[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795YP2JS5TJXN62AWM9RGTP":3,"skill-same:01M795YP2JS5TJXN62AWM9RGTP":71},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M795YP2JS5TJXN62AWM9RGTP","inference-providers",null,"Operate the TaskingAI inference microservice provider\u002Fmodel catalog, credential validation, chat completion, text embedding, rerank, provider icons, custom\u002Flocal providers, proxy safety, and provider troubleshooting.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Finference-providers\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inference-providers\ndescription: \"Operate the TaskingAI inference microservice provider\u002Fmodel\n  catalog, credential validation, chat completion, text embedding, rerank,\n  provider icons, custom\u002Flocal providers, proxy safety, and provider\n  troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# TaskingAI Inference Providers\n\nUse this sub-skill when a task is about TaskingAI's inference microservice: provider and model schema discovery, provider credentials, credential verification, chat completion, text embedding, rerank, provider icons, OpenAI-compatible\u002Fcustom hosts, local model providers, proxy\u002FURL blacklist behavior, or provider-specific failure diagnosis.\n\n## Load this first\n\n1. For provider\u002Fmodel selection, credential fields, wildcard schemas, local\u002Fcustom-host choices, and catalog counts, read [references\u002Fprovider-catalog.md](references\u002Fprovider-catalog.md).\n2. For HTTP route contracts, request\u002Fresponse bodies, validation order, streaming, fallbacks, proxy\u002Fcustom-header behavior, and icon routes, read [references\u002Fapi-reference.md](references\u002Fapi-reference.md).\n3. For source-backed native-test behavior, credential-sensitive checks, and safe skip criteria, read [references\u002Fnative-testing.md](references\u002Fnative-testing.md).\n4. For symptoms, likely causes, and recovery steps, especially `PROVIDER_ERROR` versus `REQUEST_VALIDATION_ERROR`, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n5. To inspect a user-supplied TaskingAI source tree without network calls or credentials, use [scripts\u002Finspect_inference_catalog.py](scripts\u002Finspect_inference_catalog.py).\n\n## Source-backed facts to preserve\n\n- The verified inference catalog snapshot contains 35 provider directories.\n- Model schema types are exactly `chat_completion`, `text_embedding`, `rerank`, and `wildcard`.\n- Provider and model metadata are loaded from bundled YAML resources into runtime caches before route handlers use them.\n- Static import probes passed in Python 3.10 for `APIRouter`, `Provider`, and `DebugChatCompletionModel`.\n- Credential verification can be schema-only at provider level or can call a default chat, embedding, or rerank model depending on provider metadata.\n\n## Quick routing\n\n- Backend object lifecycle, model-instance APIs exposed by the main backend, backend proxy endpoints, authentication, and database\u002FAPI object semantics belong to `..\u002Fbackend-api\u002F`.\n- Deployment variables, container startup, service URLs, image tags, port wiring, `TASKINGAI_INFERENCE_URL`, global outbound proxy setup, and storage configuration belong to `..\u002Fdeployment-configuration\u002F`.\n- Plugin tool bundles, plugin vision\u002Ftool schemas, plugin execution, and plugin image generation belong to `..\u002Fplugin-bundles\u002F`.\n- Stay here for provider catalog semantics, inference route payloads, credentials, `custom_host`, Ollama\u002FLM Studio\u002FLocalAI, provider icons, and provider-specific troubleshooting.\n\n## Operating workflow\n\n1. **Classify the requested model capability.** Use `chat_completion`, `text_embedding`, `rerank`, or `wildcard`; do not assume a wildcard schema has enough information without `provider_model_id`, `model_type`, and any required `properties`.\n2. **Choose the provider path.** Use [provider selection guidance](references\u002Fprovider-catalog.md#provider-selection-guidance) for hosted providers, hosted OpenAI-compatible routers, `custom_host`, and local OpenAI-compatible servers.\n3. **Validate credentials before invocation.** Compare the request to the provider `credentials_schema`; pass either plaintext `credentials` or `encrypted_credentials`, never both. Use [credential validation semantics](references\u002Fapi-reference.md#credential-validation-routes) when the user needs encrypted credentials for later reuse.\n4. **Build the inference payload.** Use [chat completion](references\u002Fapi-reference.md#post-v1chat_completion), [text embedding](references\u002Fapi-reference.md#post-v1text_embedding), or [rerank](references\u002Fapi-reference.md#post-v1rerank) contracts. Check model properties and configs before provider calls.\n5. **Handle proxy and URL safety deliberately.** Request-level `proxy` values must be HTTPS and are rejected if they contain a configured provider URL blacklist entry. `custom_host` endpoint URLs are checked against the same blacklist before a provider call.\n6. **Diagnose by error class.** Treat schema\u002Fmodel\u002Fproperty\u002Fproxy failures as request validation first. Treat upstream HTTP\u002FAPI\u002Fauth\u002Fquota failures as provider failures. Use [troubleshooting](references\u002Ftroubleshooting.md) before retrying with new credentials.\n\n## Hard usability cases covered here\n\n- Choose between `custom_host`, Ollama\u002FLM Studio\u002FLocalAI, OpenRouter, and a named hosted provider for an OpenAI-compatible user task while preserving the difference between actual provider model IDs and TaskingAI model schema IDs.\n- Diagnose `PROVIDER_ERROR` versus `REQUEST_VALIDATION_ERROR` during credential validation by separating local schema\u002Fmodel\u002Fproxy checks from upstream provider responses.\n","# TaskingAI Inference Providers\n\nUse this sub-skill when a task is about TaskingAI's inference microservice: provider and model schema discovery, provider credentials, credential verification, chat completion, text embedding, rerank, provider icons, OpenAI-compatible\u002Fcustom hosts, local model providers, proxy\u002FURL blacklist behavior, or provider-specific failure diagnosis.\n\n## Load this first\n\n1. For provider\u002Fmodel selection, credential fields, wildcard schemas, local\u002Fcustom-host choices, and catalog counts, read [references\u002Fprovider-catalog.md](references\u002Fprovider-catalog.md).\n2. For HTTP route contracts, request\u002Fresponse bodies, validation order, streaming, fallbacks, proxy\u002Fcustom-header behavior, and icon routes, read [references\u002Fapi-reference.md](references\u002Fapi-reference.md).\n3. For source-backed native-test behavior, credential-sensitive checks, and safe skip criteria, read [references\u002Fnative-testing.md](references\u002Fnative-testing.md).\n4. For symptoms, likely causes, and recovery steps, especially `PROVIDER_ERROR` versus `REQUEST_VALIDATION_ERROR`, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n5. To inspect a user-supplied TaskingAI source tree without network calls or credentials, use [scripts\u002Finspect_inference_catalog.py](scripts\u002Finspect_inference_catalog.py).\n\n## Source-backed facts to preserve\n\n- The verified inference catalog snapshot contains 35 provider directories.\n- Model schema types are exactly `chat_completion`, `text_embedding`, `rerank`, and `wildcard`.\n- Provider and model metadata are loaded from bundled YAML resources into runtime caches before route handlers use them.\n- Static import probes passed in Python 3.10 for `APIRouter`, `Provider`, and `DebugChatCompletionModel`.\n- Credential verification can be schema-only at provider level or can call a default chat, embedding, or rerank model depending on provider metadata.\n\n## Quick routing\n\n- Backend object lifecycle, model-instance APIs exposed by the main backend, backend proxy endpoints, authentication, and database\u002FAPI object semantics belong to `..\u002Fbackend-api\u002F`.\n- Deployment variables, container startup, service URLs, image tags, port wiring, `TASKINGAI_INFERENCE_URL`, global outbound proxy setup, and storage configuration belong to `..\u002Fdeployment-configuration\u002F`.\n- Plugin tool bundles, plugin vision\u002Ftool schemas, plugin execution, and plugin image generation belong to `..\u002Fplugin-bundles\u002F`.\n- Stay here for provider catalog semantics, inference route payloads, credentials, `custom_host`, Ollama\u002FLM Studio\u002FLocalAI, provider icons, and provider-specific troubleshooting.\n\n## Operating workflow\n\n1. **Classify the requested model capability.** Use `chat_completion`, `text_embedding`, `rerank`, or `wildcard`; do not assume a wildcard schema has enough information without `provider_model_id`, `model_type`, and any required `properties`.\n2. **Choose the provider path.** Use [provider selection guidance](references\u002Fprovider-catalog.md#provider-selection-guidance) for hosted providers, hosted OpenAI-compatible routers, `custom_host`, and local OpenAI-compatible servers.\n3. **Validate credentials before invocation.** Compare the request to the provider `credentials_schema`; pass either plaintext `credentials` or `encrypted_credentials`, never both. Use [credential validation semantics](references\u002Fapi-reference.md#credential-validation-routes) when the user needs encrypted credentials for later reuse.\n4. **Build the inference payload.** Use [chat completion](references\u002Fapi-reference.md#post-v1chat_completion), [text embedding](references\u002Fapi-reference.md#post-v1text_embedding), or [rerank](references\u002Fapi-reference.md#post-v1rerank) contracts. Check model properties and configs before provider calls.\n5. **Handle proxy and URL safety deliberately.** Request-level `proxy` values must be HTTPS and are rejected if they contain a configured provider URL blacklist entry. `custom_host` endpoint URLs are checked against the same blacklist before a provider call.\n6. **Diagnose by error class.** Treat schema\u002Fmodel\u002Fproperty\u002Fproxy failures as request validation first. Treat upstream HTTP\u002FAPI\u002Fauth\u002Fquota failures as provider failures. Use [troubleshooting](references\u002Ftroubleshooting.md) before retrying with new credentials.\n\n## Hard usability cases covered here\n\n- Choose between `custom_host`, Ollama\u002FLM Studio\u002FLocalAI, OpenRouter, and a named hosted provider for an OpenAI-compatible user task while preserving the difference between actual provider model IDs and TaskingAI model schema IDs.\n- Diagnose `PROVIDER_ERROR` versus `REQUEST_VALIDATION_ERROR` during credential validation by separating local schema\u002Fmodel\u002Fproxy checks from upstream provider responses.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Finference-providers",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-providers",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-providers",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-providers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Finference-providers\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",13266,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Finference-providers\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fnative-testing.md",7987,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Finference-providers\u002Freferences\u002Fnative-testing.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fprovider-catalog.md",12272,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Finference-providers\u002Freferences\u002Fprovider-catalog.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",11383,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Finference-providers\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Finspect_inference_catalog.py","SCRIPT","脚本",14788,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Finference-providers\u002Fscripts\u002Finspect_inference_catalog.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]