[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C54YRWR800XFXFA1ES45WN":3,"skill-same:01M6C54YRWR800XFXFA1ES45WN":78},{"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":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6C54YRWR800XFXFA1ES45WN","hypernexus",null,"HyperNexus AI control plane — persistent L2 vector memory, semantic MCP tool discovery across 60+ servers, knowledge graph, session management, billing, agent orchestration, and 400+ API endpoints. Use when the task benefits from cross-session memory (scratchpad, facts, observations), tool discovery across MCP servers, knowledge ingestion, repo analysis, system health checks, or routing through the HyperNexus Go kernel on port 7778. Trigger on mentions of 'hypernexus', 'HN', 'scratchpad', 'cross-session memory', 'MCP tools', 'tool discovery', 'knowledge graph', 'agent memory', or 'control plane'.","MDMAtk\u002FTormentNexus","MDMAtk","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F288684999?v=4","01M6C54H4AG0BYB3HTFA4C0CBJ","01M6C54H8146YDG94N9KWXV521",13,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002FMDMAtk\u002FTormentNexus\u002Fblob\u002Fmain\u002Fintegrations\u002Fmimo\u002Fskills\u002Fhypernexus\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"discovery","ingestion","use","session","repo","tool","system","knowledge","health","MCP","api","analysis","knowledge graph","vector","agent memory","routing","orchestration","memory","kernel","2026-11-10 10:12:30",false,"---\nname: hypernexus\ndescription: \"HyperNexus AI control plane — persistent L2 vector memory, semantic MCP tool discovery across 60+ servers, knowledge graph, session management, billing, agent orchestration, and 400+ API endpoints. Use when the task benefits from cross-session memory (scratchpad, facts, observations), tool discovery across MCP servers, knowledge ingestion, repo analysis, system health checks, or routing through the HyperNexus Go kernel on port 7778. Trigger on mentions of 'hypernexus', 'HN', 'scratchpad', 'cross-session memory', 'MCP tools', 'tool discovery', 'knowledge graph', 'agent memory', or 'control plane'.\"\n---\n\n# HyperNexus Integration\n\nHyperNexus is a local AI control plane running a Go kernel on port 7778 (dashboard 7779) with persistent multi-tier memory (L1 scratchpad, L2 vector store, L3 cold archive), semantic tool discovery across 60+ MCP servers \u002F 26,000+ tools, knowledge graph, session import, and agent orchestration.\n\n## When to Use\n\n- Start of any multi-step task → harvest prior context (`hypernexus_context_harvest` \u002F `hypernexus_search_memory`)\n- After a decision, gotcha, or non-obvious finding → store it (`hypernexus_add_fact` \u002F `hypernexus_record_observation`)\n- When you need a capability you don't have → discover tools (`hypernexus_mcp_search` \u002F `hypernexus_tool_discover`) then route (`hypernexus_mcp_call`)\n- When the user asks about system health, billing, or the repo → `hypernexus_system_status`, `hypernexus_billing_status`, `hypernexus_repomap`\n\n## MiMo Desktop Tools (native)\n\n| Tool | Purpose |\n|---|---|\n| `hypernexus_search_memory` | Keyword search over persistent memory |\n| `hypernexus_memory_vector_search` | Semantic \u002F conceptual memory recall |\n| `hypernexus_memory_list` | List recent facts |\n| `hypernexus_add_fact` | Store a fact \u002F decision |\n| `hypernexus_record_observation` | Record a knowledge-graph observation |\n| `hypernexus_knowledge_graph` | Add entities\u002Frelations or search the graph |\n| `hypernexus_context_harvest` | Pull relevant L2 context for a task |\n| `hypernexus_session_search` | Search imported sessions |\n| `hypernexus_session_context` | Get\u002Fset session goal & objective |\n| `hypernexus_mcp_search` | Semantic MCP tool search |\n| `hypernexus_tool_discover` | Broad capability discovery |\n| `hypernexus_mcp_call` | Route a call to a downstream MCP tool |\n| `hypernexus_code_search` | Pattern \u002F AST \u002F semantic code search |\n| `hypernexus_repomap` | Repository map with symbols |\n| `hypernexus_system_status` | Kernel + memory + MCP health |\n| `hypernexus_billing_status` | Provider quotas & costs |\n\n## HTTP API (port 7778)\n\n```bash\n# Memory\ncurl -X POST http:\u002F\u002Flocalhost:7778\u002Fapi\u002Fmemory\u002Ffacts\u002Fadd -H 'Content-Type: application\u002Fjson' \\\n  -d '{\"title\":\"...\",\"content\":\"...\",\"tags\":[\"...\"],\"namespace\":\"project\"}'\ncurl -s \"http:\u002F\u002Flocalhost:7778\u002Fapi\u002Fmemory\u002Fsearch?query=\u003Cterm>&limit=\u003Cn>\"\n\n# MCP discovery & routing\ncurl -s \"http:\u002F\u002Flocalhost:7778\u002Fapi\u002Fmcp\u002Ftools\u002Fsearch?query=\u003Cnatural+language>\"\ncurl -X POST http:\u002F\u002Flocalhost:7778\u002Fapi\u002Fmcp\u002Ftools\u002Fcall -H 'Content-Type: application\u002Fjson' \\\n  -d '{\"serverName\":\"...\",\"toolName\":\"...\",\"arguments\":{}}'\n\n# System\ncurl -s http:\u002F\u002Flocalhost:7778\u002Fhealth\ncurl -s http:\u002F\u002Flocalhost:7778\u002Fapi\u002Fsystem\u002Fstatus\ncurl -s http:\u002F\u002Flocalhost:7778\u002Fapi\u002Fbilling\u002Fstatus\n```\n\n## MiMoCode CLI Commands\n\n- `\u002Fhn-store` — store a memory fact\n- `\u002Fhn-search` — search persistent memory\n- `\u002Fhn-status` — system status\n- `\u002Fhn-tools` — discover MCP tools\n- `\u002Fhn-session` — session context \u002F search\n\n## Best Practices\n\n1. **Recall before you write**: search memory before large tasks.\n2. **Store immediately**: non-obvious findings decay fast — persist them when found.\n3. **Discover then route**: use `hypernexus_mcp_search` before hardcoding tool names.\n4. **Graph what matters**: entities + relations compound into durable knowledge.\n5. The Go kernel is the source of truth — prefer the HTTP API over shell improvisation.\n","# HyperNexus Integration\n\nHyperNexus is a local AI control plane running a Go kernel on port 7778 (dashboard 7779) with persistent multi-tier memory (L1 scratchpad, L2 vector store, L3 cold archive), semantic tool discovery across 60+ MCP servers \u002F 26,000+ tools, knowledge graph, session import, and agent orchestration.\n\n## When to Use\n\n- Start of any multi-step task → harvest prior context (`hypernexus_context_harvest` \u002F `hypernexus_search_memory`)\n- After a decision, gotcha, or non-obvious finding → store it (`hypernexus_add_fact` \u002F `hypernexus_record_observation`)\n- When you need a capability you don't have → discover tools (`hypernexus_mcp_search` \u002F `hypernexus_tool_discover`) then route (`hypernexus_mcp_call`)\n- When the user asks about system health, billing, or the repo → `hypernexus_system_status`, `hypernexus_billing_status`, `hypernexus_repomap`\n\n## MiMo Desktop Tools (native)\n\n| Tool | Purpose |\n|---|---|\n| `hypernexus_search_memory` | Keyword search over persistent memory |\n| `hypernexus_memory_vector_search` | Semantic \u002F conceptual memory recall |\n| `hypernexus_memory_list` | List recent facts |\n| `hypernexus_add_fact` | Store a fact \u002F decision |\n| `hypernexus_record_observation` | Record a knowledge-graph observation |\n| `hypernexus_knowledge_graph` | Add entities\u002Frelations or search the graph |\n| `hypernexus_context_harvest` | Pull relevant L2 context for a task |\n| `hypernexus_session_search` | Search imported sessions |\n| `hypernexus_session_context` | Get\u002Fset session goal & objective |\n| `hypernexus_mcp_search` | Semantic MCP tool search |\n| `hypernexus_tool_discover` | Broad capability discovery |\n| `hypernexus_mcp_call` | Route a call to a downstream MCP tool |\n| `hypernexus_code_search` | Pattern \u002F AST \u002F semantic code search |\n| `hypernexus_repomap` | Repository map with symbols |\n| `hypernexus_system_status` | Kernel + memory + MCP health |\n| `hypernexus_billing_status` | Provider quotas & costs |\n\n## HTTP API (port 7778)\n\n```bash\n# Memory\ncurl -X POST http:\u002F\u002Flocalhost:7778\u002Fapi\u002Fmemory\u002Ffacts\u002Fadd -H 'Content-Type: application\u002Fjson' \\\n  -d '{\"title\":\"...\",\"content\":\"...\",\"tags\":[\"...\"],\"namespace\":\"project\"}'\ncurl -s \"http:\u002F\u002Flocalhost:7778\u002Fapi\u002Fmemory\u002Fsearch?query=\u003Cterm>&limit=\u003Cn>\"\n\n# MCP discovery & routing\ncurl -s \"http:\u002F\u002Flocalhost:7778\u002Fapi\u002Fmcp\u002Ftools\u002Fsearch?query=\u003Cnatural+language>\"\ncurl -X POST http:\u002F\u002Flocalhost:7778\u002Fapi\u002Fmcp\u002Ftools\u002Fcall -H 'Content-Type: application\u002Fjson' \\\n  -d '{\"serverName\":\"...\",\"toolName\":\"...\",\"arguments\":{}}'\n\n# System\ncurl -s http:\u002F\u002Flocalhost:7778\u002Fhealth\ncurl -s http:\u002F\u002Flocalhost:7778\u002Fapi\u002Fsystem\u002Fstatus\ncurl -s http:\u002F\u002Flocalhost:7778\u002Fapi\u002Fbilling\u002Fstatus\n```\n\n## MiMoCode CLI Commands\n\n- `\u002Fhn-store` — store a memory fact\n- `\u002Fhn-search` — search persistent memory\n- `\u002Fhn-status` — system status\n- `\u002Fhn-tools` — discover MCP tools\n- `\u002Fhn-session` — session context \u002F search\n\n## Best Practices\n\n1. **Recall before you write**: search memory before large tasks.\n2. **Store immediately**: non-obvious findings decay fast — persist them when found.\n3. **Discover then route**: use `hypernexus_mcp_search` before hardcoding tool names.\n4. **Graph what matters**: entities + relations compound into durable knowledge.\n5. The Go kernel is the source of truth — prefer the HTTP API over shell improvisation.\n",{"name":5,"description":7},"main","6079b2fd99329bb8a099e7708b0567b93edf8206","integrations\u002Fmimo\u002Fskills\u002Fhypernexus",2,"https:\u002F\u002Fgithub.com\u002FMDMAtk\u002FTormentNexus","https:\u002F\u002Fgithub.com\u002FMDMAtk","2026-11-07 14:28:49",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add MDMAtk\u002FTormentNexus --skill hypernexus",{"tool":60,"command":61},"bunx","bunx skills add MDMAtk\u002FTormentNexus --skill hypernexus",{"tool":63,"command":64},"pnpm","pnpm dlx skills add MDMAtk\u002FTormentNexus --skill hypernexus","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMDMAtk\u002FTormentNexus\u002Fblob\u002Fmain\u002Fintegrations\u002Fmimo\u002Fskills\u002Fhypernexus\u002FSKILL.md",true,[68,74],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"locales\u002Fen-US.json","REFERENCE","参考文档",138,"https:\u002F\u002Fgithub.com\u002FMDMAtk\u002FTormentNexus\u002Fblob\u002Fmain\u002Fintegrations\u002Fmimo\u002Fskills\u002Fhypernexus\u002Flocales\u002Fen-US.json",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"locales\u002Fzh-CN.json",131,"https:\u002F\u002Fgithub.com\u002FMDMAtk\u002FTormentNexus\u002Fblob\u002Fmain\u002Fintegrations\u002Fmimo\u002Fskills\u002Fhypernexus\u002Flocales\u002Fzh-CN.json",[79,109,124,138,153,170],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":88,"publishedAt":42},"01M6C5659TDGC363E5EWMQZJGZ","tdd-rust","TDD workflow for RTK filter development. Red-Green-Refactor with Rust idioms. Real fixtures, token savings assertions, snapshot tests with insta. Auto-triggers on new filter implementation.","https:\u002F\u002Fgithub.com\u002FMDMAtk\u002FTormentNexus\u002Fblob\u002Fmain\u002Fthird_party\u002Frtk\u002F.claude\u002Fskills\u002Ftdd-rust\u002FSKILL.md",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",[89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"tdd rust","tdd","rust","testing","implement","command","token-savings","snapshots","filters","red-green-refactor","test coverage","auto","fix","coverage","Bash","development","add command","write tests","test","workflow",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":42},"01M6C562NZPX3J6W8F6P4KZMV1","ship","Build, commit, push & version bump workflow - automates the complete release cycle","https:\u002F\u002Fgithub.com\u002FMDMAtk\u002FTormentNexus\u002Fblob\u002Fmain\u002Fthird_party\u002Frtk\u002F.claude\u002Fskills\u002Fship\u002FSKILL.md",[],[111,116,117,118,119,120,121,103,122,123,108],"push","version","edit","write","read","grep","release","commit",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":42},"01M6C55ZXSNWBB861V5GGYR775","security-guardian","CLI security expert for RTK - command injection, shell escaping, hook security","https:\u002F\u002Fgithub.com\u002FMDMAtk\u002FTormentNexus\u002Fblob\u002Fmain\u002Fthird_party\u002Frtk\u002F.claude\u002Fskills\u002Fsecurity-guardian\u002FSKILL.md",[],[131,132,133,134,120,103,121,135,136,137,94],"security guardian","guardian","security","rtk","shell","injection","cli",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":42},"01M6C55XHCBK612DXDAD08GGE1","rtk-triage","Triage complet RTK : exécute issue-triage + pr-triage en parallèle, puis croise les données pour détecter doubles couvertures, trous sécurité, P0 sans PR, et conflits internes. Sauvegarde dans claudedocs\u002FRTK-YYYY-MM-DD.md. Args: \"en\"\u002F\"fr\" pour la langue (défaut: fr), \"save\" pour forcer la sauvegarde.","https:\u002F\u002Fgithub.com\u002FMDMAtk\u002FTormentNexus\u002Fblob\u002Fmain\u002Fthird_party\u002Frtk\u002F.claude\u002Fskills\u002Frtk-triage\u002FSKILL.md",[],[145,134,146,133,39,120,147,119,103,148,34,149,150,151,152],"rtk triage","triage","cross-analysis","save","sans","dd","issues","pr",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":163,"publishedAt":42},"01M6C55V1RDCNFJ019HRA16ZHM","rtk-tdd","Enforces TDD (Red-Green-Refactor) for Rust development. Auto-triggers on implementation, testing, refactoring, and bug fixing tasks. Provides Rust-idiomatic testing patterns with anyhow\u002Fthiserror, cfg(test), and Arrange-Act-Assert workflow.","https:\u002F\u002Fgithub.com\u002FMDMAtk\u002FTormentNexus\u002Fblob\u002Fmain\u002Fthird_party\u002Frtk\u002F.claude\u002Fskills\u002Frtk-tdd\u002FSKILL.md",[159,162],{"categoryNo":160,"categoryName":161,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":86,"categoryName":87,"taxonomyType":20,"taxonomyTypeDesc":21},[164,134,90,165,92,98,91,100,118,119,120,103,166,167,168,104,169,107,108],"rtk tdd","refactoring","CFG","testing patterns","refactor","tasks",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":42},"01M6C55RQ5QH5MBSYXMC8KF0WV","repo-recap","Generate a comprehensive repo recap (PRs, issues, releases) for sharing with team. Pass \"en\" or \"fr\" as argument for language (default fr).","https:\u002F\u002Fgithub.com\u002FMDMAtk\u002FTormentNexus\u002Fblob\u002Fmain\u002Fthird_party\u002Frtk\u002F.claude\u002Fskills\u002Frepo-recap\u002FSKILL.md",[],[177,178,27,103,121,151,179,180,181,120],"repo recap","recap","team","sharing","generate"]