[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77YVHCJQJ69DA56EWHB77TE":3,"skill-same:01M77YVHCJQJ69DA56EWHB77TE":46},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M77YVHCJQJ69DA56EWHB77TE","xiaohongshu-demand-discovery-skill",null,"Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fx\u002Fxiaohongshu-demand-discovery-skill\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: xiaohongshu-skill\ndescription: Use this skill when the user needs to work with Xiaohongshu\u002FRednote public content: QR-code login, keyword search, note details, user profiles, explore feed extraction, or small-scale demand discovery collection from recent high-interaction notes and comments. Prefer the demand-discovery command when the user wants to collect recent Xiaohongshu notes\u002Fcomments for later LLM demand analysis.\nuser-invokable: true\nmetadata: {\"openclaw\": {\"emoji\": \"\\ud83d\\udcd5\", \"requires\": {\"bins\": [\"python3\", \"playwright\"], \"anyBins\": [\"python3\", \"python\"]}, \"os\": [\"win32\", \"linux\", \"darwin\"], \"install\": [{\"id\": \"pip\", \"kind\": \"node\", \"label\": \"Install Python dependencies\", \"bins\": [\"playwright\"]}]}}\n---\n\n# Xiaohongshu Skill\n\nThis is a Python Playwright based OpenClaw skill for Xiaohongshu\u002FRednote public-content workflows. It reads page data from Xiaohongshu web pages, mainly through `window.__INITIAL_STATE__`, and returns structured JSON.\n\nIt includes the original capabilities:\n\n- QR-code login and login status checking\n- Keyword search with sort\u002Ftype\u002Ftime filters\n- Note detail extraction\n- Comment loading for note detail pages\n- User profile extraction\n- Explore feed extraction\n- Optional publishing and interaction commands retained from the upstream skill\n\nIt also adds:\n\n- **Xiaohongshu Demand Discovery Collector**\n\nThe demand discovery mode searches demand-style keywords, collects recent high-interaction notes and comments, cleans the data, removes raw user identity fields, and writes structured files for later LLM demand analysis or product-manager agent workflows.\n\n## What This Skill Is\n\nThis skill is a Xiaohongshu content and comment collection tool. The demand discovery collector can:\n\n- Search recent notes using demand-oriented keywords such as `求推荐`, `避雷`, `平替`, `真实测评`, `后悔买`, `踩坑`\n- Filter search results to notes from the last week\n- Sort by most comments by default\n- Visit note detail pages\n- Load comments\n- Prefer notes published within the recent `--days` window\n- Preserve notes whose publish time cannot be parsed as `publish_time_unknown`\n- Clean comments by removing empty, duplicate, short-noise, and obvious advertising comments\n- Save structured output files for downstream analysis\n\n## What This Skill Is Not\n\nThis skill is not:\n\n- A tool for bypassing Xiaohongshu login, captcha, rate limits, or risk controls\n- An automatic like\u002Fcomment\u002Ffollow\u002Fpublish bot for demand discovery\n- An LLM demand analysis tool\n- A product-manager agent\n- A complete SaaS product\n- An unrestricted high-volume crawler\n\nUse it for learning, research, internal product validation, and small-scale public-content collection.\n\n## When OpenClaw Should Use It\n\nPrefer `demand-discovery` when the user says things like:\n\n- “帮我跑一次小红书需求发现”\n- “抓小红书最近几天高互动笔记和评论”\n- “用小红书评论区挖用户需求”\n- “分析小红书用户在求推荐、避雷、平替里的需求”\n- “采集小红书热门笔记评论，后面喂给 LLM 分析”\n\nUse `search` when the user only wants to search a Xiaohongshu keyword:\n\n```bash\npython -m scripts search \"关键词\"\n```\n\nUse `feed` when the user provides a concrete note id\u002Flink context and wants note detail or comments:\n\n```bash\npython -m scripts feed \u003Cfeed_id> \u003Cxsec_token> --load-comments --max-comments=20\n```\n\nUse `qrcode` or `check-login` when login state is unknown or expired.\n\nDo not use interaction or publishing commands for demand discovery. The collector itself does not call `comment.py`, `interact.py`, or `publish.py`.\n\n## Installation\n\nRun all commands from the skill root directory.\n\n```bash\npip install -r requirements.txt\nplaywright install chromium\n```\n\nOn Linux\u002FWSL, Chromium dependencies may also be required:\n\n```bash\nplaywright install-deps chromium\n```\n\n## Login\n\nFirst login by QR code:\n\n```bash\npython -m scripts qrcode --headless=false\n```\n\nCheck login status:\n\n```bash\npython -m scripts check-login\n```\n\nIf cookies expire, run the QR-code login again.\n\n## Command Reference\n\n### Search\n\n```bash\npython -m scripts search \"美食\" --sort-by=最新 --note-type=图文 --publish-time=一周内 --limit=10\n```\n\nCommon search options:\n\n- `--sort-by`: `综合`, `最新`, `最多点赞`, `最多评论`, `最多收藏`\n- `--note-type`: `不限`, `视频`, `图文`\n- `--publish-time`: `不限`, `一天内`, `一周内`, `半年内`\n- `--search-scope`: `不限`, `已看过`, `未看过`, `已关注`\n- `--location`: `不限`, `同城`, `附近`\n- `--limit`: returned result limit\n\n### Feed Detail\n\n```bash\npython -m scripts feed \u003Cfeed_id> \u003Cxsec_token>\npython -m scripts feed \u003Cfeed_id> \u003Cxsec_token> --load-comments --max-comments=20\n```\n\n### Explore Feed\n\n```bash\npython -m scripts explore --limit=20\n```\n\nThe explore feed exists, but demand discovery should prefer keyword search in the first version.\n\n### User Profile\n\n```bash\npython -m scripts user \u003Cuser_id> [xsec_token]\npython -m scripts me\n```\n\n## Demand Discovery Collector\n\nBasic command:\n\n```bash\npython -m scripts demand-discovery\n```\n\nSmall-scale test:\n\n```bash\npython -m scripts demand-discovery --keywords \"求推荐\" --posts-per-keyword 1 --search-limit 3 --max-comments 5 --headless=false\n```\n\nSpecify multiple keywords:\n\n```bash\npython -m scripts demand-discovery --keywords \"求推荐,避雷,平替\" --posts-per-keyword 2 --search-limit 5 --max-comments 10 --headless=false\n```\n\nUse a keyword file:\n\n```bash\npython -m scripts demand-discovery --keywords-file keywords.txt\n```\n\nImportant parameters:\n\n- `--keywords`: comma-separated keywords\n- `--keywords-file`: UTF-8 text file, one keyword per line\n- `--days`: recent-day window for note filtering, default `3`\n- `--search-publish-time`: Xiaohongshu search time filter, default `一周内`\n- `--sort-by`: default `最多评论`, also supports `最多点赞`\n- `--note-type`: default `不限`\n- `--posts-per-keyword`: notes saved per keyword, default `3`\n- `--search-limit`: search results inspected per keyword, default `8`\n- `--max-comments`: valid comments saved per note, default `20`\n- `--output-dir`: output directory; default `data\u002Fdemand_discovery\u002F\u003Ctimestamp>\u002F`\n- `--timezone`: default `Asia\u002FShanghai`\n- `--headless`: `true` or `false`\n\nDefault demand keywords:\n\n```text\n求推荐\n避雷\n平替\n真实测评\n后悔买\n踩坑\n好用吗\n怎么选\n值不值得买\n学生党\n新手必备\n替代品\n不好用\n怎么解决\n```\n\nOutput files:\n\n- `notes_clean.jsonl`: one note-level record per saved\u002Fattempted note\n- `comments_clean.jsonl`: cleaned comment-level records\n- `collection_summary.json`: machine-readable summary and counters\n- `collector_report.md`: human-readable report\n\nThe collector uses one browser session per run:\n\n1. `XiaohongshuClient.start()`\n2. `LoginAction.check_login_status()`\n3. Reused `SearchAction`\n4. Reused `FeedDetailAction`\n5. `XiaohongshuClient.close()`\n\n## Privacy And Data Safety\n\nDemand discovery output must not save raw Xiaohongshu usernames, nicknames, avatars, or profile links. It writes `author_hash` instead:\n\n```text\nsha256(\"xiaohongshu:\" + raw_author_id)\n```\n\nThe preferred raw author id is `user_id`. If unavailable, the collector may hash another available author field such as nickname or profile link, then discard the original value.\n\n## Safety And Compliance Boundaries\n\n- Collect only publicly accessible content.\n- Do not bypass login, captcha, rate limits, or platform risk controls.\n- If captcha is triggered, stop and ask the user to handle it manually.\n- If login\u002Fcookie is invalid, stop and ask the user to log in again.\n- Do not save raw usernames, nicknames, avatars, or profile links.\n- Use `author_hash` only for deduplication and structured analysis.\n- Do not call `comment.py`, `interact.py`, or `publish.py` for demand discovery.\n- Do not run large high-frequency collections.\n- Keep first-version usage small, conservative, and reviewable.\n\n## Troubleshooting\n\n- Not logged in: run `python -m scripts qrcode --headless=false`\n- Cookie expired: login again by QR code\n- Captcha triggered: stop collection, wait, and handle verification manually in visible browser mode\n- Empty comments output: reduce batch size, test with `--headless=false`, and confirm comments load on the note page\n- Too many `publish_time_unknown`: Xiaohongshu may have changed detail fields; inspect raw note detail structure before relying on recent-day filtering\n- Detail failures from search results: `demand-discovery` uses `pc_search` as `xsec_source`; if this becomes unstable, test the original `feed` command behavior with `pc_feed`\n","# Xiaohongshu Skill\n\nThis is a Python Playwright based OpenClaw skill for Xiaohongshu\u002FRednote public-content workflows. It reads page data from Xiaohongshu web pages, mainly through `window.__INITIAL_STATE__`, and returns structured JSON.\n\nIt includes the original capabilities:\n\n- QR-code login and login status checking\n- Keyword search with sort\u002Ftype\u002Ftime filters\n- Note detail extraction\n- Comment loading for note detail pages\n- User profile extraction\n- Explore feed extraction\n- Optional publishing and interaction commands retained from the upstream skill\n\nIt also adds:\n\n- **Xiaohongshu Demand Discovery Collector**\n\nThe demand discovery mode searches demand-style keywords, collects recent high-interaction notes and comments, cleans the data, removes raw user identity fields, and writes structured files for later LLM demand analysis or product-manager agent workflows.\n\n## What This Skill Is\n\nThis skill is a Xiaohongshu content and comment collection tool. The demand discovery collector can:\n\n- Search recent notes using demand-oriented keywords such as `求推荐`, `避雷`, `平替`, `真实测评`, `后悔买`, `踩坑`\n- Filter search results to notes from the last week\n- Sort by most comments by default\n- Visit note detail pages\n- Load comments\n- Prefer notes published within the recent `--days` window\n- Preserve notes whose publish time cannot be parsed as `publish_time_unknown`\n- Clean comments by removing empty, duplicate, short-noise, and obvious advertising comments\n- Save structured output files for downstream analysis\n\n## What This Skill Is Not\n\nThis skill is not:\n\n- A tool for bypassing Xiaohongshu login, captcha, rate limits, or risk controls\n- An automatic like\u002Fcomment\u002Ffollow\u002Fpublish bot for demand discovery\n- An LLM demand analysis tool\n- A product-manager agent\n- A complete SaaS product\n- An unrestricted high-volume crawler\n\nUse it for learning, research, internal product validation, and small-scale public-content collection.\n\n## When OpenClaw Should Use It\n\nPrefer `demand-discovery` when the user says things like:\n\n- “帮我跑一次小红书需求发现”\n- “抓小红书最近几天高互动笔记和评论”\n- “用小红书评论区挖用户需求”\n- “分析小红书用户在求推荐、避雷、平替里的需求”\n- “采集小红书热门笔记评论，后面喂给 LLM 分析”\n\nUse `search` when the user only wants to search a Xiaohongshu keyword:\n\n```bash\npython -m scripts search \"关键词\"\n```\n\nUse `feed` when the user provides a concrete note id\u002Flink context and wants note detail or comments:\n\n```bash\npython -m scripts feed \u003Cfeed_id> \u003Cxsec_token> --load-comments --max-comments=20\n```\n\nUse `qrcode` or `check-login` when login state is unknown or expired.\n\nDo not use interaction or publishing commands for demand discovery. The collector itself does not call `comment.py`, `interact.py`, or `publish.py`.\n\n## Installation\n\nRun all commands from the skill root directory.\n\n```bash\npip install -r requirements.txt\nplaywright install chromium\n```\n\nOn Linux\u002FWSL, Chromium dependencies may also be required:\n\n```bash\nplaywright install-deps chromium\n```\n\n## Login\n\nFirst login by QR code:\n\n```bash\npython -m scripts qrcode --headless=false\n```\n\nCheck login status:\n\n```bash\npython -m scripts check-login\n```\n\nIf cookies expire, run the QR-code login again.\n\n## Command Reference\n\n### Search\n\n```bash\npython -m scripts search \"美食\" --sort-by=最新 --note-type=图文 --publish-time=一周内 --limit=10\n```\n\nCommon search options:\n\n- `--sort-by`: `综合`, `最新`, `最多点赞`, `最多评论`, `最多收藏`\n- `--note-type`: `不限`, `视频`, `图文`\n- `--publish-time`: `不限`, `一天内`, `一周内`, `半年内`\n- `--search-scope`: `不限`, `已看过`, `未看过`, `已关注`\n- `--location`: `不限`, `同城`, `附近`\n- `--limit`: returned result limit\n\n### Feed Detail\n\n```bash\npython -m scripts feed \u003Cfeed_id> \u003Cxsec_token>\npython -m scripts feed \u003Cfeed_id> \u003Cxsec_token> --load-comments --max-comments=20\n```\n\n### Explore Feed\n\n```bash\npython -m scripts explore --limit=20\n```\n\nThe explore feed exists, but demand discovery should prefer keyword search in the first version.\n\n### User Profile\n\n```bash\npython -m scripts user \u003Cuser_id> [xsec_token]\npython -m scripts me\n```\n\n## Demand Discovery Collector\n\nBasic command:\n\n```bash\npython -m scripts demand-discovery\n```\n\nSmall-scale test:\n\n```bash\npython -m scripts demand-discovery --keywords \"求推荐\" --posts-per-keyword 1 --search-limit 3 --max-comments 5 --headless=false\n```\n\nSpecify multiple keywords:\n\n```bash\npython -m scripts demand-discovery --keywords \"求推荐,避雷,平替\" --posts-per-keyword 2 --search-limit 5 --max-comments 10 --headless=false\n```\n\nUse a keyword file:\n\n```bash\npython -m scripts demand-discovery --keywords-file keywords.txt\n```\n\nImportant parameters:\n\n- `--keywords`: comma-separated keywords\n- `--keywords-file`: UTF-8 text file, one keyword per line\n- `--days`: recent-day window for note filtering, default `3`\n- `--search-publish-time`: Xiaohongshu search time filter, default `一周内`\n- `--sort-by`: default `最多评论`, also supports `最多点赞`\n- `--note-type`: default `不限`\n- `--posts-per-keyword`: notes saved per keyword, default `3`\n- `--search-limit`: search results inspected per keyword, default `8`\n- `--max-comments`: valid comments saved per note, default `20`\n- `--output-dir`: output directory; default `data\u002Fdemand_discovery\u002F\u003Ctimestamp>\u002F`\n- `--timezone`: default `Asia\u002FShanghai`\n- `--headless`: `true` or `false`\n\nDefault demand keywords:\n\n```text\n求推荐\n避雷\n平替\n真实测评\n后悔买\n踩坑\n好用吗\n怎么选\n值不值得买\n学生党\n新手必备\n替代品\n不好用\n怎么解决\n```\n\nOutput files:\n\n- `notes_clean.jsonl`: one note-level record per saved\u002Fattempted note\n- `comments_clean.jsonl`: cleaned comment-level records\n- `collection_summary.json`: machine-readable summary and counters\n- `collector_report.md`: human-readable report\n\nThe collector uses one browser session per run:\n\n1. `XiaohongshuClient.start()`\n2. `LoginAction.check_login_status()`\n3. Reused `SearchAction`\n4. Reused `FeedDetailAction`\n5. `XiaohongshuClient.close()`\n\n## Privacy And Data Safety\n\nDemand discovery output must not save raw Xiaohongshu usernames, nicknames, avatars, or profile links. It writes `author_hash` instead:\n\n```text\nsha256(\"xiaohongshu:\" + raw_author_id)\n```\n\nThe preferred raw author id is `user_id`. If unavailable, the collector may hash another available author field such as nickname or profile link, then discard the original value.\n\n## Safety And Compliance Boundaries\n\n- Collect only publicly accessible content.\n- Do not bypass login, captcha, rate limits, or platform risk controls.\n- If captcha is triggered, stop and ask the user to handle it manually.\n- If login\u002Fcookie is invalid, stop and ask the user to log in again.\n- Do not save raw usernames, nicknames, avatars, or profile links.\n- Use `author_hash` only for deduplication and structured analysis.\n- Do not call `comment.py`, `interact.py`, or `publish.py` for demand discovery.\n- Do not run large high-frequency collections.\n- Keep first-version usage small, conservative, and reviewable.\n\n## Troubleshooting\n\n- Not logged in: run `python -m scripts qrcode --headless=false`\n- Cookie expired: login again by QR code\n- Captcha triggered: stop collection, wait, and handle verification manually in visible browser mode\n- Empty comments output: reduce batch size, test with `--headless=false`, and confirm comments load on the note page\n- Too many `publish_time_unknown`: Xiaohongshu may have changed detail fields; inspect raw note detail structure before relying on recent-day filtering\n- Detail failures from search results: `demand-discovery` uses `pc_search` as `xsec_source`; if this becomes unstable, test the original `feed` command behavior with `pc_feed`\n",{},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fx\u002Fxiaohongshu-demand-discovery-skill",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":7,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill xiaohongshu-demand-discovery-skill",{"tool":38,"command":39},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill xiaohongshu-demand-discovery-skill",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill xiaohongshu-demand-discovery-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fx\u002Fxiaohongshu-demand-discovery-skill\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":18},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]