[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZYDYTNPVHGCFQJCFPR76M":3,"skill-same:01M78ZYDYTNPVHGCFQJCFPR76M":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},"01M78ZYDYTNPVHGCFQJCFPR76M","durable-execution",null,"Convert mcp-agent workflows into durable Temporal-backed workers with pause\u002Fresume, signals, retries, activity registration, and operational guardrails.","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\u002Fmcp-agent\u002Fsub-skills\u002Fdurable-execution\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: durable-execution\ndescription: \"Convert mcp-agent workflows into durable Temporal-backed workers\n  with pause\u002Fresume, signals, retries, activity registration, and operational\n  guardrails.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# durable-execution\n\nUse this sub-skill when an mcp-agent app must run workflows durably with the Temporal executor: production workers, long-running tools, pause\u002Fresume, human approval signals, activity\u002Ftask retries, task registration, workflow handles, and Temporal service constraints.\n\n## Route First\n\n- Use `..\u002Fworkflow-patterns\u002FSKILL.md` first when the task is choosing between router, orchestrator, parallel, evaluator, swarm, or other workflow shapes.\n- Use `..\u002Fcore-sdk\u002FSKILL.md` first when the task is basic `MCPApp`, `Agent`, provider, secrets, or local asyncio setup.\n- Use `..\u002Fcli-cloud-operations\u002FSKILL.md` when the user specifically asks for hosted cloud deployment or cloud workflow CLI commands.\n- Stay here when the workflow shape already exists and the work is making it durable, observable, retry-safe, signalable, or worker-backed.\n\n## Durable Conversion Checklist\n\n1. Confirm the Temporal extra is available before importing Temporal-specific modules: install with `mcp-agent[temporal]`, which brings in `temporalio[opentelemetry]`.\n2. Set `execution_engine: temporal` and configure `temporal.host`, `temporal.namespace`, and `temporal.task_queue`; in current settings, `host` includes the port such as `localhost:7233`.\n3. Keep the same `@app.workflow`, `@app.workflow_run`, `@app.workflow_task`, `@app.async_tool`, and `Agent` APIs where possible. The decorators adapt to asyncio or Temporal based on configuration.\n4. Create a worker process that imports the app and any modules that register workflows\u002Ftasks, then runs `create_temporal_worker_for_app(app)`.\n5. Put custom reusable activities in importable modules and list them under `workflow_task_modules` when they are registered with the static `workflow_task` decorator or otherwise need preloading.\n6. Configure task retry behavior with local `@app.workflow_task(retry_policy=...)` metadata or top-level `workflow_task_retry_policies` for exact, suffix, prefix wildcard, and `*` matching.\n7. Design pause\u002Fresume with `executor.wait_for_signal(...)` inside the workflow and `executor.signal(...)`, workflow registry resume, or MCP server resume tools outside it.\n8. Keep workflow code deterministic. Move external API calls, file I\u002FO, MCP tool calls, database writes, and provider calls into workflow tasks\u002Factivities or existing mcp-agent abstractions.\n9. Validate static config with `scripts\u002Fcheck_temporal_config.py`; generate a safe starter worker\u002Fapp skeleton with `scripts\u002Fworker_skeleton.py`.\n\n## Reference Map\n\n- Temporal worker and activity design: `references\u002Ftemporal-workflows.md`\n- Pause\u002Fresume, signals, and human approvals: `references\u002Fpause-resume-and-signals.md`\n- Operational troubleshooting: `references\u002Ftroubleshooting.md`\n- Static config validator: `scripts\u002Fcheck_temporal_config.py`\n- Worker\u002Fapp skeleton generator: `scripts\u002Fworker_skeleton.py`\n\n## Safety Notes\n\n- A Temporal worker is a long-running service process. The bundled scripts do not start a Temporal worker, connect to a cluster, or call providers unless the user edits and runs the generated application code.\n- Temporal is optional. Base mcp-agent installs may import core SDK APIs but fail on `mcp_agent.executor.temporal` until the Temporal extra is installed.\n- Temporal server examples are skip-service unless the user already has a local or remote Temporal cluster and explicitly wants to run them.\n- Do not put secrets in config examples. Use environment placeholders, secrets files, or a deployment secret manager.\n","# durable-execution\n\nUse this sub-skill when an mcp-agent app must run workflows durably with the Temporal executor: production workers, long-running tools, pause\u002Fresume, human approval signals, activity\u002Ftask retries, task registration, workflow handles, and Temporal service constraints.\n\n## Route First\n\n- Use `..\u002Fworkflow-patterns\u002FSKILL.md` first when the task is choosing between router, orchestrator, parallel, evaluator, swarm, or other workflow shapes.\n- Use `..\u002Fcore-sdk\u002FSKILL.md` first when the task is basic `MCPApp`, `Agent`, provider, secrets, or local asyncio setup.\n- Use `..\u002Fcli-cloud-operations\u002FSKILL.md` when the user specifically asks for hosted cloud deployment or cloud workflow CLI commands.\n- Stay here when the workflow shape already exists and the work is making it durable, observable, retry-safe, signalable, or worker-backed.\n\n## Durable Conversion Checklist\n\n1. Confirm the Temporal extra is available before importing Temporal-specific modules: install with `mcp-agent[temporal]`, which brings in `temporalio[opentelemetry]`.\n2. Set `execution_engine: temporal` and configure `temporal.host`, `temporal.namespace`, and `temporal.task_queue`; in current settings, `host` includes the port such as `localhost:7233`.\n3. Keep the same `@app.workflow`, `@app.workflow_run`, `@app.workflow_task`, `@app.async_tool`, and `Agent` APIs where possible. The decorators adapt to asyncio or Temporal based on configuration.\n4. Create a worker process that imports the app and any modules that register workflows\u002Ftasks, then runs `create_temporal_worker_for_app(app)`.\n5. Put custom reusable activities in importable modules and list them under `workflow_task_modules` when they are registered with the static `workflow_task` decorator or otherwise need preloading.\n6. Configure task retry behavior with local `@app.workflow_task(retry_policy=...)` metadata or top-level `workflow_task_retry_policies` for exact, suffix, prefix wildcard, and `*` matching.\n7. Design pause\u002Fresume with `executor.wait_for_signal(...)` inside the workflow and `executor.signal(...)`, workflow registry resume, or MCP server resume tools outside it.\n8. Keep workflow code deterministic. Move external API calls, file I\u002FO, MCP tool calls, database writes, and provider calls into workflow tasks\u002Factivities or existing mcp-agent abstractions.\n9. Validate static config with `scripts\u002Fcheck_temporal_config.py`; generate a safe starter worker\u002Fapp skeleton with `scripts\u002Fworker_skeleton.py`.\n\n## Reference Map\n\n- Temporal worker and activity design: `references\u002Ftemporal-workflows.md`\n- Pause\u002Fresume, signals, and human approvals: `references\u002Fpause-resume-and-signals.md`\n- Operational troubleshooting: `references\u002Ftroubleshooting.md`\n- Static config validator: `scripts\u002Fcheck_temporal_config.py`\n- Worker\u002Fapp skeleton generator: `scripts\u002Fworker_skeleton.py`\n\n## Safety Notes\n\n- A Temporal worker is a long-running service process. The bundled scripts do not start a Temporal worker, connect to a cluster, or call providers unless the user edits and runs the generated application code.\n- Temporal is optional. Base mcp-agent installs may import core SDK APIs but fail on `mcp_agent.executor.temporal` until the Temporal extra is installed.\n- Temporal server examples are skip-service unless the user already has a local or remote Temporal cluster and explicitly wants to run them.\n- Do not put secrets in config examples. Use environment placeholders, secrets files, or a deployment secret manager.\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\u002Fmcp-agent\u002Fsub-skills\u002Fdurable-execution",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 durable-execution",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill durable-execution",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill durable-execution","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent\u002Fsub-skills\u002Fdurable-execution\u002FSKILL.md",[47,53,57,61,67],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fpause-resume-and-signals.md","REFERENCE","参考文档",7984,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent\u002Fsub-skills\u002Fdurable-execution\u002Freferences\u002Fpause-resume-and-signals.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftemporal-workflows.md",9711,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent\u002Fsub-skills\u002Fdurable-execution\u002Freferences\u002Ftemporal-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",8051,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent\u002Fsub-skills\u002Fdurable-execution\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_temporal_config.py","SCRIPT","脚本",18163,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent\u002Fsub-skills\u002Fdurable-execution\u002Fscripts\u002Fcheck_temporal_config.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fworker_skeleton.py",8998,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmcp-agent\u002Fsub-skills\u002Fdurable-execution\u002Fscripts\u002Fworker_skeleton.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",[],[]]