[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795YRKCS2ST1E2004DF37A2":3,"skill-same:01M795YRKCS2ST1E2004DF37A2":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},"01M795YRKCS2ST1E2004DF37A2","plugin-bundles",null,"Work with the TaskingAI plugin microservice bundle catalog, plugin schemas, execution, credential validation, image storage, and plugin-specific 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\u002Fplugin-bundles\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: plugin-bundles\ndescription: \"Work with the TaskingAI plugin microservice bundle catalog, plugin\n  schemas, execution, credential validation, image storage, and plugin-specific\n  troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# TaskingAI Plugin Bundles\n\nUse this sub-skill when the task is about TaskingAI's plugin microservice: built-in bundle\u002Fplugin discovery, plugin input\u002Foutput schema selection, plugin execution payloads, credential validation, generated image storage, or plugin-specific troubleshooting.\n\n## Load this first\n\n1. For catalog selection, schema shape, and no-credential bundle choices, read [references\u002Fbundle-catalog.md](references\u002Fbundle-catalog.md).\n2. For HTTP route contracts, request\u002Fresponse bodies, credential validation, and execution flow, read [references\u002Fapi-reference.md](references\u002Fapi-reference.md).\n3. For source-backed native-test behavior and safe skip criteria, read [references\u002Fnative-testing.md](references\u002Fnative-testing.md).\n4. For failure diagnosis, especially local image URL versus S3 storage problems, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n5. To inspect a local TaskingAI checkout without network calls or credentials, use [scripts\u002Finspect_plugin_bundles.py](scripts\u002Finspect_plugin_bundles.py).\n\n## Source-backed facts to preserve\n\n- The plugin microservice exposes 47 built-in bundles and 86 plugins in the verified catalog snapshot.\n- Static import checks passed in Python 3.10 for `APIRouter`, `Bundle`, `Plugin`, `Arithmetic`, and `ChartMaker`.\n- Catalog metadata is defined by bundle schemas and plugin schemas, then loaded into in-memory caches at service startup.\n- Plugin execution validates bundle credentials before plugin lookup\u002Finput validation, then calls the dynamically loaded bundle\u002Fplugin handler class.\n- Generated-image plugins use either local storage or S3-compatible storage based on object-storage configuration.\n\n## Quick routing\n\n- Need a safe synthetic no-credential tool? Prefer `arithmetic\u002Fadd` or `arithmetic\u002Fdivide` for precise numeric behavior. Use `chart_maker\u002F*` or `qr_code_generator\u002Fgenerate_qr_code` only when image storage and `project_id` are intentionally in scope.\n- Need to send a backend-created tool instance\u002Faction through TaskingAI's backend object lifecycle? Route that task to `..\u002Fbackend-api\u002F` and return here only for plugin bundle\u002Fschema payload details.\n- Need inference-provider model invocation or provider credentials unrelated to plugin bundles? Route to `..\u002Finference-providers\u002F`.\n- Need deployment environment basics, container startup, or cross-service env wiring? Route to `..\u002Fdeployment-configuration\u002F`; return here for plugin-specific storage and credential variables.\n\n## Operating workflow\n\n1. **Identify the bundle and plugin.** Use the no-credential and credentialed catalogs in [references\u002Fbundle-catalog.md](references\u002Fbundle-catalog.md). Confirm whether provider credentials, network access, `project_id`, or image storage are required.\n2. **Validate schema before execution.** Compare the task payload to the plugin input schema types: `string`, `integer`, `number`, `boolean`, `string_array`, `integer_array`, `number_array`, `boolean_array`, `image_url`, or `file_url`. Required inputs must be present; URL types must start with `http`.\n3. **Choose the credential path.** For no-credential bundles, pass `{}` as credentials. For credentialed bundles, pass either plaintext `credentials` or encrypted credentials, never both. Use the verification endpoint if credentials must be encrypted for later reuse.\n4. **Execute through the plugin service contract.** POST to `\u002Fv1\u002Fexecute` with `bundle_id`, `plugin_id`, `input_params`, `credentials`, and optional `project_id`. Expect `status: success` plus `data.status` and `data.data` on normal execution.\n5. **Handle storage outputs.** If the plugin returns `url` or `image_url`, check whether local or S3 storage is configured and diagnose with [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) before blaming the provider.\n\n## Hard usability cases covered here\n\n- Select a no-credential built-in bundle for a synthetic tool workflow and explain exact expected input\u002Foutput schema: use `arithmetic\u002Fadd` with numeric `number_1`, `number_2` and numeric `result`, or use `arithmetic\u002Fdivide` and explicitly reject `number_2 = 0`.\n- Diagnose a generated chart or QR-code URL that works under local storage but fails under S3, or vice versa, by checking `OBJECT_STORAGE_TYPE`, local `HOST_URL`\u002F`PATH_TO_VOLUME`, S3 endpoint\u002Fbucket\u002Fpublic-domain variables, and whether the returned URL path includes the generated image category prefix.\n","# TaskingAI Plugin Bundles\n\nUse this sub-skill when the task is about TaskingAI's plugin microservice: built-in bundle\u002Fplugin discovery, plugin input\u002Foutput schema selection, plugin execution payloads, credential validation, generated image storage, or plugin-specific troubleshooting.\n\n## Load this first\n\n1. For catalog selection, schema shape, and no-credential bundle choices, read [references\u002Fbundle-catalog.md](references\u002Fbundle-catalog.md).\n2. For HTTP route contracts, request\u002Fresponse bodies, credential validation, and execution flow, read [references\u002Fapi-reference.md](references\u002Fapi-reference.md).\n3. For source-backed native-test behavior and safe skip criteria, read [references\u002Fnative-testing.md](references\u002Fnative-testing.md).\n4. For failure diagnosis, especially local image URL versus S3 storage problems, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n5. To inspect a local TaskingAI checkout without network calls or credentials, use [scripts\u002Finspect_plugin_bundles.py](scripts\u002Finspect_plugin_bundles.py).\n\n## Source-backed facts to preserve\n\n- The plugin microservice exposes 47 built-in bundles and 86 plugins in the verified catalog snapshot.\n- Static import checks passed in Python 3.10 for `APIRouter`, `Bundle`, `Plugin`, `Arithmetic`, and `ChartMaker`.\n- Catalog metadata is defined by bundle schemas and plugin schemas, then loaded into in-memory caches at service startup.\n- Plugin execution validates bundle credentials before plugin lookup\u002Finput validation, then calls the dynamically loaded bundle\u002Fplugin handler class.\n- Generated-image plugins use either local storage or S3-compatible storage based on object-storage configuration.\n\n## Quick routing\n\n- Need a safe synthetic no-credential tool? Prefer `arithmetic\u002Fadd` or `arithmetic\u002Fdivide` for precise numeric behavior. Use `chart_maker\u002F*` or `qr_code_generator\u002Fgenerate_qr_code` only when image storage and `project_id` are intentionally in scope.\n- Need to send a backend-created tool instance\u002Faction through TaskingAI's backend object lifecycle? Route that task to `..\u002Fbackend-api\u002F` and return here only for plugin bundle\u002Fschema payload details.\n- Need inference-provider model invocation or provider credentials unrelated to plugin bundles? Route to `..\u002Finference-providers\u002F`.\n- Need deployment environment basics, container startup, or cross-service env wiring? Route to `..\u002Fdeployment-configuration\u002F`; return here for plugin-specific storage and credential variables.\n\n## Operating workflow\n\n1. **Identify the bundle and plugin.** Use the no-credential and credentialed catalogs in [references\u002Fbundle-catalog.md](references\u002Fbundle-catalog.md). Confirm whether provider credentials, network access, `project_id`, or image storage are required.\n2. **Validate schema before execution.** Compare the task payload to the plugin input schema types: `string`, `integer`, `number`, `boolean`, `string_array`, `integer_array`, `number_array`, `boolean_array`, `image_url`, or `file_url`. Required inputs must be present; URL types must start with `http`.\n3. **Choose the credential path.** For no-credential bundles, pass `{}` as credentials. For credentialed bundles, pass either plaintext `credentials` or encrypted credentials, never both. Use the verification endpoint if credentials must be encrypted for later reuse.\n4. **Execute through the plugin service contract.** POST to `\u002Fv1\u002Fexecute` with `bundle_id`, `plugin_id`, `input_params`, `credentials`, and optional `project_id`. Expect `status: success` plus `data.status` and `data.data` on normal execution.\n5. **Handle storage outputs.** If the plugin returns `url` or `image_url`, check whether local or S3 storage is configured and diagnose with [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) before blaming the provider.\n\n## Hard usability cases covered here\n\n- Select a no-credential built-in bundle for a synthetic tool workflow and explain exact expected input\u002Foutput schema: use `arithmetic\u002Fadd` with numeric `number_1`, `number_2` and numeric `result`, or use `arithmetic\u002Fdivide` and explicitly reject `number_2 = 0`.\n- Diagnose a generated chart or QR-code URL that works under local storage but fails under S3, or vice versa, by checking `OBJECT_STORAGE_TYPE`, local `HOST_URL`\u002F`PATH_TO_VOLUME`, S3 endpoint\u002Fbucket\u002Fpublic-domain variables, and whether the returned URL path includes the generated image category prefix.\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\u002Fplugin-bundles",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 plugin-bundles",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill plugin-bundles",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill plugin-bundles","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Fplugin-bundles\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",9980,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Fplugin-bundles\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fbundle-catalog.md",10922,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Fplugin-bundles\u002Freferences\u002Fbundle-catalog.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fnative-testing.md",7623,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Fplugin-bundles\u002Freferences\u002Fnative-testing.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",11933,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Fplugin-bundles\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Finspect_plugin_bundles.py","SCRIPT","脚本",8271,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftaskingai\u002Fsub-skills\u002Fplugin-bundles\u002Fscripts\u002Finspect_plugin_bundles.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",[],[]]