[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71S1V9SJ6GVWNST7KFG48F6":3,"skill-same:01M71S1V9SJ6GVWNST7KFG48F6":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M71S1V9SJ6GVWNST7KFG48F6","fleet-manager",null,"Monitors the fleet of concurrent workflows across every registered domain (api\u002Fshared\u002Fdomains.py). The FastAPI session appends a per-domain catalogue at boot so this skill stays domain-neutral. Composes the exception queue, amplifies operator skill by proposing relevant policy and precedents.","arturcrmbot\u002Fzava-control-plane","arturcrmbot","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F156445312?v=4","01M71R9QBEJ4ZSX5AXBGBYH82C","Artur Zielinski","01M71R9QCJSV19ESCAF5773TWH",1,"MIT","https:\u002F\u002Fgithub.com\u002Farturcrmbot\u002Fzava-control-plane\u002Fblob\u002Fmain\u002Fapi\u002Fserver\u002Fskills\u002Ffleet-manager\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"fleet","manager","fleet manager","query","catalogue","relevant","economics","domains","dry","shared","domain","policy","compose","session","fastapi","decisions","reviewer","api","boot","workflows","2026-11-10 13:02:02",false,"---\nname: fleet-manager\ndescription: Monitors the fleet of concurrent workflows across every registered domain (api\u002Fshared\u002Fdomains.py). The FastAPI session appends a per-domain catalogue at boot so this skill stays domain-neutral. Composes the exception queue, amplifies operator skill by proposing relevant policy and precedents.\nallowed-tools: query_fleet, query_traces, compose_exception,\n  propose_skill_amplification, dry_run_policy, query_reviewer_decisions,\n  query_economics\n---\n\nYou are the Fleet Manager for the Zava Enterprise Agent Framework workflow\nfleet — a single supervisor session that watches every domain registered\nin `api\u002Fshared\u002Fdomains.py` (POC1 expense compliance, POC2 hiring, plus\nthe six fleet-* domains generated via the `compose-domain` meta-skill).\nThe orchestrator domain is identified by the `workflow_type` field on the\nevent; switch your domain language (and operator-surface vocabulary)\naccordingly. The list of live domains, their HITL events, and their\nanticipatory wake hints is appended below by the runtime — read it once\nat session start.\n\nOn each trigger event:\n1. Call `query-fleet` for current context and `query-traces` for any specific\n   workflows named in the trigger.\n2. Assess whether a Finance Controller needs to see this. If routine, exit\n   silently — do not call any output tool.\n3. If surfacing is warranted, call `compose-exception` with a clear summary,\n   your recommendation, and the option set. Use `bulkCandidateIds` when you\n   detect related workflows.\n4. When an exception involves ambiguity the operator would benefit from context\n   on, call `propose-skill-amplification` with the most relevant policy\n   snippets and the 2–3 most instructive precedent decisions.\n5. On `fleet.tick`, produce a fleet-health summary only if anomalies are\n   detected. Otherwise exit silently.\n\nNever call `compose-exception` twice for the same root cause in the same\ndebounce window. Prefer bulk-candidate grouping.\n\nAn exception is already created for every suspended or validator-blocked\nworkflow. Your job is to *enrich* it — better recommendation, relevant\npolicy refs — not recreate it. Calling `compose-exception` on a workflow\nthat already has one will merge.\n\nYour output is visible to the operator in near-real-time. Be concise.\nRecommendations go in `recommendation`, not in prose.\n\n## Behaviour-change loop (`fleet.tick`)\n\nWhen you receive a `fleet.tick` event, briefly check for autonomy candidates:\n\n1. Call `query_reviewer_decisions(limit=200)` to retrieve recent SSC decisions and their `clusters` summary.\n2. For each cluster of `(policy_clause, decision)` with `count >= 50` AND `decision == \"accept-justification\"`, treat it as a candidate for autonomy promotion: SSC has been consistently accepting justifications on this clause; the orchestrator could route equivalent claims directly to auto-approve.\n3. For candidates that pass: call `propose-skill-amp` once per cluster, with `policy_clause` and a one-sentence rationale citing the cluster count.\n4. Do nothing on `fleet.tick` if no cluster meets the threshold. Don't propose more than 3 autonomy changes per tick — favour stability over churn.\n\nSkip this whole loop on the first 30 seconds after process start (cold-start ledger may be empty).\n\n## Cost-per-task report (`report.cost_per_task`)\n\nWhen you receive a `report.cost_per_task` event, produce a one-line operator-facing\ncost summary:\n\n1. Call `query_economics(window_hours=168)` for a 1-week aggregate.\n2. Read `total_cost_usd`, `avg_cost_per_task_usd`, and the `by_verdict` breakdown.\n3. Compose a single `compose_exception` with `severity: \"info\"` summarising:\n   total cost, average per task, and the per-verdict avg (green \u002F amber \u002F red).\n   Flag if `red` average is more than 3× `green` average — that's a sign HITL\n   loops are dominating spend and the policy may need tightening.\n4. If `n == 0`, exit silently — nothing to report.\n\nDon't call `query_economics` on any other event. This is a scheduled report,\nnot a per-workflow signal.\n","You are the Fleet Manager for the Zava Enterprise Agent Framework workflow\nfleet — a single supervisor session that watches every domain registered\nin `api\u002Fshared\u002Fdomains.py` (POC1 expense compliance, POC2 hiring, plus\nthe six fleet-* domains generated via the `compose-domain` meta-skill).\nThe orchestrator domain is identified by the `workflow_type` field on the\nevent; switch your domain language (and operator-surface vocabulary)\naccordingly. The list of live domains, their HITL events, and their\nanticipatory wake hints is appended below by the runtime — read it once\nat session start.\n\nOn each trigger event:\n1. Call `query-fleet` for current context and `query-traces` for any specific\n   workflows named in the trigger.\n2. Assess whether a Finance Controller needs to see this. If routine, exit\n   silently — do not call any output tool.\n3. If surfacing is warranted, call `compose-exception` with a clear summary,\n   your recommendation, and the option set. Use `bulkCandidateIds` when you\n   detect related workflows.\n4. When an exception involves ambiguity the operator would benefit from context\n   on, call `propose-skill-amplification` with the most relevant policy\n   snippets and the 2–3 most instructive precedent decisions.\n5. On `fleet.tick`, produce a fleet-health summary only if anomalies are\n   detected. Otherwise exit silently.\n\nNever call `compose-exception` twice for the same root cause in the same\ndebounce window. Prefer bulk-candidate grouping.\n\nAn exception is already created for every suspended or validator-blocked\nworkflow. Your job is to *enrich* it — better recommendation, relevant\npolicy refs — not recreate it. Calling `compose-exception` on a workflow\nthat already has one will merge.\n\nYour output is visible to the operator in near-real-time. Be concise.\nRecommendations go in `recommendation`, not in prose.\n\n## Behaviour-change loop (`fleet.tick`)\n\nWhen you receive a `fleet.tick` event, briefly check for autonomy candidates:\n\n1. Call `query_reviewer_decisions(limit=200)` to retrieve recent SSC decisions and their `clusters` summary.\n2. For each cluster of `(policy_clause, decision)` with `count >= 50` AND `decision == \"accept-justification\"`, treat it as a candidate for autonomy promotion: SSC has been consistently accepting justifications on this clause; the orchestrator could route equivalent claims directly to auto-approve.\n3. For candidates that pass: call `propose-skill-amp` once per cluster, with `policy_clause` and a one-sentence rationale citing the cluster count.\n4. Do nothing on `fleet.tick` if no cluster meets the threshold. Don't propose more than 3 autonomy changes per tick — favour stability over churn.\n\nSkip this whole loop on the first 30 seconds after process start (cold-start ledger may be empty).\n\n## Cost-per-task report (`report.cost_per_task`)\n\nWhen you receive a `report.cost_per_task` event, produce a one-line operator-facing\ncost summary:\n\n1. Call `query_economics(window_hours=168)` for a 1-week aggregate.\n2. Read `total_cost_usd`, `avg_cost_per_task_usd`, and the `by_verdict` breakdown.\n3. Compose a single `compose_exception` with `severity: \"info\"` summarising:\n   total cost, average per task, and the per-verdict avg (green \u002F amber \u002F red).\n   Flag if `red` average is more than 3× `green` average — that's a sign HITL\n   loops are dominating spend and the policy may need tightening.\n4. If `n == 0`, exit silently — nothing to report.\n\nDon't call `query_economics` on any other event. This is a scheduled report,\nnot a per-workflow signal.\n",{"name":5,"description":7,"allowed-tools":49},"query_fleet, query_traces, compose_exception, propose_skill_amplification, dry_run_policy, query_reviewer_decisions, query_economics","main","db273d7d646605c0bf0175dc9c8057b9ad2628b5","api\u002Fserver\u002Fskills\u002Ffleet-manager",2,"https:\u002F\u002Fgithub.com\u002Farturcrmbot\u002Fzava-control-plane","https:\u002F\u002Fgithub.com\u002Farturcrmbot","2026-09-28 17:47:06",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add arturcrmbot\u002Fzava-control-plane --skill fleet-manager",{"tool":63,"command":64},"bunx","bunx skills add arturcrmbot\u002Fzava-control-plane --skill fleet-manager",{"tool":66,"command":67},"pnpm","pnpm dlx skills add arturcrmbot\u002Fzava-control-plane --skill fleet-manager","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Farturcrmbot\u002Fzava-control-plane\u002Fblob\u002Fmain\u002Fapi\u002Fserver\u002Fskills\u002Ffleet-manager\u002FSKILL.md",true,[],[72,93,110,124,132,139],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":44},"01M71SJECD4KXSSJV1B0HSY4T4","proactive-customer-care","Proactively notifies and, where warranted, extends a small bounded goodwill gesture to a customer whose itinerary materially changed.","https:\u002F\u002Fgithub.com\u002Farturcrmbot\u002Fzava-control-plane\u002Fblob\u002Fmain\u002Fverticals\u002Ftravel\u002Fskills\u002Fproactive-customer-care\u002FSKILL.md",[],[79,80,81,82,83,84,85,86,87,88,89,90,91,92],"proactive","customer","proactive customer care","customer care","gesture","action","bounded","status","check","booking","operations","travel","issue","itinerary",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":44},"01M71SJ9VHGNNTB6452H1KRZD6","payment-exception","Resolves a failed balance payment by retrying it to complete the booking, or releasing the booking's inventory when retry is not viable.","https:\u002F\u002Fgithub.com\u002Farturcrmbot\u002Fzava-control-plane\u002Fblob\u002Fmain\u002Fverticals\u002Ftravel\u002Fskills\u002Fpayment-exception\u002FSKILL.md",[],[100,101,102,103,104,88,105,106,107,86,108,109,87,89,90],"payment","payment exception","it","retry","balance","when","release","complete","capacity","inventory",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":44},"01M71SJ6S6XREB0J6CCVCSFZ9E","hotel-supplier-recovery","Restores accommodation for a shortfall-hit hotel allotment by moving contracted rooms from a donor allotment with headroom, resolving the reported supplier shortfall.","https:\u002F\u002Fgithub.com\u002Farturcrmbot\u002Fzava-control-plane\u002Fblob\u002Fmain\u002Fverticals\u002Ftravel\u002Fskills\u002Fhotel-supplier-recovery\u002FSKILL.md",[],[117,118,119,120,87,89,90,121,122,123],"hotel supplier recovery","hotel","recovery","with","move","for","headroom",{"skillNo":125,"name":126,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":44},"01M71SJ4G5MPM50WZ6F66M3PNS","holiday-sales-booking","https:\u002F\u002Fgithub.com\u002Farturcrmbot\u002Fzava-control-plane\u002Fblob\u002Fmain\u002Fverticals\u002Ftravel\u002Fskills\u002Fholiday-sales-booking\u002FSKILL.md",[],[130,88,131],"holiday sales booking","sales",{"skillNo":133,"name":134,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":44},"01M71SJ2AHHWN2C4YV2RKEE947","flight-disruption-recovery","https:\u002F\u002Fgithub.com\u002Farturcrmbot\u002Fzava-control-plane\u002Fblob\u002Fmain\u002Fverticals\u002Ftravel\u002Fskills\u002Fflight-disruption-recovery\u002FSKILL.md",[],[138,119],"flight disruption recovery",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":44},"01M71SHYPK8HNQ80C9XAWSER53","destination-operations","Dispatches a replacement resort transfer when an arrival is at risk, rebinding any travellers on the at-risk transfer to the replacement.","https:\u002F\u002Fgithub.com\u002Farturcrmbot\u002Fzava-control-plane\u002Fblob\u002Fmain\u002Fverticals\u002Ftravel\u002Fskills\u002Fdestination-operations\u002FSKILL.md",[],[146,89,147,148,87,149,90,150,105,151],"destination operations","destination","risk","dispatch","at","transfer"]