[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DECVG08WTF6HQXHAG6EZVQ":3,"skill-same:01M6DECVG08WTF6HQXHAG6EZVQ":131},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6DECVG08WTF6HQXHAG6EZVQ","lightning-studio-driver",null,"Use when driving Lightning.ai Studios via the lightning_sdk (auth, account switching, org-aware teamspace\u002Fstudio discovery, create\u002Fstart\u002Fstop\u002F switch-machine, upload, run commands) or when installing a big licensed suite (e.g. Schrödinger) on a Studio and running GPU jobs (FEP\u002FMD) on it. Encodes.","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\u002Fskills\u002Flightning-studio-driver\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"lightning studio driver","lightning","use","switching","schrödinger","commands","upload","switch","jobs","stop","sdk","discovery","start","gpu","run","create","auth","2026-11-10 10:12:30",false,"---\nname: lightning-studio-driver\ndescription: \"Use when driving Lightning.ai Studios via the lightning_sdk (auth, account switching, org-aware teamspace\u002Fstudio discovery, create\u002Fstart\u002Fstop\u002F switch-machine, upload, run commands) or when installing a big licensed suite (e.g. Schrödinger) on a Studio and running GPU jobs (FEP\u002FMD) on it. Encodes.\"\n---\n\n# lightning-studio-driver\n\nDrive Lightning.ai Studios programmatically via `lightning_sdk` (installed at\n`C:\\Python314`). The `lightning` CLI is BROKEN on Windows (imports\n`simple_term_menu`→`termios`) — always use the SDK, never the CLI.\n\n## Credentials — the hard boundary\n\n- Auth = two env vars: `LIGHTNING_USER_ID` (non-secret UUID) + `LIGHTNING_API_KEY` (secret).\n- **The assistant NEVER types\u002Fwrites the API KEY** into any field, env var, or\n  config. Only READ it from the registry:\n  `[Environment]::GetEnvironmentVariable('LIGHTNING_API_KEY','User')`. The USER\n  sets the key. The assistant MAY set the non-secret `LIGHTNING_USER_ID` itself.\n- **setx pitfall (bites every time):** `setx VAR=value` (with `=`) SILENTLY\n  FAILS to update on Windows. Must be `setx VAR value` (SPACE). Verify after:\n  `[Environment]::GetEnvironmentVariable('VAR','User')`.\n- Keys pasted in chat are compromised → tell the user to ROTATE, then re-set.\n- In-process for a run: `$env:LIGHTNING_USER_ID = [Environment]::GetEnvironmentVariable('LIGHTNING_USER_ID','User')` (same for key), then run python.\n\n## Auth + WHO AM I\n\n```python\nfrom lightning_sdk.lightning_cloud.login import Auth\nfrom lightning_sdk.api.user_api import UserApi\na = Auth(); a.authenticate()\nuid = a.user_id\nuname = getattr(UserApi()._get_user_by_id(user_id=uid), \"username\", None)\n```\n`Auth()` resolves the account from `LIGHTNING_USER_ID` (it overrides — mismatched\nuser_id + key lands on the user_id's account). Confirm `uid`\u002F`uname` match the\naccount you expect BEFORE acting.\n\n## ★ Org-owned teamspaces — the discovery gap that wastes hours\n\n`User(name=uname).teamspaces` ONLY lists PERSONAL teamspaces. Studios created in\nan **organization** (the normal case when the web UI shows \"X Org\" \u002F URL\n`\u002F\u003Corg-slug>\u002F...`) are INVISIBLE to it → you'll see `teamspaces=0, studios=0`\nand wrongly conclude the account is empty. Enumerate via the org instead:\n\n```python\nfrom lightning_sdk.lightning_cloud.rest_client import LightningClient\nc = LightningClient()\norgs = c.organizations_service_list_organizations().organizations   # id, name, display_name\nmem  = c.projects_service_list_memberships().memberships             # teamspace name + project_id\n```\nThe org **`name`** (e.g. `prekzursiltm`) is what the SDK needs — NOT the URL\nslug (`prekzursil-org`) nor the display name (`PrekzursilTM`), which both fail.\nThen connect the teamspace and its studios:\n\n```python\nfrom lightning_sdk import Teamspace, Studio\nts = Teamspace(name=\"\u003Cteamspace-name>\", org=\"\u003Corg-name>\")   # e.g. quantum-paradox-exploration-project\nfor s in ts.studios: print(s.name, s.status, getattr(s,'machine','?'))\n```\nTwo accounts can have teamspaces with the SAME NAME but different `project_id` —\nthey are NOT shared; a studio in one is not in the other.\n\n## Studio lifecycle\n\n```python\nfrom lightning_sdk import Studio, Teamspace, Machine\nts = Teamspace(name=..., org=...)\ns = Studio(name=\"phenibut-fep\", teamspace=ts, create_ok=True)   # create or reuse\ns.start(Machine.CPU)          # cheap; use for install\u002Fupload\ns.switch_machine(Machine.A100)  # only for the GPU job\ns.run(\"bash -lc 'echo hi'\")   # exec a shell command, returns stdout\ns.upload_file(local, remote)  # or s.upload_folder(...)\ns.stop()                      # full stop (zero cost)\n```\n- `Machine` enum: `CPU, T4, L4, A100, A100_80GB, L40S, H100, …`. Availability is\n  cluster-dependent — `switch_machine(L40S)` may 404 \"accelerator not found\";\n  fall back A100→L4→T4. Studio filesystem persists across switch\u002Fstop\u002Fsleep.\n- **★ CHECK GPU AVAILABILITY + BALANCE BEFORE a big install.** A teamspace on\n  an AWS cluster may have **NO A100 at all** (\"accelerator lit-a100-1 not found\n  for this AWS cluster\") — only the machines its cluster offers work. AND\n  starting ANY GPU needs sufficient BALANCE (\"Insufficient balance to start the\n  cloud space, top up\") — ~11 credits was NOT enough for even L4\u002FT4. A studio\n  can install Schrödinger fine on CPU yet be UNABLE to run the GPU job. So:\n  before uploading 14 GB, probe `switch_machine(A100)` (or list cluster\n  machines) + confirm balance. If the FEP MUST run on A100, use an account whose\n  cluster HAS A100 and has balance (e.g. the one that ran it before) — don't\n  reinstall on a fresh account until GPU+balance are confirmed there.\n- **NEVER launch the GPU job if the machine is still CPU** — check\n  `nvidia-smi` returns a real GPU first; a failed `switch_machine` leaves you on\n  CPU and FEP+ on CPU is useless (weeks). Gate the launch on `GPU!=''`.\n- **Auto-sleep:** an idle Studio sleeps after ~10 min → status `sleeping`,\n  machine `-`, ZERO compute cost, filesystem intact. So an idle GPU stops\n  billing itself; you rarely need to force-stop to save credits.\n- Results\u002Flarge tool outputs paginate; `s.run` returns stdout as a string.\n\n## Free-tier reality (same failure modes as the Boltz free tier)\n\n- ~1 heavy job concurrent; free A100 ≈ a few hours + a ~4h session cap.\n- **Switching accounts ORPHANS in-flight work** (studio is account-scoped). Do\n  ONE thing → collect\u002Fconfirm → then switch. Never switch mid-run.\n- Fresh account has NO teamspace until web-UI onboarding (SDK can't bootstrap a\n  teamspace: `Studio(create_ok=True)` → \"Couldn't resolve teamspace\"). Once ANY\n  teamspace exists (org or personal), SDK create works.\n\n## cloud-hub rotation (like Modal's md_account_*)\n\ncloud-hub exposes `lg_account_list\u002Fcurrent\u002Fswitch\u002Fcycle\u002Fadd`. To avoid the setx\ndance, register named profiles — but keep the SECRET as an env REF, not a\nliteral, to honor the boundary:\n```\nlg_account_add(name=\"home\", env={\"LIGHTNING_USER_ID\":\"f09cac56-...\", \"LIGHTNING_API_KEY\":\"${LIGHTNING_API_KEY}\"})\n```\nFor multi-account rotation with distinct keys, give each account its own env var\n(`LIGHTNING_API_KEY_HOME`, …) that the user sets once, and reference it. Then\n`lg_account_switch \u003Cname>` swaps creds + respawns the backend — no setx per use.\n\n## Installing Schrödinger + running FEP (the heavy path)\n\nMirrors the Modal install (`compute\u002Fmodal_scripts\u002Fschrodinger_modal.py`) and the\n`lightning-a2d-fep` scaffold (`D:\u002FResearch\u002F_infra\u002Flightning-a2d-fep`):\n1. `s.start(Machine.CPU)`; upload `2026-2_Schrodinger_Linux.zip` (~14.4 GB) +\n   `26-2.lic` into `~\u002F_schrod_src\u002F`. **★ Upload backslash trap (bites every\n   time):** `Studio.upload_file(local, \"dir\u002Fsub\u002Ffile\")` NORMALIZES the remote\n   path to Windows `\\` ON THE CLIENT → the file lands as a FLAT file literally\n   named `dir\\sub\\file` (backslash is a valid Linux filename char), NOT inside\n   `dir\u002F`. Progress bar hits 100% and reports success, but `ls ~\u002Fdir` is empty.\n   The 14 GB is NOT lost — DON'T re-upload. Rename in place on the studio:\n   ```python\n   s.run(r\"\"\"python3 - \u003C\u003C'PY'\n   import os; h=os.path.expanduser(\"~\")\n   for n in list(os.listdir(h)):\n       if \"\\\\\" in n:\n           d=os.path.join(h,n.replace(\"\\\\\",\"\u002F\")); os.makedirs(os.path.dirname(d),exist_ok=True); os.replace(os.path.join(h,n),d)\n   PY\"\"\")\n   ```\n   Then verify `stat -c%s ~\u002F_schrod_src\u002F2026-2_Schrodinger_Linux.zip` == local size.\n2. `.\u002FINSTALL -b -s $SCHRODINGER -k \u002Ftmp \u003C8 products>` (mmshare, desmond, scisol,\n   ffld, glide, epik, jaguar, psp). License → `install -m 600 26-2.lic $SCHRODINGER\u002Flicenses\u002F`.\n3. License x509 on Linux: the perpetual local-entitlement lic x509-fails on Linux\n   (\"error code 20\"). Do NOT apply the verifier BYPASS (permanently declined).\n   If it fails, use AToM-OpenMM (license-free) or run FEP on the local Windows\n   Schrödinger MCP prep + a different physics path.\n4. `s.switch_machine(Machine.A100)`; run `fep_plus … -RESTART` detached; the\n   run mirrors progress + auto-resumes (see `lightning-a2d-fep\u002Fschrodinger\u002Frun_fep.sh`).\n   Poll with `s.run(\"tail ~\u002Ffep.log\")`; collect when done.\n\n## Worked context (2026-07-04)\n\nAccounts seen: `prekzursil1993` (a0967440) — teamspace quantum-paradox-…, studio\nexperimental-environment-hosting-devbox WITH Schrödinger installed; `prekzursil`\n(f09cac56) org `prekzursiltm`, teamspace quantum-paradox-… (empty, separate);\nbrowser org `prekzursil-org` studio `pipeline-devbox`. Lesson: verify WHICH\naccount a studio lives in before assuming the key can reach it.\n","# lightning-studio-driver\n\nDrive Lightning.ai Studios programmatically via `lightning_sdk` (installed at\n`C:\\Python314`). The `lightning` CLI is BROKEN on Windows (imports\n`simple_term_menu`→`termios`) — always use the SDK, never the CLI.\n\n## Credentials — the hard boundary\n\n- Auth = two env vars: `LIGHTNING_USER_ID` (non-secret UUID) + `LIGHTNING_API_KEY` (secret).\n- **The assistant NEVER types\u002Fwrites the API KEY** into any field, env var, or\n  config. Only READ it from the registry:\n  `[Environment]::GetEnvironmentVariable('LIGHTNING_API_KEY','User')`. The USER\n  sets the key. The assistant MAY set the non-secret `LIGHTNING_USER_ID` itself.\n- **setx pitfall (bites every time):** `setx VAR=value` (with `=`) SILENTLY\n  FAILS to update on Windows. Must be `setx VAR value` (SPACE). Verify after:\n  `[Environment]::GetEnvironmentVariable('VAR','User')`.\n- Keys pasted in chat are compromised → tell the user to ROTATE, then re-set.\n- In-process for a run: `$env:LIGHTNING_USER_ID = [Environment]::GetEnvironmentVariable('LIGHTNING_USER_ID','User')` (same for key), then run python.\n\n## Auth + WHO AM I\n\n```python\nfrom lightning_sdk.lightning_cloud.login import Auth\nfrom lightning_sdk.api.user_api import UserApi\na = Auth(); a.authenticate()\nuid = a.user_id\nuname = getattr(UserApi()._get_user_by_id(user_id=uid), \"username\", None)\n```\n`Auth()` resolves the account from `LIGHTNING_USER_ID` (it overrides — mismatched\nuser_id + key lands on the user_id's account). Confirm `uid`\u002F`uname` match the\naccount you expect BEFORE acting.\n\n## ★ Org-owned teamspaces — the discovery gap that wastes hours\n\n`User(name=uname).teamspaces` ONLY lists PERSONAL teamspaces. Studios created in\nan **organization** (the normal case when the web UI shows \"X Org\" \u002F URL\n`\u002F\u003Corg-slug>\u002F...`) are INVISIBLE to it → you'll see `teamspaces=0, studios=0`\nand wrongly conclude the account is empty. Enumerate via the org instead:\n\n```python\nfrom lightning_sdk.lightning_cloud.rest_client import LightningClient\nc = LightningClient()\norgs = c.organizations_service_list_organizations().organizations   # id, name, display_name\nmem  = c.projects_service_list_memberships().memberships             # teamspace name + project_id\n```\nThe org **`name`** (e.g. `prekzursiltm`) is what the SDK needs — NOT the URL\nslug (`prekzursil-org`) nor the display name (`PrekzursilTM`), which both fail.\nThen connect the teamspace and its studios:\n\n```python\nfrom lightning_sdk import Teamspace, Studio\nts = Teamspace(name=\"\u003Cteamspace-name>\", org=\"\u003Corg-name>\")   # e.g. quantum-paradox-exploration-project\nfor s in ts.studios: print(s.name, s.status, getattr(s,'machine','?'))\n```\nTwo accounts can have teamspaces with the SAME NAME but different `project_id` —\nthey are NOT shared; a studio in one is not in the other.\n\n## Studio lifecycle\n\n```python\nfrom lightning_sdk import Studio, Teamspace, Machine\nts = Teamspace(name=..., org=...)\ns = Studio(name=\"phenibut-fep\", teamspace=ts, create_ok=True)   # create or reuse\ns.start(Machine.CPU)          # cheap; use for install\u002Fupload\ns.switch_machine(Machine.A100)  # only for the GPU job\ns.run(\"bash -lc 'echo hi'\")   # exec a shell command, returns stdout\ns.upload_file(local, remote)  # or s.upload_folder(...)\ns.stop()                      # full stop (zero cost)\n```\n- `Machine` enum: `CPU, T4, L4, A100, A100_80GB, L40S, H100, …`. Availability is\n  cluster-dependent — `switch_machine(L40S)` may 404 \"accelerator not found\";\n  fall back A100→L4→T4. Studio filesystem persists across switch\u002Fstop\u002Fsleep.\n- **★ CHECK GPU AVAILABILITY + BALANCE BEFORE a big install.** A teamspace on\n  an AWS cluster may have **NO A100 at all** (\"accelerator lit-a100-1 not found\n  for this AWS cluster\") — only the machines its cluster offers work. AND\n  starting ANY GPU needs sufficient BALANCE (\"Insufficient balance to start the\n  cloud space, top up\") — ~11 credits was NOT enough for even L4\u002FT4. A studio\n  can install Schrödinger fine on CPU yet be UNABLE to run the GPU job. So:\n  before uploading 14 GB, probe `switch_machine(A100)` (or list cluster\n  machines) + confirm balance. If the FEP MUST run on A100, use an account whose\n  cluster HAS A100 and has balance (e.g. the one that ran it before) — don't\n  reinstall on a fresh account until GPU+balance are confirmed there.\n- **NEVER launch the GPU job if the machine is still CPU** — check\n  `nvidia-smi` returns a real GPU first; a failed `switch_machine` leaves you on\n  CPU and FEP+ on CPU is useless (weeks). Gate the launch on `GPU!=''`.\n- **Auto-sleep:** an idle Studio sleeps after ~10 min → status `sleeping`,\n  machine `-`, ZERO compute cost, filesystem intact. So an idle GPU stops\n  billing itself; you rarely need to force-stop to save credits.\n- Results\u002Flarge tool outputs paginate; `s.run` returns stdout as a string.\n\n## Free-tier reality (same failure modes as the Boltz free tier)\n\n- ~1 heavy job concurrent; free A100 ≈ a few hours + a ~4h session cap.\n- **Switching accounts ORPHANS in-flight work** (studio is account-scoped). Do\n  ONE thing → collect\u002Fconfirm → then switch. Never switch mid-run.\n- Fresh account has NO teamspace until web-UI onboarding (SDK can't bootstrap a\n  teamspace: `Studio(create_ok=True)` → \"Couldn't resolve teamspace\"). Once ANY\n  teamspace exists (org or personal), SDK create works.\n\n## cloud-hub rotation (like Modal's md_account_*)\n\ncloud-hub exposes `lg_account_list\u002Fcurrent\u002Fswitch\u002Fcycle\u002Fadd`. To avoid the setx\ndance, register named profiles — but keep the SECRET as an env REF, not a\nliteral, to honor the boundary:\n```\nlg_account_add(name=\"home\", env={\"LIGHTNING_USER_ID\":\"f09cac56-...\", \"LIGHTNING_API_KEY\":\"${LIGHTNING_API_KEY}\"})\n```\nFor multi-account rotation with distinct keys, give each account its own env var\n(`LIGHTNING_API_KEY_HOME`, …) that the user sets once, and reference it. Then\n`lg_account_switch \u003Cname>` swaps creds + respawns the backend — no setx per use.\n\n## Installing Schrödinger + running FEP (the heavy path)\n\nMirrors the Modal install (`compute\u002Fmodal_scripts\u002Fschrodinger_modal.py`) and the\n`lightning-a2d-fep` scaffold (`D:\u002FResearch\u002F_infra\u002Flightning-a2d-fep`):\n1. `s.start(Machine.CPU)`; upload `2026-2_Schrodinger_Linux.zip` (~14.4 GB) +\n   `26-2.lic` into `~\u002F_schrod_src\u002F`. **★ Upload backslash trap (bites every\n   time):** `Studio.upload_file(local, \"dir\u002Fsub\u002Ffile\")` NORMALIZES the remote\n   path to Windows `\\` ON THE CLIENT → the file lands as a FLAT file literally\n   named `dir\\sub\\file` (backslash is a valid Linux filename char), NOT inside\n   `dir\u002F`. Progress bar hits 100% and reports success, but `ls ~\u002Fdir` is empty.\n   The 14 GB is NOT lost — DON'T re-upload. Rename in place on the studio:\n   ```python\n   s.run(r\"\"\"python3 - \u003C\u003C'PY'\n   import os; h=os.path.expanduser(\"~\")\n   for n in list(os.listdir(h)):\n       if \"\\\\\" in n:\n           d=os.path.join(h,n.replace(\"\\\\\",\"\u002F\")); os.makedirs(os.path.dirname(d),exist_ok=True); os.replace(os.path.join(h,n),d)\n   PY\"\"\")\n   ```\n   Then verify `stat -c%s ~\u002F_schrod_src\u002F2026-2_Schrodinger_Linux.zip` == local size.\n2. `.\u002FINSTALL -b -s $SCHRODINGER -k \u002Ftmp \u003C8 products>` (mmshare, desmond, scisol,\n   ffld, glide, epik, jaguar, psp). License → `install -m 600 26-2.lic $SCHRODINGER\u002Flicenses\u002F`.\n3. License x509 on Linux: the perpetual local-entitlement lic x509-fails on Linux\n   (\"error code 20\"). Do NOT apply the verifier BYPASS (permanently declined).\n   If it fails, use AToM-OpenMM (license-free) or run FEP on the local Windows\n   Schrödinger MCP prep + a different physics path.\n4. `s.switch_machine(Machine.A100)`; run `fep_plus … -RESTART` detached; the\n   run mirrors progress + auto-resumes (see `lightning-a2d-fep\u002Fschrodinger\u002Frun_fep.sh`).\n   Poll with `s.run(\"tail ~\u002Ffep.log\")`; collect when done.\n\n## Worked context (2026-07-04)\n\nAccounts seen: `prekzursil1993` (a0967440) — teamspace quantum-paradox-…, studio\nexperimental-environment-hosting-devbox WITH Schrödinger installed; `prekzursil`\n(f09cac56) org `prekzursiltm`, teamspace quantum-paradox-… (empty, separate);\nbrowser org `prekzursil-org` studio `pipeline-devbox`. Lesson: verify WHICH\naccount a studio lives in before assuming the key can reach it.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Flightning-studio-driver","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill lightning-studio-driver",{"tool":53,"command":54},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill lightning-studio-driver",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill lightning-studio-driver","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Flightning-studio-driver\u002FSKILL.md",true,[61,67,71,75,79,83,87,91,95,99,103,107,111,115,119,123,127],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"steps\u002Fstep-01-init.md","REFERENCE","参考文档",5784,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-01-init.md",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"steps\u002Fstep-01b-continue.md",4867,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-01b-continue.md",{"path":72,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":73,"sourceHtmlUrl":74},"steps\u002Fstep-02-discovery.md",6671,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-02-discovery.md",{"path":76,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":77,"sourceHtmlUrl":78},"steps\u002Fstep-03-core-experience.md",8205,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-03-core-experience.md",{"path":80,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":81,"sourceHtmlUrl":82},"steps\u002Fstep-04-emotional-response.md",8265,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-04-emotional-response.md",{"path":84,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":85,"sourceHtmlUrl":86},"steps\u002Fstep-05-inspiration.md",8612,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-05-inspiration.md",{"path":88,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":89,"sourceHtmlUrl":90},"steps\u002Fstep-06-design-system.md",8801,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-06-design-system.md",{"path":92,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":93,"sourceHtmlUrl":94},"steps\u002Fstep-07-defining-experience.md",8750,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-07-defining-experience.md",{"path":96,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":97,"sourceHtmlUrl":98},"steps\u002Fstep-08-visual-foundation.md",8404,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-08-visual-foundation.md",{"path":100,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":101,"sourceHtmlUrl":102},"steps\u002Fstep-09-design-directions.md",8582,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-09-design-directions.md",{"path":104,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":105,"sourceHtmlUrl":106},"steps\u002Fstep-10-user-journeys.md",8349,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-10-user-journeys.md",{"path":108,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":109,"sourceHtmlUrl":110},"steps\u002Fstep-11-component-strategy.md",8694,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-11-component-strategy.md",{"path":112,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":113,"sourceHtmlUrl":114},"steps\u002Fstep-12-ux-patterns.md",7963,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-12-ux-patterns.md",{"path":116,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":117,"sourceHtmlUrl":118},"steps\u002Fstep-13-responsive-accessibility.md",9060,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-13-responsive-accessibility.md",{"path":120,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":121,"sourceHtmlUrl":122},"steps\u002Fstep-14-complete.md",6845,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fsteps\u002Fstep-14-complete.md",{"path":124,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":125,"sourceHtmlUrl":126},"ux-design-template.md",236,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fux-design-template.md",{"path":128,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":129,"sourceHtmlUrl":130},"workflow.md",1307,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fbmad-create-ux-design\u002Fworkflow.md",[132,153,183,210,224,239],{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":36},"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",[],[139,140,141,142,143,144,145,146,147,21,148,149,150,151,152],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"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":164,"publishedAt":36},"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",[159],{"categoryNo":160,"categoryName":161,"taxonomyType":162,"taxonomyTypeDesc":163},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[165,166,167,168,169,170,171,172,173,174,32,175,176,177,21,178,179,180,181,182],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":195,"publishedAt":36},"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",[189,192],{"categoryNo":190,"categoryName":191,"taxonomyType":162,"taxonomyTypeDesc":163},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":193,"categoryName":194,"taxonomyType":162,"taxonomyTypeDesc":163},"01JBSEEDCAT000000000000008","测试与质量",[196,197,198,199,200,201,202,203,204,205,166,206,207,208,209],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":216,"publishedAt":36},"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",[],[212,217,218,219,220,221,222,223],"setup","report","project","installation","project setup","issues","state",{"skillNo":225,"name":31,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":230,"publishedAt":36},"01M6DF6X6C2XB0P6GX76P7TTYV","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",[229],{"categoryNo":160,"categoryName":161,"taxonomyType":162,"taxonomyTypeDesc":163},[31,231,144,232,233,234,21,235,236,237,238],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":240,"name":217,"nameZh":6,"description":241,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":242,"categories":243,"keywords":244,"publishedAt":36},"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",[],[217,219,180,245,221,246],"files","interactive"]