[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SXGWCVRBB2764FNB8P15Q":3,"skill-same:01M78SXGWCVRBB2764FNB8P15Q":67},{"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},"01M78SXGWCVRBB2764FNB8P15Q","execution-and-monitoring",null,"Select and operate local, SSH, or Slurm experiment execution with bounded, zero-LLM monitoring, safe paths, truthful terminal outcomes, and actionable recovery.","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\u002Fauto-deep-researcher-24x7\u002Fsub-skills\u002Fexecution-and-monitoring\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: execution-and-monitoring\ndescription: \"Select and operate local, SSH, or Slurm experiment execution with bounded, zero-LLM monitoring, safe paths, truthful terminal outcomes, and actionable recovery.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Execution and monitoring\n\nUse this skill when an experiment must be launched, inspected, or recovered and\nbackend choice or liveness semantics matter. It covers the execution boundary,\nnot the research loop or provider\u002Ftool-selection policy.\n\n## Route first\n\n1. Read the `execution.mode` value and the monitor settings.\n2. Select exactly one backend: `local`, `ssh`, or `slurm`.\n3. Validate required fields before launching anything. For `ssh` and `slurm`,\n   controller state remains local while the tool-visible workspace and logs are\n   remote. A Slurm login node is a submit\u002Ffile-operation host, not a place to\n   keep a watcher, `tmux`, `srun --wait`, or another persistent job process.\n4. Pass command arguments as an argument vector at the backend boundary. Never\n   turn untrusted command text into a shell string. Treat `slurm_setup` and\n   extra scheduler directives as trusted operator configuration.\n5. Record the returned `pid` and `log_file`; for Slurm, `pid` is the integer\n   Slurm job id. Then use the zero-LLM monitor until a terminal decision.\n\nSee [backends.md](references\u002Fbackends.md) for constructors, factory fields,\ntransport, path rules, and scheduler state mapping. See\n[monitoring.md](references\u002Fmonitoring.md) for the polling contract and result\nshape. See [troubleshooting.md](references\u002Ftroubleshooting.md) before retrying.\n\n## Configuration gate\n\nThe execution block uses these fields:\n\n- `mode`: `local` (default), `ssh`, or `slurm`.\n- `ssh_host`, `remote_workspace`, `remote_python` (default `python3`), and\n  `ssh_args` (default `[]`) for remote modes.\n- Slurm additionally requires `slurm_partition` and `slurm_time`; it accepts\n  `slurm_gpus_per_job`, `slurm_gres`, `slurm_qos`, `slurm_account`,\n  `slurm_setup`, `slurm_extra_sbatch`, `slurm_unknown_grace_polls`, and\n  `slurm_time_buffer`.\n- `monitor.poll_interval` defaults to 900 seconds, `monitor.zero_llm` defaults\n  to true, and `monitor.notify_on_complete` defaults to true.\n\nRun the bundled read-only validator when changing these values:\n\n```text\npython scripts\u002Fcheck_backend_config.py --config config.yaml\n```\n\nIt does not connect, submit, launch, or write. Add `--workspace-root DIR\n--path RELATIVE_PATH` to check a path against a workspace, including symlink\nescape detection.\n\n## Safe launch and monitor contract\n\nThe launch tool parses command text with shell-like quoting into `argv`, rejects\nan empty command and a small set of destructive executable names, and delegates\nwith `shell=False`. Semicolons and pipes therefore remain ordinary argument\ntext; they do not create a second command. A log path is normalized and checked\nbefore the backend creates its parent or opens it.\n\nThe monitor performs only backend PID\u002Fjob liveness, a short log tail, and GPU\nstatus while the job is alive. It makes no LLM call. On completion it reads up\nto 50 log lines, extracts common `loss`, `accuracy`, `FGD`, `FID`, `epoch`, and\n`step` values, and asks `final_status()` for the backend's terminal evidence.\n`status` is `failed` only when `success` is explicitly false; otherwise it is\n`completed` with `success` possibly unknown. Treat `success: null` as\nindeterminate, not proof of successful training.\n\nFor Slurm, never reap a job while `sacct` reports `PENDING` or any running-bucket\nstate, even after `slurm_time + slurm_time_buffer`: queue time is not bounded by\n`--time`. Only unconfirmed probes are bounded by consecutive unknown grace and\nthe wall-clock backstop. A confirmed Slurm `FAILED`, `TIMEOUT`, `CANCELLED`,\n`OUT_OF_MEMORY`, or other failure state must remain failed and be carried into\nstate\u002Fledger\u002Freporting. A confirmed `COMPLETED` is the only Slurm success.\n\n## Recovery checklist\n\n- `local`: inspect the final log tail and rerun only after deciding whether the\n  process ended normally; PID-only final status is inherently indeterminate.\n- `ssh`: first verify host\u002Fworkspace\u002Fhelper reachability; retry transient SSH\n  actions without changing the remote command. Do not create a remote watcher.\n- `slurm`: distinguish `PENDING` from unknown. Query `sacct` first; use its\n  state as truth, and expect the monitor's bounded unknown handling only when\n  accounting\u002Ftransport cannot confirm the job. A job reaped by the backstop has\n  unknown terminal state; reconcile the scheduler and log before calling it a\n  success or resubmitting.\n- Any path error mentioning “escapes workspace” is a safety stop. Correct the\n  relative path; do not weaken normalization or follow a symlink.\n","# Execution and monitoring\n\nUse this skill when an experiment must be launched, inspected, or recovered and\nbackend choice or liveness semantics matter. It covers the execution boundary,\nnot the research loop or provider\u002Ftool-selection policy.\n\n## Route first\n\n1. Read the `execution.mode` value and the monitor settings.\n2. Select exactly one backend: `local`, `ssh`, or `slurm`.\n3. Validate required fields before launching anything. For `ssh` and `slurm`,\n   controller state remains local while the tool-visible workspace and logs are\n   remote. A Slurm login node is a submit\u002Ffile-operation host, not a place to\n   keep a watcher, `tmux`, `srun --wait`, or another persistent job process.\n4. Pass command arguments as an argument vector at the backend boundary. Never\n   turn untrusted command text into a shell string. Treat `slurm_setup` and\n   extra scheduler directives as trusted operator configuration.\n5. Record the returned `pid` and `log_file`; for Slurm, `pid` is the integer\n   Slurm job id. Then use the zero-LLM monitor until a terminal decision.\n\nSee [backends.md](references\u002Fbackends.md) for constructors, factory fields,\ntransport, path rules, and scheduler state mapping. See\n[monitoring.md](references\u002Fmonitoring.md) for the polling contract and result\nshape. See [troubleshooting.md](references\u002Ftroubleshooting.md) before retrying.\n\n## Configuration gate\n\nThe execution block uses these fields:\n\n- `mode`: `local` (default), `ssh`, or `slurm`.\n- `ssh_host`, `remote_workspace`, `remote_python` (default `python3`), and\n  `ssh_args` (default `[]`) for remote modes.\n- Slurm additionally requires `slurm_partition` and `slurm_time`; it accepts\n  `slurm_gpus_per_job`, `slurm_gres`, `slurm_qos`, `slurm_account`,\n  `slurm_setup`, `slurm_extra_sbatch`, `slurm_unknown_grace_polls`, and\n  `slurm_time_buffer`.\n- `monitor.poll_interval` defaults to 900 seconds, `monitor.zero_llm` defaults\n  to true, and `monitor.notify_on_complete` defaults to true.\n\nRun the bundled read-only validator when changing these values:\n\n```text\npython scripts\u002Fcheck_backend_config.py --config config.yaml\n```\n\nIt does not connect, submit, launch, or write. Add `--workspace-root DIR\n--path RELATIVE_PATH` to check a path against a workspace, including symlink\nescape detection.\n\n## Safe launch and monitor contract\n\nThe launch tool parses command text with shell-like quoting into `argv`, rejects\nan empty command and a small set of destructive executable names, and delegates\nwith `shell=False`. Semicolons and pipes therefore remain ordinary argument\ntext; they do not create a second command. A log path is normalized and checked\nbefore the backend creates its parent or opens it.\n\nThe monitor performs only backend PID\u002Fjob liveness, a short log tail, and GPU\nstatus while the job is alive. It makes no LLM call. On completion it reads up\nto 50 log lines, extracts common `loss`, `accuracy`, `FGD`, `FID`, `epoch`, and\n`step` values, and asks `final_status()` for the backend's terminal evidence.\n`status` is `failed` only when `success` is explicitly false; otherwise it is\n`completed` with `success` possibly unknown. Treat `success: null` as\nindeterminate, not proof of successful training.\n\nFor Slurm, never reap a job while `sacct` reports `PENDING` or any running-bucket\nstate, even after `slurm_time + slurm_time_buffer`: queue time is not bounded by\n`--time`. Only unconfirmed probes are bounded by consecutive unknown grace and\nthe wall-clock backstop. A confirmed Slurm `FAILED`, `TIMEOUT`, `CANCELLED`,\n`OUT_OF_MEMORY`, or other failure state must remain failed and be carried into\nstate\u002Fledger\u002Freporting. A confirmed `COMPLETED` is the only Slurm success.\n\n## Recovery checklist\n\n- `local`: inspect the final log tail and rerun only after deciding whether the\n  process ended normally; PID-only final status is inherently indeterminate.\n- `ssh`: first verify host\u002Fworkspace\u002Fhelper reachability; retry transient SSH\n  actions without changing the remote command. Do not create a remote watcher.\n- `slurm`: distinguish `PENDING` from unknown. Query `sacct` first; use its\n  state as truth, and expect the monitor's bounded unknown handling only when\n  accounting\u002Ftransport cannot confirm the job. A job reaped by the backstop has\n  unknown terminal state; reconcile the scheduler and log before calling it a\n  success or resubmitting.\n- Any path error mentioning “escapes workspace” is a safety stop. Correct the\n  relative path; do not weaken normalization or follow a symlink.\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\u002Fauto-deep-researcher-24x7\u002Fsub-skills\u002Fexecution-and-monitoring",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 execution-and-monitoring",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill execution-and-monitoring",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill execution-and-monitoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fauto-deep-researcher-24x7\u002Fsub-skills\u002Fexecution-and-monitoring\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fbackends.md","REFERENCE","参考文档",7112,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fauto-deep-researcher-24x7\u002Fsub-skills\u002Fexecution-and-monitoring\u002Freferences\u002Fbackends.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fmonitoring.md",3930,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fauto-deep-researcher-24x7\u002Fsub-skills\u002Fexecution-and-monitoring\u002Freferences\u002Fmonitoring.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",5756,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fauto-deep-researcher-24x7\u002Fsub-skills\u002Fexecution-and-monitoring\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_backend_config.py","SCRIPT","脚本",7134,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fauto-deep-researcher-24x7\u002Fsub-skills\u002Fexecution-and-monitoring\u002Fscripts\u002Fcheck_backend_config.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]