[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77X73TH73X02CQD4T3VM37X":3,"skill-same:01M77X73TH73X02CQD4T3VM37X":62},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":44,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M77X73TH73X02CQD4T3VM37X","twitter-auto-engage",null,"Automated Twitter\u002FX engagement script that scans a curated pool of target accounts, generates authentic GPT-powered replies, and posts them via the Twitter GraphQL API. Use when you want to run a scheduled engagement routine that builds presence through high-quality, non-sycophantic replies to thought leaders in your niche.","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\u002Ft\u002Ftwitter-auto-engage\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: twitter-auto-engage\ndescription: Automated Twitter\u002FX engagement script that scans a curated pool of target accounts, generates authentic GPT-powered replies, and posts them via the Twitter GraphQL API. Use when you want to run a scheduled engagement routine that builds presence through high-quality, non-sycophantic replies to thought leaders in your niche.\nhomepage: https:\u002F\u002Fcanlah.ai\nmetadata: {\"requires\": [\"python3\", \"openai\", \"rnet_twitter\"], \"env\": [\"OPENAI_API_KEY\", \"TWITTER_COOKIE_PATH\"], \"tags\": [\"twitter\", \"social-media\", \"engagement\", \"automation\", \"openai\", \"gpt\"]}\n---\n\n# Twitter Auto-Engage\n\nAutomated Twitter\u002FX engagement system that scans a pool of target accounts, selects their highest-engagement recent tweets, generates context-aware replies using GPT, and posts them with human-like timing. Built for founders and builders who want to grow through genuine technical conversation, not follower-baiting.\n\n## Requirements\n\n```bash\npip install openai\n# rnet_twitter — async Twitter GraphQL client (see rnet_twitter.py)\n```\n\nYou also need:\n- A valid Twitter\u002FX session cookie file (`twitter_cookies.json`)\n- An OpenAI API key\n\n## Setup\n\n```bash\nexport OPENAI_API_KEY=\"your_openai_api_key\"\nexport TWITTER_COOKIE_PATH=\"\u002Fpath\u002Fto\u002Ftwitter_cookies.json\"\n```\n\nThe script reads cookies from a JSON file exported from a logged-in browser session. See [Obtaining Twitter Cookies](#obtaining-twitter-cookies) below.\n\n## Usage\n\n```bash\n# Run a single engagement session (5 replies max)\npython auto_engage.py\n\n# Schedule 4x daily via cron (recommended)\n# Morning, midday, afternoon, evening sessions\n0 8,12,16,21 * * * cd {skillDir} && python auto_engage.py >> logs\u002Fengage.log 2>&1\n```\n\n## Configuration\n\nEdit the following constants at the top of the script to customize behavior:\n\n| Constant | Default | Description |\n|----------|---------|-------------|\n| `TARGETS_PER_RUN` | 20 | Accounts to check each session |\n| `MAX_REPLIES_PER_RUN` | 5 | Maximum replies to post per session |\n| `RUN_PROBABILITY` | 0.85 | Randomized skip chance (human variability) |\n| `MIN_REPLY_LENGTH` | 80 | Minimum character count for a reply |\n| `MAX_REPLY_LENGTH` | 260 | Maximum character count for a reply |\n\n## Target Account Pool\n\nOrganize accounts into named categories with per-session quotas. The script randomly samples `TARGETS_PER_RUN` accounts from the full pool each session.\n\nExample structure:\n\n```python\nTARGET_POOL = {\n    \"ai_builders\": [\n        \"simonw\",     # Example: ML tools, Datasette\n        \"swyx\",       # Example: AI engineering\n    ],\n    \"indie_builders\": [\n        \"dvassallo\",  # Example: indie hacker\n        \"tdinh_me\",   # Example: bootstrapped SaaS\n    ],\n    \"marketing\": [\n        \"harrydry\",   # Example: Marketing Examples\n        \"wes_kao\",    # Example: content strategy\n    ],\n}\n\nCATEGORY_QUOTAS = {\n    \"ai_builders\":   2,  # replies per session\n    \"indie_builders\": 2,\n    \"marketing\":     1,\n}\n```\n\nReplace handles with accounts relevant to your niche and goals.\n\n## Reply Generation\n\nReplies are generated by GPT using a structured voice prompt. The system enforces:\n\n### Voice Rules (Configurable)\n- Direct, clear sentences — no filler words\n- Specific over vague: numbers, tool names, concrete observations\n- Intellectually curious tone — genuine questions, not rhetorical\n- Comfortable acknowledging uncertainty or failure\n\n### Hard Bans (Built-in Filters)\nThe generated reply is rejected and skipped if it contains:\n- Sycophantic openers: \"Great post\", \"Love this\", \"So true\", \"Spot on\", etc.\n- Casual slang: lol, damn, wild, ngl, fr, bro, lowkey, fire, bussin, no cap\n- Emojis (any Unicode > U+1F600)\n- Exclamation marks (configurable tolerance)\n- Corporate speak: leverage, synergy, paradigm, game-changer\n- Self-promotion or product name-dropping\n\n### Three Reply Archetypes\nGPT is prompted to pick ONE of:\n\n**A) Micro-insight + Question**\nShare a specific observation from your own experience, then ask something you genuinely want answered.\n> \"Ran into this building our brand tool — embeddings drift ~15% after 3 months without retraining. How often are you recalibrating?\"\n\n**B) Respectful Challenge**\nPolitely push back with data or a counterexample, then invite their perspective.\n> \"Counterpoint: Stripe's docs are famously good but they still need a sales team for enterprise. Isn't the real question where self-serve stops working?\"\n\n**C) Pattern Recognition**\nConnect their point to something non-obvious from a different domain.\n> \"This mirrors what happened in recommendation systems — Netflix found that optimizing for clicks killed retention. The proxy metric trap is everywhere. What's your equivalent of 'watch time'?\"\n\n## Customizing Your Voice\n\nEdit the `USER_CONTEXT` variable (or equivalent prompt section) to describe your background:\n\n```python\nUSER_CONTEXT = \"\"\"You are writing a Twitter reply as YOUR_NAME.\n\nBACKGROUND:\n- Brief description of who you are\n- What you're building\n- Genuine interests relevant to the accounts you target\n\nVOICE:\n- [Your preferred communication style]\n- [Specific things to include or avoid]\n\"\"\"\n```\n\nThe more specific and authentic your context, the better the replies.\n\n## State Management\n\nThe script maintains `auto_reply_state.json` to track replied tweet IDs, preventing duplicate replies across sessions:\n\n```json\n{\n  \"replied_tweets\": [\"tweet_id_1\", \"tweet_id_2\"],\n  \"last_updated\": \"2026-03-06T09:30:00\"\n}\n```\n\nState is capped at the last 100 tweet IDs to prevent unbounded growth.\n\n## Engagement Logic\n\nFor each selected account the script:\n\n1. Fetches the 10 most recent original tweets (excluding retweets and @-replies)\n2. Filters out tweet IDs already replied to\n3. Selects the tweet with highest combined engagement (likes + replies)\n4. Generates a reply via GPT — if GPT outputs `SKIP`, the tweet is marked seen and skipped\n5. Likes the tweet first (pre-reply like is an algorithmic signal)\n6. Posts the reply\n7. Waits 3-6 seconds (randomized human-like delay) before moving to the next account\n\n## Output\n\nEach session prints a summary and appends to your log. When called by a bot framework, the script outputs a JSON block after the `---JSON_OUTPUT---` separator for programmatic consumption:\n\n```json\n[\n  {\n    \"target\": \"simonw\",\n    \"tweet\": \"LLMs are increasingly being used for...\",\n    \"reply\": \"The retrieval side of this is underrated...\",\n    \"url\": \"https:\u002F\u002Fx.com\u002Fsimonw\u002Fstatus\u002F...\",\n    \"liked\": true\n  }\n]\n```\n\n## Obtaining Twitter Cookies\n\n1. Log in to Twitter\u002FX in Chrome or Firefox\n2. Open DevTools > Application > Cookies > `https:\u002F\u002Fx.com`\n3. Export the cookie values to a JSON file in the format expected by `rnet_twitter.py`\n4. Store the file at the path referenced by `TWITTER_COOKIE_PATH`\n\nDo not commit cookie files to version control.\n\n## Rate Limiting Guidelines\n\n- 5 replies per session, 4 sessions per day = 20 replies\u002Fday maximum\n- 85% probability of running each session adds natural variability\n- 3-6 second delay between each reply action\n- 1-2 second delay between like and reply on the same tweet\n\nTwitter's informal limits for reply actions are not publicly documented, but staying under 50 replies\u002Fday and spacing them across multiple sessions avoids most friction.\n\n## Troubleshooting\n\n**Reply not posting**: Verify your cookie file is fresh. Twitter sessions expire — re-export cookies from your browser.\n\n**GPT always outputs SKIP**: Your `USER_CONTEXT` may not align with the selected accounts. Ensure your background gives GPT enough to work with for the topic domain.\n\n**Too many sycophancy rejections**: GPT may default to affirmative openers. Increase the system prompt emphasis on the ban list or lower the temperature slightly.\n\n**Account flagged \u002F rate limited by Twitter**: Reduce `MAX_REPLIES_PER_RUN` to 3 and `RUN_PROBABILITY` to 0.6 for a more conservative cadence.\n\n---\n\n## Author\n\n**[Canlah AI](https:\u002F\u002Fcanlah.ai)** — Run performance marketing without breaking your brand.\n\n- GitHub: [github.com\u002FPHY041](https:\u002F\u002Fgithub.com\u002FPHY041)\n- All Skills: [clawhub.ai\u002FPHY041](https:\u002F\u002Fclawhub.ai\u002FPHY041)\n","# Twitter Auto-Engage\n\nAutomated Twitter\u002FX engagement system that scans a pool of target accounts, selects their highest-engagement recent tweets, generates context-aware replies using GPT, and posts them with human-like timing. Built for founders and builders who want to grow through genuine technical conversation, not follower-baiting.\n\n## Requirements\n\n```bash\npip install openai\n# rnet_twitter — async Twitter GraphQL client (see rnet_twitter.py)\n```\n\nYou also need:\n- A valid Twitter\u002FX session cookie file (`twitter_cookies.json`)\n- An OpenAI API key\n\n## Setup\n\n```bash\nexport OPENAI_API_KEY=\"your_openai_api_key\"\nexport TWITTER_COOKIE_PATH=\"\u002Fpath\u002Fto\u002Ftwitter_cookies.json\"\n```\n\nThe script reads cookies from a JSON file exported from a logged-in browser session. See [Obtaining Twitter Cookies](#obtaining-twitter-cookies) below.\n\n## Usage\n\n```bash\n# Run a single engagement session (5 replies max)\npython auto_engage.py\n\n# Schedule 4x daily via cron (recommended)\n# Morning, midday, afternoon, evening sessions\n0 8,12,16,21 * * * cd {skillDir} && python auto_engage.py >> logs\u002Fengage.log 2>&1\n```\n\n## Configuration\n\nEdit the following constants at the top of the script to customize behavior:\n\n| Constant | Default | Description |\n|----------|---------|-------------|\n| `TARGETS_PER_RUN` | 20 | Accounts to check each session |\n| `MAX_REPLIES_PER_RUN` | 5 | Maximum replies to post per session |\n| `RUN_PROBABILITY` | 0.85 | Randomized skip chance (human variability) |\n| `MIN_REPLY_LENGTH` | 80 | Minimum character count for a reply |\n| `MAX_REPLY_LENGTH` | 260 | Maximum character count for a reply |\n\n## Target Account Pool\n\nOrganize accounts into named categories with per-session quotas. The script randomly samples `TARGETS_PER_RUN` accounts from the full pool each session.\n\nExample structure:\n\n```python\nTARGET_POOL = {\n    \"ai_builders\": [\n        \"simonw\",     # Example: ML tools, Datasette\n        \"swyx\",       # Example: AI engineering\n    ],\n    \"indie_builders\": [\n        \"dvassallo\",  # Example: indie hacker\n        \"tdinh_me\",   # Example: bootstrapped SaaS\n    ],\n    \"marketing\": [\n        \"harrydry\",   # Example: Marketing Examples\n        \"wes_kao\",    # Example: content strategy\n    ],\n}\n\nCATEGORY_QUOTAS = {\n    \"ai_builders\":   2,  # replies per session\n    \"indie_builders\": 2,\n    \"marketing\":     1,\n}\n```\n\nReplace handles with accounts relevant to your niche and goals.\n\n## Reply Generation\n\nReplies are generated by GPT using a structured voice prompt. The system enforces:\n\n### Voice Rules (Configurable)\n- Direct, clear sentences — no filler words\n- Specific over vague: numbers, tool names, concrete observations\n- Intellectually curious tone — genuine questions, not rhetorical\n- Comfortable acknowledging uncertainty or failure\n\n### Hard Bans (Built-in Filters)\nThe generated reply is rejected and skipped if it contains:\n- Sycophantic openers: \"Great post\", \"Love this\", \"So true\", \"Spot on\", etc.\n- Casual slang: lol, damn, wild, ngl, fr, bro, lowkey, fire, bussin, no cap\n- Emojis (any Unicode > U+1F600)\n- Exclamation marks (configurable tolerance)\n- Corporate speak: leverage, synergy, paradigm, game-changer\n- Self-promotion or product name-dropping\n\n### Three Reply Archetypes\nGPT is prompted to pick ONE of:\n\n**A) Micro-insight + Question**\nShare a specific observation from your own experience, then ask something you genuinely want answered.\n> \"Ran into this building our brand tool — embeddings drift ~15% after 3 months without retraining. How often are you recalibrating?\"\n\n**B) Respectful Challenge**\nPolitely push back with data or a counterexample, then invite their perspective.\n> \"Counterpoint: Stripe's docs are famously good but they still need a sales team for enterprise. Isn't the real question where self-serve stops working?\"\n\n**C) Pattern Recognition**\nConnect their point to something non-obvious from a different domain.\n> \"This mirrors what happened in recommendation systems — Netflix found that optimizing for clicks killed retention. The proxy metric trap is everywhere. What's your equivalent of 'watch time'?\"\n\n## Customizing Your Voice\n\nEdit the `USER_CONTEXT` variable (or equivalent prompt section) to describe your background:\n\n```python\nUSER_CONTEXT = \"\"\"You are writing a Twitter reply as YOUR_NAME.\n\nBACKGROUND:\n- Brief description of who you are\n- What you're building\n- Genuine interests relevant to the accounts you target\n\nVOICE:\n- [Your preferred communication style]\n- [Specific things to include or avoid]\n\"\"\"\n```\n\nThe more specific and authentic your context, the better the replies.\n\n## State Management\n\nThe script maintains `auto_reply_state.json` to track replied tweet IDs, preventing duplicate replies across sessions:\n\n```json\n{\n  \"replied_tweets\": [\"tweet_id_1\", \"tweet_id_2\"],\n  \"last_updated\": \"2026-03-06T09:30:00\"\n}\n```\n\nState is capped at the last 100 tweet IDs to prevent unbounded growth.\n\n## Engagement Logic\n\nFor each selected account the script:\n\n1. Fetches the 10 most recent original tweets (excluding retweets and @-replies)\n2. Filters out tweet IDs already replied to\n3. Selects the tweet with highest combined engagement (likes + replies)\n4. Generates a reply via GPT — if GPT outputs `SKIP`, the tweet is marked seen and skipped\n5. Likes the tweet first (pre-reply like is an algorithmic signal)\n6. Posts the reply\n7. Waits 3-6 seconds (randomized human-like delay) before moving to the next account\n\n## Output\n\nEach session prints a summary and appends to your log. When called by a bot framework, the script outputs a JSON block after the `---JSON_OUTPUT---` separator for programmatic consumption:\n\n```json\n[\n  {\n    \"target\": \"simonw\",\n    \"tweet\": \"LLMs are increasingly being used for...\",\n    \"reply\": \"The retrieval side of this is underrated...\",\n    \"url\": \"https:\u002F\u002Fx.com\u002Fsimonw\u002Fstatus\u002F...\",\n    \"liked\": true\n  }\n]\n```\n\n## Obtaining Twitter Cookies\n\n1. Log in to Twitter\u002FX in Chrome or Firefox\n2. Open DevTools > Application > Cookies > `https:\u002F\u002Fx.com`\n3. Export the cookie values to a JSON file in the format expected by `rnet_twitter.py`\n4. Store the file at the path referenced by `TWITTER_COOKIE_PATH`\n\nDo not commit cookie files to version control.\n\n## Rate Limiting Guidelines\n\n- 5 replies per session, 4 sessions per day = 20 replies\u002Fday maximum\n- 85% probability of running each session adds natural variability\n- 3-6 second delay between each reply action\n- 1-2 second delay between like and reply on the same tweet\n\nTwitter's informal limits for reply actions are not publicly documented, but staying under 50 replies\u002Fday and spacing them across multiple sessions avoids most friction.\n\n## Troubleshooting\n\n**Reply not posting**: Verify your cookie file is fresh. Twitter sessions expire — re-export cookies from your browser.\n\n**GPT always outputs SKIP**: Your `USER_CONTEXT` may not align with the selected accounts. Ensure your background gives GPT enough to work with for the topic domain.\n\n**Too many sycophancy rejections**: GPT may default to affirmative openers. Increase the system prompt emphasis on the ban list or lower the temperature slightly.\n\n**Account flagged \u002F rate limited by Twitter**: Reduce `MAX_REPLIES_PER_RUN` to 3 and `RUN_PROBABILITY` to 0.6 for a more conservative cadence.\n\n---\n\n## Author\n\n**[Canlah AI](https:\u002F\u002Fcanlah.ai)** — Run performance marketing without breaking your brand.\n\n- GitHub: [github.com\u002FPHY041](https:\u002F\u002Fgithub.com\u002FPHY041)\n- All Skills: [clawhub.ai\u002FPHY041](https:\u002F\u002Fclawhub.ai\u002FPHY041)\n",{"name":5,"homepage":24,"metadata":25,"description":7},"https:\u002F\u002Fcanlah.ai",{"env":26,"tags":29,"requires":36},[27,28],"OPENAI_API_KEY","TWITTER_COOKIE_PATH",[30,31,32,33,34,35],"twitter","social-media","engagement","automation","openai","gpt",[37,34,38],"python3","rnet_twitter","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Ft\u002Ftwitter-auto-engage",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":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill twitter-auto-engage",{"tool":54,"command":55},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill twitter-auto-engage",{"tool":57,"command":58},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill twitter-auto-engage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Ft\u002Ftwitter-auto-engage\u002FSKILL.md",true,[],[63,70,77,84,91,98],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"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":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"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",[],[]]