance not running or wrong URL | Check the URL is correct and the instance is running |\n| Empty results | Instance blocks the query | Try a different instance or self-host |\n| Slow responses | Public instance under load | Self-host or use a less-loaded public instance |\n| `json` format not supported | Old SearXNG version | Try `format=rss` or upgrade SearXNG |\n\n## Pitfalls\n\n- **Always set `SEARXNG_URL`**: Without it, the skill cannot function.\n- **URL-encode queries**: Spaces and special characters must be URL-encoded in curl, or use `urllib.parse.quote()` in Python.\n- **Use `format=json`**: The default format may not be machine-readable. Always request JSON explicitly.\n- **Set a timeout**: Always use `--max-time` or `timeout=` to avoid hanging on unreachable instances.\n- **Self-hosting is best**: Public instances may go down, rate-limit, or block. A self-hosted instance is reliable.\n\n## Instance Discovery\n\nIf `SEARXNG_URL` is not set and the user asks about SearXNG, help them either:\n1. Find a public SearXNG instance (search for \"public searxng instance\")\n2. Set up their own with Docker or pip\n\nPublic instances are listed at: https:\u002F\u002Fsearxng.org\u002F\n",{"name":5,"author":23,"license":14,"version":24,"metadata":25,"platforms":39,"description":7},"hermes-agent","1.0.0",{"hermes":26},{"tags":27,"related_skills":34,"fallback_for_toolsets":37},[28,29,30,31,32,33],"search","searxng","meta-search","self-hosted","free","fallback",[35,36],"duckduckgo-search","domain-intel",[38],"web",[40,41],"linux","macos","main","f6a8453b945427ad778127c99f3da279c47a2220","bmad-runtime-lib\u002F_source_review\u002Fhermes-agent-main\u002Fhermes-agent-main\u002Foptional-skills\u002Fresearch\u002Fsearxng-search","https:\u002F\u002Fgithub.com\u002FRESousa01\u002Fbmad-runtime-dev","https:\u002F\u002Fgithub.com\u002FRESousa01","2026-10-19 13:01:14",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add RESousa01\u002Fbmad-runtime-dev --skill searxng-search",{"tool":54,"command":55},"bunx","bunx skills add RESousa01\u002Fbmad-runtime-dev --skill searxng-search",{"tool":57,"command":58},"pnpm","pnpm dlx skills add RESousa01\u002Fbmad-runtime-dev --skill searxng-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRESousa01\u002Fbmad-runtime-dev\u002Fblob\u002Fmain\u002Fbmad-runtime-lib\u002F_source_review\u002Fhermes-agent-main\u002Fhermes-agent-main\u002Foptional-skills\u002Fresearch\u002Fsearxng-search\u002FSKILL.md",true,[62],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"scripts\u002Fsearxng.sh","SCRIPT","脚本",524,"https:\u002F\u002Fgithub.com\u002FRESousa01\u002Fbmad-runtime-dev\u002Fblob\u002Fmain\u002Fbmad-runtime-lib\u002F_source_review\u002Fhermes-agent-main\u002Fhermes-agent-main\u002Foptional-skills\u002Fresearch\u002Fsearxng-search\u002Fscripts\u002Fsearxng.sh",[69,78,86,93,100,107],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":73,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M78H3BBP6055J6C6Y0H85EFP","skill-creator","Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FRESousa01\u002Fbmad-runtime-dev\u002Fblob\u002Fmain\u002Fbmad-runtime-lib\u002F_source_review\u002Fopenclaw-main\u002Fopenclaw-main\u002Fskills\u002Fskill-creator\u002Flicense.txt","https:\u002F\u002Fgithub.com\u002FRESousa01\u002Fbmad-runtime-dev\u002Fblob\u002Fmain\u002Fbmad-runtime-lib\u002F_source_review\u002Fopenclaw-main\u002Fopenclaw-main\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M78H0B17WY9EQRPAV9G55Y2D","prose","OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.","https:\u002F\u002Fgithub.com\u002FRESousa01\u002Fbmad-runtime-dev\u002Fblob\u002Fmain\u002Fbmad-runtime-lib\u002F_source_review\u002Fopenclaw-main\u002Fopenclaw-main\u002Fextensions\u002Fopen-prose\u002Fskills\u002Fprose\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FRESousa01\u002Fbmad-runtime-dev\u002Fblob\u002Fmain\u002Fbmad-runtime-lib\u002F_source_review\u002Fopenclaw-main\u002Fopenclaw-main\u002Fextensions\u002Fopen-prose\u002Fskills\u002Fprose\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M78GYV3AEHB5ZQ8XH131F9HE","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FRESousa01\u002Fbmad-runtime-dev\u002Fblob\u002Fmain\u002Fbmad-runtime-lib\u002F_source_review\u002Fhermes-agent-main\u002Fhermes-agent-main\u002Fskills\u002Fsoftware-development\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M78GYQ03NRD6F6KVBDX8STSJ","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FRESousa01\u002Fbmad-runtime-dev\u002Fblob\u002Fmain\u002Fbmad-runtime-lib\u002F_source_review\u002Fhermes-agent-main\u002Fhermes-agent-main\u002Fskills\u002Fsoftware-development\u002Fsystematic-debugging\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":18},"01M78GYMHFYT1W2W0RN48E49BQ","spike","Throwaway experiments to validate an idea before build.","https:\u002F\u002Fgithub.com\u002FRESousa01\u002Fbmad-runtime-dev\u002Fblob\u002Fmain\u002Fbmad-runtime-lib\u002F_source_review\u002Fhermes-agent-main\u002Fhermes-agent-main\u002Fskills\u002Fsoftware-development\u002Fspike\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M78GYF9P7VZ8YJCVJPYS6KER","simplify-code","Parallel 3-agent cleanup of recent code changes.","https:\u002F\u002Fgithub.com\u002FRESousa01\u002Fbmad-runtime-dev\u002Fblob\u002Fmain\u002Fbmad-runtime-lib\u002F_source_review\u002Fhermes-agent-main\u002Fhermes-agent-main\u002Fskills\u002Fsoftware-development\u002Fsimplify-code\u002FSKILL.md",[],[]]