[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72ZAVNT91RKTF5DS7A0GJVC":3,"skill-same:01M72ZAVNT91RKTF5DS7A0GJVC":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M72ZAVNT91RKTF5DS7A0GJVC","connections-optimizer",null,"Reorganize the user's X and LinkedIn network with review-first pruning, add\u002Ffollow recommendations, and channel-specific warm outreach drafted in the user's real voice. Use when the user wants to clean up following lists, grow toward current priorities, or rebalance a social graph around higher-signal relationships.","SriramGandhiS\u002FSkills","SriramGandhiS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211849986?v=4","01M72WQCW12BYX71C6WN584TTA","Sriram S","01M72WQCWTJ2RD0ET1X31AF1RC",1,"MIT","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fskills\u002Fconnections-optimizer\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: connections-optimizer\ndescription: Reorganize the user's X and LinkedIn network with review-first pruning, add\u002Ffollow recommendations, and channel-specific warm outreach drafted in the user's real voice. Use when the user wants to clean up following lists, grow toward current priorities, or rebalance a social graph around higher-signal relationships.\norigin: ECC\n---\n\n# Connections Optimizer\n\nReorganize the user's network instead of treating outbound as a one-way prospecting list.\n\nThis skill handles:\n\n- X following cleanup and expansion\n- LinkedIn follow and connection analysis\n- review-first prune queues\n- add and follow recommendations\n- warm-path identification\n- Apple Mail, X DM, and LinkedIn draft generation in the user's real voice\n\n## When to Activate\n\n- the user wants to prune their X following\n- the user wants to rebalance who they follow or stay connected to\n- the user says \"clean up my network\", \"who should I unfollow\", \"who should I follow\", \"who should I reconnect with\"\n- outreach quality depends on network structure, not just cold list generation\n\n## Required Inputs\n\nCollect or infer:\n\n- current priorities and active work\n- target roles, industries, geos, or ecosystems\n- platform selection: X, LinkedIn, or both\n- do-not-touch list\n- mode: `light-pass`, `default`, or `aggressive`\n\nIf the user does not specify a mode, use `default`.\n\n## Tool Requirements\n\n### Preferred\n\n- `x-api` for X graph inspection and recent activity\n- `lead-intelligence` for target discovery and warm-path ranking\n- `social-graph-ranker` when the user wants bridge value scored independently of the broader lead workflow\n- Exa \u002F deep research for person and company enrichment\n- `brand-voice` before drafting outbound\n\n### Fallbacks\n\n- browser control for LinkedIn analysis and drafting\n- browser control for X if API coverage is constrained\n- Apple Mail or Mail.app drafting via desktop automation when email is the right channel\n\n## Safety Defaults\n\n- default is review-first, never blind auto-pruning\n- X: prune only accounts the user follows, never followers\n- LinkedIn: treat 1st-degree connection removal as manual-review-first\n- do not auto-send DMs, invites, or emails\n- emit a ranked action plan and drafts before any apply step\n\n## Platform Rules\n\n### X\n\n- mutuals are stickier than one-way follows\n- non-follow-backs can be pruned more aggressively\n- heavily inactive or disappeared accounts should surface quickly\n- engagement, signal quality, and bridge value matter more than raw follower count\n\n### LinkedIn\n\n- API-first if the user actually has LinkedIn API access\n- browser workflow must work when API access is missing\n- distinguish outbound follows from accepted 1st-degree connections\n- outbound follows can be pruned more freely\n- accepted 1st-degree connections should default to review, not auto-remove\n\n## Modes\n\n### `light-pass`\n\n- prune only high-confidence low-value one-way follows\n- surface the rest for review\n- generate a small add\u002Ffollow list\n\n### `default`\n\n- balanced prune queue\n- balanced keep list\n- ranked add\u002Ffollow queue\n- draft warm intros or direct outreach where useful\n\n### `aggressive`\n\n- larger prune queue\n- lower tolerance for stale non-follow-backs\n- still review-gated before apply\n\n## Scoring Model\n\nUse these positive signals:\n\n- reciprocity\n- recent activity\n- alignment to current priorities\n- network bridge value\n- role relevance\n- real engagement history\n- recent presence and responsiveness\n\nUse these negative signals:\n\n- disappeared or abandoned account\n- stale one-way follow\n- off-priority topic cluster\n- low-value noise\n- repeated non-response\n- no follow-back when many better replacements exist\n\nMutuals and real warm-path bridges should be penalized less aggressively than one-way follows.\n\n## Workflow\n\n1. Capture priorities, do-not-touch constraints, and selected platforms.\n2. Pull the current following \u002F connection inventory.\n3. Score prune candidates with explicit reasons.\n4. Score keep candidates with explicit reasons.\n5. Use `lead-intelligence` plus research surfaces to rank expansion candidates.\n6. Match the right channel:\n   - X DM for warm, fast social touch points\n   - LinkedIn message for professional graph adjacency\n   - Apple Mail draft for higher-context intros or outreach\n7. Run `brand-voice` before drafting messages.\n8. Return a review pack before any apply step.\n\n## Review Pack Format\n\n```text\nCONNECTIONS OPTIMIZER REPORT\n============================\n\nMode:\nPlatforms:\nPriority Set:\n\nPrune Queue\n- handle \u002F profile\n  reason:\n  confidence:\n  action:\n\nReview Queue\n- handle \u002F profile\n  reason:\n  risk:\n\nKeep \u002F Protect\n- handle \u002F profile\n  bridge value:\n\nAdd \u002F Follow Targets\n- person\n  why now:\n  warm path:\n  preferred channel:\n\nDrafts\n- X DM:\n- LinkedIn:\n- Apple Mail:\n```\n\n## Outbound Rules\n\n- Default email path is Apple Mail \u002F Mail.app draft creation.\n- Do not send automatically.\n- Choose the channel based on warmth, relevance, and context depth.\n- Do not force a DM when an email or no outreach is the right move.\n- Drafts should sound like the user, not like automated sales copy.\n\n## Related Skills\n\n- `brand-voice` for the reusable voice profile\n- `social-graph-ranker` for the standalone bridge-scoring and warm-path math\n- `lead-intelligence` for weighted target and warm-path discovery\n- `x-api` for X graph access, drafting, and optional apply flows\n- `content-engine` when the user also wants public launch content around network moves\n","# Connections Optimizer\n\nReorganize the user's network instead of treating outbound as a one-way prospecting list.\n\nThis skill handles:\n\n- X following cleanup and expansion\n- LinkedIn follow and connection analysis\n- review-first prune queues\n- add and follow recommendations\n- warm-path identification\n- Apple Mail, X DM, and LinkedIn draft generation in the user's real voice\n\n## When to Activate\n\n- the user wants to prune their X following\n- the user wants to rebalance who they follow or stay connected to\n- the user says \"clean up my network\", \"who should I unfollow\", \"who should I follow\", \"who should I reconnect with\"\n- outreach quality depends on network structure, not just cold list generation\n\n## Required Inputs\n\nCollect or infer:\n\n- current priorities and active work\n- target roles, industries, geos, or ecosystems\n- platform selection: X, LinkedIn, or both\n- do-not-touch list\n- mode: `light-pass`, `default`, or `aggressive`\n\nIf the user does not specify a mode, use `default`.\n\n## Tool Requirements\n\n### Preferred\n\n- `x-api` for X graph inspection and recent activity\n- `lead-intelligence` for target discovery and warm-path ranking\n- `social-graph-ranker` when the user wants bridge value scored independently of the broader lead workflow\n- Exa \u002F deep research for person and company enrichment\n- `brand-voice` before drafting outbound\n\n### Fallbacks\n\n- browser control for LinkedIn analysis and drafting\n- browser control for X if API coverage is constrained\n- Apple Mail or Mail.app drafting via desktop automation when email is the right channel\n\n## Safety Defaults\n\n- default is review-first, never blind auto-pruning\n- X: prune only accounts the user follows, never followers\n- LinkedIn: treat 1st-degree connection removal as manual-review-first\n- do not auto-send DMs, invites, or emails\n- emit a ranked action plan and drafts before any apply step\n\n## Platform Rules\n\n### X\n\n- mutuals are stickier than one-way follows\n- non-follow-backs can be pruned more aggressively\n- heavily inactive or disappeared accounts should surface quickly\n- engagement, signal quality, and bridge value matter more than raw follower count\n\n### LinkedIn\n\n- API-first if the user actually has LinkedIn API access\n- browser workflow must work when API access is missing\n- distinguish outbound follows from accepted 1st-degree connections\n- outbound follows can be pruned more freely\n- accepted 1st-degree connections should default to review, not auto-remove\n\n## Modes\n\n### `light-pass`\n\n- prune only high-confidence low-value one-way follows\n- surface the rest for review\n- generate a small add\u002Ffollow list\n\n### `default`\n\n- balanced prune queue\n- balanced keep list\n- ranked add\u002Ffollow queue\n- draft warm intros or direct outreach where useful\n\n### `aggressive`\n\n- larger prune queue\n- lower tolerance for stale non-follow-backs\n- still review-gated before apply\n\n## Scoring Model\n\nUse these positive signals:\n\n- reciprocity\n- recent activity\n- alignment to current priorities\n- network bridge value\n- role relevance\n- real engagement history\n- recent presence and responsiveness\n\nUse these negative signals:\n\n- disappeared or abandoned account\n- stale one-way follow\n- off-priority topic cluster\n- low-value noise\n- repeated non-response\n- no follow-back when many better replacements exist\n\nMutuals and real warm-path bridges should be penalized less aggressively than one-way follows.\n\n## Workflow\n\n1. Capture priorities, do-not-touch constraints, and selected platforms.\n2. Pull the current following \u002F connection inventory.\n3. Score prune candidates with explicit reasons.\n4. Score keep candidates with explicit reasons.\n5. Use `lead-intelligence` plus research surfaces to rank expansion candidates.\n6. Match the right channel:\n   - X DM for warm, fast social touch points\n   - LinkedIn message for professional graph adjacency\n   - Apple Mail draft for higher-context intros or outreach\n7. Run `brand-voice` before drafting messages.\n8. Return a review pack before any apply step.\n\n## Review Pack Format\n\n```text\nCONNECTIONS OPTIMIZER REPORT\n============================\n\nMode:\nPlatforms:\nPriority Set:\n\nPrune Queue\n- handle \u002F profile\n  reason:\n  confidence:\n  action:\n\nReview Queue\n- handle \u002F profile\n  reason:\n  risk:\n\nKeep \u002F Protect\n- handle \u002F profile\n  bridge value:\n\nAdd \u002F Follow Targets\n- person\n  why now:\n  warm path:\n  preferred channel:\n\nDrafts\n- X DM:\n- LinkedIn:\n- Apple Mail:\n```\n\n## Outbound Rules\n\n- Default email path is Apple Mail \u002F Mail.app draft creation.\n- Do not send automatically.\n- Choose the channel based on warmth, relevance, and context depth.\n- Do not force a DM when an email or no outreach is the right move.\n- Drafts should sound like the user, not like automated sales copy.\n\n## Related Skills\n\n- `brand-voice` for the reusable voice profile\n- `social-graph-ranker` for the standalone bridge-scoring and warm-path math\n- `lead-intelligence` for weighted target and warm-path discovery\n- `x-api` for X graph access, drafting, and optional apply flows\n- `content-engine` when the user also wants public launch content around network moves\n",{"name":5,"origin":24,"description":7},"ECC","master","d6ca01da0f24a3b0e26e4a8b7b66cbd25d429f5d","skills\u002Fconnections-optimizer",0,"https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills","https:\u002F\u002Fgithub.com\u002FSriramGandhiS","https:\u002F\u002Fsriram.website\u002F","Curious guy who keeps tinkering until something works","2026-05-20 16:21:34",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add SriramGandhiS\u002FSkills --skill connections-optimizer",{"tool":40,"command":41},"bunx","bunx skills add SriramGandhiS\u002FSkills --skill connections-optimizer",{"tool":43,"command":44},"pnpm","pnpm dlx skills add SriramGandhiS\u002FSkills --skill connections-optimizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fskills\u002Fconnections-optimizer\u002FSKILL.md",true,[],[49,56,61,67,74,81],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M732609EPJWV13PVTX3GT4TM","webgpu-threejs-tsl","Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002Fskills\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":57,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7325XM47AGWB6K6C4VXKE6B","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7325WP6DES69JKC840VMFEP","verification-loop","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7325TFQF1DZTQ6J3WGQQ1VR","tdd-workflow","Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Ftdd-workflow\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7325RGV9AY9PK92D2V8KKPW","strategic-compact","Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fstrategic-compact\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7325MZC28SE86E7NMCNEFS4","security-review","Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment\u002Fsensitive features. Provides comprehensive security checklist and patterns.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fsecurity-review\u002FSKILL.md",[],[]]