[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBBBPNRSZMHMEJCJKB7H0R":3,"skill-same:01M6DBBBPNRSZMHMEJCJKB7H0R":60},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":14,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":45,"install":46,"resources":59},"01M6DBBBPNRSZMHMEJCJKB7H0R","drive-biomni-lab",null,"Use when the user wants to run a biomedical\u002Fclinical-genomics analysis on the hosted Biomni Lab (biomni.phylo.bio, Phylo Inc.) from Claude Code - starting or continuing a Biomni agent task, controlling effort\u002Fmodel, attaching skills or @-resources, polling a run, switching\u002Frotating accounts, or checking usage\u002Fbilling. Triggers: \"run this on Biomni\", \"rotate Biomni accounts\", or the bm_* tools.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdrive-biomni-lab\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"biomni","drive","drive biomni lab","run","code","Tools","analysis","model","user","use","task","genomics","biomedical","switching","triggers","clinical","2026-11-10 10:12:30",false,"---\nname: drive-biomni-lab\ndescription: \"Use when the user wants to run a biomedical\u002Fclinical-genomics analysis on the hosted Biomni Lab (biomni.phylo.bio, Phylo Inc.) from Claude Code - starting or continuing a Biomni agent task, controlling effort\u002Fmodel, attaching skills or @-resources, polling a run, switching\u002Frotating accounts, or checking usage\u002Fbilling. Triggers: \\\"run this on Biomni\\\", \\\"rotate Biomni accounts\\\", or the bm_* tools.\"\n---\n\n# Drive Biomni Lab (hosted) via the cookie-broker connector\n\nThe cloud-hub **`biomni`** backend exposes 25 `bm_*` tools that drive the hosted\nBiomni Lab far beyond its official 10-tool claude.ai connector — **effort control,\nskills, @-resources, live HPC\u002FGPU introspection, usage-aware account rotation** —\nwhile **never handling the credential** (a local broker injects the `session_id`\ncookie; you only ever see masked previews). Setup + architecture:\n`tools\u002Fmcp\u002Fcloud-hub\u002Fbiomni-mcp\u002FREADME.md`.\n\n## Preconditions (fail fast, don't improvise auth)\n\n- The `bm_*` tools are live (hub restarted after the backend was registered).\n- For each account, its **daemons are running** — debug Chrome (signed in) + broker +\n  refresher (see the biomni-mcp README \u002F `autostart.py`).\n- If a call returns **401 \u002F no-auth**, the account's cookie is stale → tell the user to\n  ensure that account's debug Chrome is signed in and its refresher is running. **Do\n  NOT** try to obtain or paste a token yourself — auth is the broker's job.\n\n## The task loop\n\n1. **Pick the account** — `bm_account_list` \u002F `bm_account_current`; switch with\n   `bm_account_switch` or rotate with `bm_account_cycle`. Before a heavy run, check\n   `bm_billing_balance` and rotate to an account with headroom (runs consume usage).\n2. **Pick a project** — `bm_list_projects` (or `bm_create_project`).\n3. **Start a task** — `bm_create_session(project_id, content, model_profile=…)`:\n   - `model_profile` is the EFFORT tier: `standard` (default) | `fast` | `premium`\n     (`\"max\"` is accepted as an alias for premium). Use `premium` for hard\u002Fmultimodal\n     work, `fast` for cheap iteration.\n   - `submit_initial_message=True` (default) starts the run immediately.\n   - To attach **skills** or **@-resources**, instead create with\n     `submit_initial_message=False`, then `bm_send_message(session_id, content, …)` +\n     `bm_start_processing`.\n4. **Attach skills \u002F resources** (via `bm_send_message`):\n   - **Skills** → `attached_skills_json` = a JSON array of skills from `bm_list_skills`\n     (`{id,name,category,intent:\"use\"}`); only *active* skills apply\n     (`bm_set_skill_status`).\n   - **Resources** (tools\u002Fdatabases\u002Fpackages) → `@name` mentions **inside** `content`\n     (e.g. `\"@Addgene @airr analyse …\"`). There is no separate field.\n5. **Watch it** — poll `bm_get_messages` (reliable) for the reasoning\u002Ftool trace;\n   `bm_session_runtime(session_id, kind=…)` for live compute (`background-processes` |\n   `gpu-sandboxes` | `hpc-jobs` | `hpc-pipelines` | `machines`);\n   `bm_get_streaming` for a best-effort live peek. Biomni tasks take 30 s–10 min —\n   poll a few times, don't spin. `bm_cancel` stops a run.\n6. **Results** — `bm_list_results` lists output file names\u002Fsizes; the files are\n   downloaded from the Biomni web app (not directly). Point the user to the run link.\n\n## Cautions\n\n- **$$$ \u002F billable:** `bm_create_session(submit_initial_message=True)` and\n  `bm_start_processing` consume the account's usage (real HPC\u002FGPU). Confirm intent for\n  large or repeated runs; rotate accounts with `bm_billing_balance` before one runs dry.\n- **`bm_api_raw`** can reach mutating\u002F`DELETE` routes on the user's own account —\n  confirm before calling those.\n- **Trust but verify Biomni output.** Biomni is an autonomous agent and has produced\n  confident-but-wrong numbers\u002Fcitations before; treat its results as\n  hypothesis-generation and have it (or a second pass) self-audit before you rely on them.\n\n## Escape hatch\n\n`bm_api_raw(method, path, body_json, query_json)` calls ANY `api.phylo.bio` endpoint\n(e.g. `\u002Fv2\u002Fusers\u002Fme\u002Fmemory`, `\u002Fv2\u002Fmcp\u002Fservers`) — use it for anything the 25 typed\ntools don't cover.\n","# Drive Biomni Lab (hosted) via the cookie-broker connector\n\nThe cloud-hub **`biomni`** backend exposes 25 `bm_*` tools that drive the hosted\nBiomni Lab far beyond its official 10-tool claude.ai connector — **effort control,\nskills, @-resources, live HPC\u002FGPU introspection, usage-aware account rotation** —\nwhile **never handling the credential** (a local broker injects the `session_id`\ncookie; you only ever see masked previews). Setup + architecture:\n`tools\u002Fmcp\u002Fcloud-hub\u002Fbiomni-mcp\u002FREADME.md`.\n\n## Preconditions (fail fast, don't improvise auth)\n\n- The `bm_*` tools are live (hub restarted after the backend was registered).\n- For each account, its **daemons are running** — debug Chrome (signed in) + broker +\n  refresher (see the biomni-mcp README \u002F `autostart.py`).\n- If a call returns **401 \u002F no-auth**, the account's cookie is stale → tell the user to\n  ensure that account's debug Chrome is signed in and its refresher is running. **Do\n  NOT** try to obtain or paste a token yourself — auth is the broker's job.\n\n## The task loop\n\n1. **Pick the account** — `bm_account_list` \u002F `bm_account_current`; switch with\n   `bm_account_switch` or rotate with `bm_account_cycle`. Before a heavy run, check\n   `bm_billing_balance` and rotate to an account with headroom (runs consume usage).\n2. **Pick a project** — `bm_list_projects` (or `bm_create_project`).\n3. **Start a task** — `bm_create_session(project_id, content, model_profile=…)`:\n   - `model_profile` is the EFFORT tier: `standard` (default) | `fast` | `premium`\n     (`\"max\"` is accepted as an alias for premium). Use `premium` for hard\u002Fmultimodal\n     work, `fast` for cheap iteration.\n   - `submit_initial_message=True` (default) starts the run immediately.\n   - To attach **skills** or **@-resources**, instead create with\n     `submit_initial_message=False`, then `bm_send_message(session_id, content, …)` +\n     `bm_start_processing`.\n4. **Attach skills \u002F resources** (via `bm_send_message`):\n   - **Skills** → `attached_skills_json` = a JSON array of skills from `bm_list_skills`\n     (`{id,name,category,intent:\"use\"}`); only *active* skills apply\n     (`bm_set_skill_status`).\n   - **Resources** (tools\u002Fdatabases\u002Fpackages) → `@name` mentions **inside** `content`\n     (e.g. `\"@Addgene @airr analyse …\"`). There is no separate field.\n5. **Watch it** — poll `bm_get_messages` (reliable) for the reasoning\u002Ftool trace;\n   `bm_session_runtime(session_id, kind=…)` for live compute (`background-processes` |\n   `gpu-sandboxes` | `hpc-jobs` | `hpc-pipelines` | `machines`);\n   `bm_get_streaming` for a best-effort live peek. Biomni tasks take 30 s–10 min —\n   poll a few times, don't spin. `bm_cancel` stops a run.\n6. **Results** — `bm_list_results` lists output file names\u002Fsizes; the files are\n   downloaded from the Biomni web app (not directly). Point the user to the run link.\n\n## Cautions\n\n- **$$$ \u002F billable:** `bm_create_session(submit_initial_message=True)` and\n  `bm_start_processing` consume the account's usage (real HPC\u002FGPU). Confirm intent for\n  large or repeated runs; rotate accounts with `bm_billing_balance` before one runs dry.\n- **`bm_api_raw`** can reach mutating\u002F`DELETE` routes on the user's own account —\n  confirm before calling those.\n- **Trust but verify Biomni output.** Biomni is an autonomous agent and has produced\n  confident-but-wrong numbers\u002Fcitations before; treat its results as\n  hypothesis-generation and have it (or a second pass) self-audit before you rely on them.\n\n## Escape hatch\n\n`bm_api_raw(method, path, body_json, query_json)` calls ANY `api.phylo.bio` endpoint\n(e.g. `\u002Fv2\u002Fusers\u002Fme\u002Fmemory`, `\u002Fv2\u002Fmcp\u002Fservers`) — use it for anything the 25 typed\ntools don't cover.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fdrive-biomni-lab","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill drive-biomni-lab",{"tool":52,"command":53},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill drive-biomni-lab",{"tool":55,"command":56},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill drive-biomni-lab","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdrive-biomni-lab\u002FSKILL.md",true,[],[61,81,112,139,153,168],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":35},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[68,69,70,71,72,29,73,74,75,28,76,77,78,79,80],"clarify requirements","clarify","requirements","risk","options","prompts","goal","scanning","context","repo","injection","execution","file",{"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":92,"publishedAt":35},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[93,94,95,96,97,98,99,100,101,102,103,104,105,106,28,107,108,109,110,111],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":124,"publishedAt":35},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[118,121],{"categoryNo":119,"categoryName":120,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":122,"categoryName":123,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000008","测试与质量",[125,126,127,128,129,130,131,132,133,134,94,135,136,137,138],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":35},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[141,146,147,148,149,150,151,152],"setup","report","project","installation","project setup","issues","state",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":160,"publishedAt":35},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[159],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},[155,161,29,162,163,164,28,27,165,166,167],"start issue","issue","ready","work on issue","work","work on","development",{"skillNo":169,"name":146,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":35},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[146,148,109,174,150,175],"files","interactive"]