[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794FPBFPWENZFZP82VK9E05":3,"skill-same:01M794FPBFPWENZFZP82VK9E05":70},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M794FPBFPWENZFZP82VK9E05","sdk-clients",null,"Use RocketRide Python and TypeScript\u002FNode SDKs and CLI safely for auth, task tokens, data transfer, events, file store, and API troubleshooting.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fsdk-clients\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sdk-clients\ndescription: \"Use RocketRide Python and TypeScript\u002FNode SDKs and CLI safely for\n  auth, task tokens, data transfer, events, file store, and API\n  troubleshooting.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# SDK Clients\n\nUse this sub-skill when a task is about calling RocketRide from Python,\nTypeScript\u002FNode, or the `rocketride` CLI: connecting, authenticating, starting a\npipeline, using the returned task token, sending data\u002Ffiles, streaming through a\npipe, subscribing to events, reading status, using the account file store, or\nchecking that the SDK imports cleanly.\n\n## Use this for\n\n- Python `RocketRideClient` scripts and async usage\n- TypeScript\u002FNode `RocketRideClient` scripts, browser\u002Fclient usage, and `DataPipe`\n- CLI command selection and Python-vs-TypeScript CLI flag differences\n- URI\u002Fauth environment handling, especially `ROCKETRIDE_URI`, `ROCKETRIDE_APIKEY`,\n  `ROCKETRIDE_AUTH`, `ROCKETRIDE_PIPELINE`, and `ROCKETRIDE_TOKEN`\n- Task token lifecycle: `use()`\u002F`start` -> data operations\u002Fstatus -> `terminate()`\u002F`stop`\n- Upload progress and server event callbacks\n- Account file-store methods (`fs_*` \u002F `fs*`) and direct URLs\n- Safe import\u002Fsignature smoke checks without starting services or connecting\n\n## Do not use this for\n\n- Designing `.pipe` JSON shape, lanes, sources, and recipes -> `..\u002Fpipeline-authoring\u002F`\n- Starting engines, Docker, Helm, Cloud\u002Fself-hosting operations, or DAP protocol depth -> `..\u002Fruntime-deployment\u002F`\n- Node provider\u002Fservice schemas and generated node documentation -> `..\u002Fnodes-catalog\u002F`\n- MCP server or n8n integration workflows -> `..\u002Fmcp-and-integrations\u002F`\n- IDE\u002FVS Code extension behavior -> `..\u002Fide-and-apps\u002F`\n\n## First decisions\n\n1. Identify the client surface: Python SDK, TypeScript\u002FNode SDK, browser SDK,\n   or CLI. The method names and file-upload shapes differ.\n2. Identify endpoint class: local\u002Fself-hosted (`ws:\u002F\u002F...` or `http:\u002F\u002F...`) versus\n   Cloud (`https:\u002F\u002F...` or `wss:\u002F\u002F...`). For any Cloud host, never use `http:\u002F\u002F`,\n   `ws:\u002F\u002F`, or a bare hostname because normalization can produce an unencrypted\n   `ws:\u002F\u002F` connection.\n3. Identify authentication source. Python\u002FTypeScript SDKs and CLIs read\n   `ROCKETRIDE_APIKEY`; MCP and some Cloud docs also use `ROCKETRIDE_AUTH`.\n   For SDK\u002FCLI tasks, set or pass `ROCKETRIDE_APIKEY` unless the code explicitly\n   copies `ROCKETRIDE_AUTH` into the client auth value.\n4. Identify whether a task token already exists. If not, start with `use()` or\n   `rocketride start` and capture the returned token before `send`, `pipe`,\n   `chat`, `status`, `stop`, or file-store task-scoped operations.\n\n## Reference map\n\n- [Python SDK API](references\u002Fpython-sdk-api.md) — inspected Python signatures,\n  async usage, token lifecycle, file store, events, and common pitfalls.\n- [TypeScript SDK API](references\u002Ftypescript-sdk-api.md) — `RocketRideClient`,\n  `DataPipe`, browser\u002FNode differences, env handling, namespaces, and examples.\n- [CLI reference](references\u002Fcli-reference.md) — command matrix, Python vs\n  TypeScript CLI flags, environment variables, and token use.\n- [Troubleshooting](references\u002Ftroubleshooting.md) — auth\u002FURI mistakes, token\n  errors, upload\u002FSSE issues, CLI path conflicts, file-store path rules, and safe\n  import checks.\n\n## Safe smoke check\n\nAfter installing the Python SDK in the environment that will run client code,\nrun the bundled import\u002Fsignature check. It performs no network connection:\n\n```bash\npython scripts\u002Fsdk_import_smoke.py\n```\n\nUse `--json` when another tool needs structured output.\n\n## Good output for SDK\u002FCLI tasks\n\n- Names the SDK\u002FCLI surface and uses its exact method\u002Fflag names\n- Uses secure Cloud URI schemes and avoids logging API keys\n- Starts or reuses a task token before data operations\n- Chooses `send` for one-shot payloads, `send_files`\u002F`sendFiles` for files, and\n  `pipe`\u002F`DataPipe` for chunked or SSE-scoped streaming\n- Terminates tasks when done unless the workflow is intentionally long-lived\n- Keeps `.pipe` schema design and engine deployment details routed to the sibling\n  sub-skills instead of expanding them here\n","# SDK Clients\n\nUse this sub-skill when a task is about calling RocketRide from Python,\nTypeScript\u002FNode, or the `rocketride` CLI: connecting, authenticating, starting a\npipeline, using the returned task token, sending data\u002Ffiles, streaming through a\npipe, subscribing to events, reading status, using the account file store, or\nchecking that the SDK imports cleanly.\n\n## Use this for\n\n- Python `RocketRideClient` scripts and async usage\n- TypeScript\u002FNode `RocketRideClient` scripts, browser\u002Fclient usage, and `DataPipe`\n- CLI command selection and Python-vs-TypeScript CLI flag differences\n- URI\u002Fauth environment handling, especially `ROCKETRIDE_URI`, `ROCKETRIDE_APIKEY`,\n  `ROCKETRIDE_AUTH`, `ROCKETRIDE_PIPELINE`, and `ROCKETRIDE_TOKEN`\n- Task token lifecycle: `use()`\u002F`start` -> data operations\u002Fstatus -> `terminate()`\u002F`stop`\n- Upload progress and server event callbacks\n- Account file-store methods (`fs_*` \u002F `fs*`) and direct URLs\n- Safe import\u002Fsignature smoke checks without starting services or connecting\n\n## Do not use this for\n\n- Designing `.pipe` JSON shape, lanes, sources, and recipes -> `..\u002Fpipeline-authoring\u002F`\n- Starting engines, Docker, Helm, Cloud\u002Fself-hosting operations, or DAP protocol depth -> `..\u002Fruntime-deployment\u002F`\n- Node provider\u002Fservice schemas and generated node documentation -> `..\u002Fnodes-catalog\u002F`\n- MCP server or n8n integration workflows -> `..\u002Fmcp-and-integrations\u002F`\n- IDE\u002FVS Code extension behavior -> `..\u002Fide-and-apps\u002F`\n\n## First decisions\n\n1. Identify the client surface: Python SDK, TypeScript\u002FNode SDK, browser SDK,\n   or CLI. The method names and file-upload shapes differ.\n2. Identify endpoint class: local\u002Fself-hosted (`ws:\u002F\u002F...` or `http:\u002F\u002F...`) versus\n   Cloud (`https:\u002F\u002F...` or `wss:\u002F\u002F...`). For any Cloud host, never use `http:\u002F\u002F`,\n   `ws:\u002F\u002F`, or a bare hostname because normalization can produce an unencrypted\n   `ws:\u002F\u002F` connection.\n3. Identify authentication source. Python\u002FTypeScript SDKs and CLIs read\n   `ROCKETRIDE_APIKEY`; MCP and some Cloud docs also use `ROCKETRIDE_AUTH`.\n   For SDK\u002FCLI tasks, set or pass `ROCKETRIDE_APIKEY` unless the code explicitly\n   copies `ROCKETRIDE_AUTH` into the client auth value.\n4. Identify whether a task token already exists. If not, start with `use()` or\n   `rocketride start` and capture the returned token before `send`, `pipe`,\n   `chat`, `status`, `stop`, or file-store task-scoped operations.\n\n## Reference map\n\n- [Python SDK API](references\u002Fpython-sdk-api.md) — inspected Python signatures,\n  async usage, token lifecycle, file store, events, and common pitfalls.\n- [TypeScript SDK API](references\u002Ftypescript-sdk-api.md) — `RocketRideClient`,\n  `DataPipe`, browser\u002FNode differences, env handling, namespaces, and examples.\n- [CLI reference](references\u002Fcli-reference.md) — command matrix, Python vs\n  TypeScript CLI flags, environment variables, and token use.\n- [Troubleshooting](references\u002Ftroubleshooting.md) — auth\u002FURI mistakes, token\n  errors, upload\u002FSSE issues, CLI path conflicts, file-store path rules, and safe\n  import checks.\n\n## Safe smoke check\n\nAfter installing the Python SDK in the environment that will run client code,\nrun the bundled import\u002Fsignature check. It performs no network connection:\n\n```bash\npython scripts\u002Fsdk_import_smoke.py\n```\n\nUse `--json` when another tool needs structured output.\n\n## Good output for SDK\u002FCLI tasks\n\n- Names the SDK\u002FCLI surface and uses its exact method\u002Fflag names\n- Uses secure Cloud URI schemes and avoids logging API keys\n- Starts or reuses a task token before data operations\n- Chooses `send` for one-shot payloads, `send_files`\u002F`sendFiles` for files, and\n  `pipe`\u002F`DataPipe` for chunked or SSE-scoped streaming\n- Terminates tasks when done unless the workflow is intentionally long-lived\n- Keeps `.pipe` schema design and engine deployment details routed to the sibling\n  sub-skills instead of expanding them here\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fsdk-clients",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill sdk-clients",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill sdk-clients",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill sdk-clients","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fsdk-clients\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcli-reference.md","REFERENCE","参考文档",6580,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fsdk-clients\u002Freferences\u002Fcli-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fpython-sdk-api.md",11710,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fsdk-clients\u002Freferences\u002Fpython-sdk-api.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",9166,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fsdk-clients\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftypescript-sdk-api.md",14156,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fsdk-clients\u002Freferences\u002Ftypescript-sdk-api.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fsdk_import_smoke.py","SCRIPT","脚本",5376,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frocketride-server\u002Fsub-skills\u002Fsdk-clients\u002Fscripts\u002Fsdk_import_smoke.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"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":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]