[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X5G38GF72SB259YY5JFGT0":3,"skill-same:01M6X5G38GF72SB259YY5JFGT0":48},{"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":18,"publishedAt":22,"linkOnly":23,"markdownContent":24,"markdownBody":25,"frontMatter":26,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M6X5G38GF72SB259YY5JFGT0","pk-team-rebalance",null,"Command: pk-team-rebalance","projectious-work\u002Fprocesskit","projectious-work","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F263889726?v=4","01M6N97TJJ118WQ35CHRV8RD0E","projectious.work","01M6N97TPWJPF0BMKYQ4PBY5W8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fharness\u002Fclaude-skills\u002Fpk-team-rebalance\u002FSKILL.md",[],[19,20,21],"team","pk team rebalance","command","2026-11-10 10:12:30",false,"---\nname: pk-team-rebalance\ndescription: \"Command: pk-team-rebalance\"\n---\n\n# Command: pk-team-rebalance\n\nApply a `pk-team-review` recommendation. Targeted re-tiering of one or\nmore roles without full team recreation. Requires `--confirm` to\nprevent accidental writes.\n\n## Syntax\n\n```\npk-team-rebalance\n  --roles \u003Clist|\"all\">         # comma-separated role names, or \"all\"\n  --confirm                    # required; prevents accidental writes\n  --reason \u003Cstring>            # recorded in the DecisionRecord amendment\n  [--landscape-artifact \u003CART-id>]  # explicit landscape override\n  [--landscape \u003Cartifact-id>]      # alias for --landscape-artifact\n  [--weight-overrides \u003Cjson>]      # override stored weights for this run\n  [--threshold-overrides \u003Cjson>]   # override stored thresholds for this run\n```\n\n## Process (sequential)\n\n### Step 1 — Load governing DecisionRecord + DEC-*-TeamWeights check\n\n```\ndecision-record.get_decision(\u003Cgoverning-DEC-id>)\n```\n\nRead `spec.inputs_snapshot` to retrieve:\n- Stored formula weights (used unless `--weight-overrides` supplied)\n- `governance_floor`\n- `parallelism_cap`\n- The landscape artifact ID from the prior run\n\n**DEC-*-TeamWeights newer-than-governing-DEC check:**\n\nQuery the decision index for the most-recent accepted DecisionRecord\ntagged `team-weights-override` (see\n`references\u002Fteam-weights-decision-schema.md`). If one exists and its\n`metadata.created` is **newer** than the governing team\nDecisionRecord's `metadata.created`, emit this warning and do NOT\nsilently apply the new weights:\n\n```\nWARNING: A newer DEC-*-TeamWeights record (created \u003CISO-date>)\npost-dates the governing team DecisionRecord (created \u003CISO-date>).\nWeight policy has changed since the last pk-team-create run. This\ntargeted rebalance uses stored weights from the governing DEC.\nTo apply the updated weights across all roles, run:\n  pk-team-rebalance --roles all --confirm --reason \"\u003Creason>\"\n```\n\nCLI `--weight-overrides` and `--threshold-overrides` always override\nstored values regardless of DEC age.\n\nIf `--roles all` is specified, re-run the full `pk-team-create` logic\n(steps 1–8 of `pk-team-create`) and write a new DecisionRecord instead\nof amending. The remainder of this document covers the non-`all`\npath.\n\n### Step 2 — Resolve landscape snapshot\n\nSame resolution logic as `pk-team-create` Step 1. If `--landscape` is\nnot supplied, use the latest `landscape-summary` artifact. Warn if\nolder than 90 days; do not block.\n\n### Step 3 — Resolve archetype names → catalog (role, seniority) and re-score\n\n`--roles` accepts archetype names (`developer`, `senior-architect`,\n...). Resolve each name through the archetype-catalog mapping\n(`assets\u002Farchetype-catalog-mapping.yaml`, layered with\n`context\u002Fteam\u002Farchetype-catalog-mapping.yaml` if present) into the\ncatalog `(ROLE-id, seniority)` pair. Operate on the matching\n`RoleSlot(s)` in the active chartering Scope.\n\nFor each archetype in `--roles`:\n\n1. Look up `(role, seniority)` via the mapping. Abort if the\n   archetype is not present and no project override defines it.\n2. Query accessible models scoped to that archetype's pinned tier:\n   ```\n   model-recommender.query_models(\n     G_floor=\u003Cgovernance_floor>,\n     apply_user_filter=true\n   )\n   ```\n3. Apply the tiering formula with stored (or override) weights.\n4. Select the best-scoring candidate for the tier.\n5. If the best candidate is the same model currently filling the\n   archetype's RoleSlot(s): report \"no change needed\"; skip writes.\n\n### Step 4 — End old role-slot-fill Bindings\n\nFor each archetype where a model change is needed, list the\nmatching RoleSlots in the active chartering Scope via\n`team-manager.list_role_slots(scope=\u003Cchartering-scope>, role=\u003CROLE-id>,\nstate=\"filled\")`, then for each filled slot end its current fill\nBinding:\n\n```\nbinding-management.end_binding(\n  id=\u003Ccurrent-role-slot-fill-BIND-id>,\n  reason=\"superseded by pk-team-rebalance: \u003C--reason> (\u003CISO-timestamp>)\"\n)\n```\n\n### Step 5 — Re-fill the existing RoleSlots\n\nA targeted rebalance does NOT close-and-reopen the slot — capacity\n(slot count) hasn't changed; only the TeamMember and the model\nunderneath it have. For each affected RoleSlot:\n\n```\nteam-manager.fill_role_slot(\n  id=\u003CSLOT-id>,\n  team_member_slug=\u003Cnew-team-member-slug>,\n  rationale=\"rebalanced \u003CISO-timestamp>: \u003C--reason> \"\n            \"(model: \u003Cnew-model-id>, score: \u003Cscore>)\",\n  valid_from=\u003Ctoday>,\n  valid_until=\u003Cchartering Scope's ends_at, if any>\n)\n```\n\n(If the new TeamMember does not yet exist in `context\u002Fteam-members\u002F`,\nprovision it first via the team-member skill. Ephemeral\n`(role, seniority)` dispatches that have no persistent TeamMember\nre-attach to the slot's `default_model_profile` instead — no fill\nwrite is needed.)\n\n### Step 6 — _(folded into step 5)_\n\nv1 split this into \"create new role-assignment Binding\"; v2's\n`fill_role_slot` writes the `role-slot-fill` Binding inline, so a\nseparate step is no longer required.\n\n### Step 7 — Update roster.md in-place\n\nRewrite the affected rows in `context\u002Fteam\u002Froster.md`'s routing table.\nUpdate the \"Last rebalanced\" timestamp and append the reason to the\nhistory section.\n\n### Step 8 — Amend governing DecisionRecord\n\nAppend to the governing DecisionRecord's `progress_notes`:\n\n```\nRebalanced on \u003CISO-timestamp> by \u003Cactor>:\n  Roles changed: \u003Clist>\n  Reason: \u003C--reason>\n  New assignments: \u003Crole> → \u003Cmodel-id> (score: \u003Cscore>)\n  Weights used: C=\u003CC> K=\u003CK> L=\u003CL> G=\u003CG>\n  Landscape: \u003Cartifact-id> (\u003Cdate>)\n```\n\nA new DecisionRecord is NOT written unless `--roles all` is used.\n\n## The `--roles all` shortcut\n\n`pk-team-rebalance --roles all --confirm --reason \"\u003Creason>\"` is\nequivalent to running `pk-team-create` with the stored weights and\nsubscription, except:\n- A new DecisionRecord IS written (superseding the current one).\n- The deactivation sequence from `pk-team-create` Step 5 applies in full.\n\nUse this when the landscape has shifted so broadly that targeted\nrebalancing would touch every role anyway.\n\n## State side-effects\n\nEnds N old `role-slot-fill` Bindings. Re-fills the affected RoleSlots\n(no slot create\u002Fclose — capacity is unchanged) and writes N new\n`role-slot-fill` Bindings via `team-manager.fill_role_slot`. Amends\nroster.md in-place. Appends to the governing DecisionRecord's\n`progress_notes`. Does NOT write a new DecisionRecord (unless\n`--roles all`).\n\n## Safety\n\n- `--confirm` is always required. The command prints the plan and\n  exits if `--confirm` is absent.\n- Dry-run preview is printed before writing, even with `--confirm`:\n  show the plan and ask for explicit \"proceed\" confirmation in\n  interactive mode; in non-interactive mode proceed immediately after\n  showing the plan.\n\n\n---\n\nThis command is a processkit skill shim. Load and follow the matching skill for `pk-team-rebalance` from `context\u002Fskills\u002F` instead of executing underlying helper scripts directly. Do not run `context\u002Fskills\u002F**\u002Fscripts\u002F*.py`, `doctor.py`, or `uv run ...\u002Fscripts\u002F...` unless the skill instructions explicitly require that implementation detail for the current step.\n","# Command: pk-team-rebalance\n\nApply a `pk-team-review` recommendation. Targeted re-tiering of one or\nmore roles without full team recreation. Requires `--confirm` to\nprevent accidental writes.\n\n## Syntax\n\n```\npk-team-rebalance\n  --roles \u003Clist|\"all\">         # comma-separated role names, or \"all\"\n  --confirm                    # required; prevents accidental writes\n  --reason \u003Cstring>            # recorded in the DecisionRecord amendment\n  [--landscape-artifact \u003CART-id>]  # explicit landscape override\n  [--landscape \u003Cartifact-id>]      # alias for --landscape-artifact\n  [--weight-overrides \u003Cjson>]      # override stored weights for this run\n  [--threshold-overrides \u003Cjson>]   # override stored thresholds for this run\n```\n\n## Process (sequential)\n\n### Step 1 — Load governing DecisionRecord + DEC-*-TeamWeights check\n\n```\ndecision-record.get_decision(\u003Cgoverning-DEC-id>)\n```\n\nRead `spec.inputs_snapshot` to retrieve:\n- Stored formula weights (used unless `--weight-overrides` supplied)\n- `governance_floor`\n- `parallelism_cap`\n- The landscape artifact ID from the prior run\n\n**DEC-*-TeamWeights newer-than-governing-DEC check:**\n\nQuery the decision index for the most-recent accepted DecisionRecord\ntagged `team-weights-override` (see\n`references\u002Fteam-weights-decision-schema.md`). If one exists and its\n`metadata.created` is **newer** than the governing team\nDecisionRecord's `metadata.created`, emit this warning and do NOT\nsilently apply the new weights:\n\n```\nWARNING: A newer DEC-*-TeamWeights record (created \u003CISO-date>)\npost-dates the governing team DecisionRecord (created \u003CISO-date>).\nWeight policy has changed since the last pk-team-create run. This\ntargeted rebalance uses stored weights from the governing DEC.\nTo apply the updated weights across all roles, run:\n  pk-team-rebalance --roles all --confirm --reason \"\u003Creason>\"\n```\n\nCLI `--weight-overrides` and `--threshold-overrides` always override\nstored values regardless of DEC age.\n\nIf `--roles all` is specified, re-run the full `pk-team-create` logic\n(steps 1–8 of `pk-team-create`) and write a new DecisionRecord instead\nof amending. The remainder of this document covers the non-`all`\npath.\n\n### Step 2 — Resolve landscape snapshot\n\nSame resolution logic as `pk-team-create` Step 1. If `--landscape` is\nnot supplied, use the latest `landscape-summary` artifact. Warn if\nolder than 90 days; do not block.\n\n### Step 3 — Resolve archetype names → catalog (role, seniority) and re-score\n\n`--roles` accepts archetype names (`developer`, `senior-architect`,\n...). Resolve each name through the archetype-catalog mapping\n(`assets\u002Farchetype-catalog-mapping.yaml`, layered with\n`context\u002Fteam\u002Farchetype-catalog-mapping.yaml` if present) into the\ncatalog `(ROLE-id, seniority)` pair. Operate on the matching\n`RoleSlot(s)` in the active chartering Scope.\n\nFor each archetype in `--roles`:\n\n1. Look up `(role, seniority)` via the mapping. Abort if the\n   archetype is not present and no project override defines it.\n2. Query accessible models scoped to that archetype's pinned tier:\n   ```\n   model-recommender.query_models(\n     G_floor=\u003Cgovernance_floor>,\n     apply_user_filter=true\n   )\n   ```\n3. Apply the tiering formula with stored (or override) weights.\n4. Select the best-scoring candidate for the tier.\n5. If the best candidate is the same model currently filling the\n   archetype's RoleSlot(s): report \"no change needed\"; skip writes.\n\n### Step 4 — End old role-slot-fill Bindings\n\nFor each archetype where a model change is needed, list the\nmatching RoleSlots in the active chartering Scope via\n`team-manager.list_role_slots(scope=\u003Cchartering-scope>, role=\u003CROLE-id>,\nstate=\"filled\")`, then for each filled slot end its current fill\nBinding:\n\n```\nbinding-management.end_binding(\n  id=\u003Ccurrent-role-slot-fill-BIND-id>,\n  reason=\"superseded by pk-team-rebalance: \u003C--reason> (\u003CISO-timestamp>)\"\n)\n```\n\n### Step 5 — Re-fill the existing RoleSlots\n\nA targeted rebalance does NOT close-and-reopen the slot — capacity\n(slot count) hasn't changed; only the TeamMember and the model\nunderneath it have. For each affected RoleSlot:\n\n```\nteam-manager.fill_role_slot(\n  id=\u003CSLOT-id>,\n  team_member_slug=\u003Cnew-team-member-slug>,\n  rationale=\"rebalanced \u003CISO-timestamp>: \u003C--reason> \"\n            \"(model: \u003Cnew-model-id>, score: \u003Cscore>)\",\n  valid_from=\u003Ctoday>,\n  valid_until=\u003Cchartering Scope's ends_at, if any>\n)\n```\n\n(If the new TeamMember does not yet exist in `context\u002Fteam-members\u002F`,\nprovision it first via the team-member skill. Ephemeral\n`(role, seniority)` dispatches that have no persistent TeamMember\nre-attach to the slot's `default_model_profile` instead — no fill\nwrite is needed.)\n\n### Step 6 — _(folded into step 5)_\n\nv1 split this into \"create new role-assignment Binding\"; v2's\n`fill_role_slot` writes the `role-slot-fill` Binding inline, so a\nseparate step is no longer required.\n\n### Step 7 — Update roster.md in-place\n\nRewrite the affected rows in `context\u002Fteam\u002Froster.md`'s routing table.\nUpdate the \"Last rebalanced\" timestamp and append the reason to the\nhistory section.\n\n### Step 8 — Amend governing DecisionRecord\n\nAppend to the governing DecisionRecord's `progress_notes`:\n\n```\nRebalanced on \u003CISO-timestamp> by \u003Cactor>:\n  Roles changed: \u003Clist>\n  Reason: \u003C--reason>\n  New assignments: \u003Crole> → \u003Cmodel-id> (score: \u003Cscore>)\n  Weights used: C=\u003CC> K=\u003CK> L=\u003CL> G=\u003CG>\n  Landscape: \u003Cartifact-id> (\u003Cdate>)\n```\n\nA new DecisionRecord is NOT written unless `--roles all` is used.\n\n## The `--roles all` shortcut\n\n`pk-team-rebalance --roles all --confirm --reason \"\u003Creason>\"` is\nequivalent to running `pk-team-create` with the stored weights and\nsubscription, except:\n- A new DecisionRecord IS written (superseding the current one).\n- The deactivation sequence from `pk-team-create` Step 5 applies in full.\n\nUse this when the landscape has shifted so broadly that targeted\nrebalancing would touch every role anyway.\n\n## State side-effects\n\nEnds N old `role-slot-fill` Bindings. Re-fills the affected RoleSlots\n(no slot create\u002Fclose — capacity is unchanged) and writes N new\n`role-slot-fill` Bindings via `team-manager.fill_role_slot`. Amends\nroster.md in-place. Appends to the governing DecisionRecord's\n`progress_notes`. Does NOT write a new DecisionRecord (unless\n`--roles all`).\n\n## Safety\n\n- `--confirm` is always required. The command prints the plan and\n  exits if `--confirm` is absent.\n- Dry-run preview is printed before writing, even with `--confirm`:\n  show the plan and ask for explicit \"proceed\" confirmation in\n  interactive mode; in non-interactive mode proceed immediately after\n  showing the plan.\n\n\n---\n\nThis command is a processkit skill shim. Load and follow the matching skill for `pk-team-rebalance` from `context\u002Fskills\u002F` instead of executing underlying helper scripts directly. Do not run `context\u002Fskills\u002F**\u002Fscripts\u002F*.py`, `doctor.py`, or `uv run ...\u002Fscripts\u002F...` unless the skill instructions explicitly require that implementation detail for the current step.\n",{"name":5,"description":7},"main","4876a92620ee792aac2ac9a1a806322d8a572367","archive\u002Fprocesskit-install-20261101\u002Fharness\u002Fclaude-skills\u002Fpk-team-rebalance","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit","https:\u002F\u002Fprojectious-work.github.io\u002Fprocesskit\u002F","https:\u002F\u002Fgithub.com\u002Fprojectious-work","2026-11-11 23:24:18",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add projectious-work\u002Fprocesskit --skill pk-team-rebalance",{"tool":40,"command":41},"bunx","bunx skills add projectious-work\u002Fprocesskit --skill pk-team-rebalance",{"tool":43,"command":44},"pnpm","pnpm dlx skills add projectious-work\u002Fprocesskit --skill pk-team-rebalance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fharness\u002Fclaude-skills\u002Fpk-team-rebalance\u002FSKILL.md",true,[],[49,56,63,69,97,117],{"skillNo":50,"name":51,"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":52,"categories":53,"keywords":54,"publishedAt":55},"01M7665G2ED3624R3X93304265","standard-ui-design","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-ui-design\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":55},"01M76651QTC6W0HJ4AFW2MMR3V","standard-agent-use","Company standard for working with AI agents. Use when deciding what to delegate to agents, capturing open work, keeping agent memory or knowledge notes, improving an agent workflow, or introducing agent work in a team or for a client.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-agent-use\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"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":66,"categories":67,"keywords":68,"publishedAt":55},"01M76650NN4T8P241021NBR64S","standard-agent-building","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-agent-building\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":80,"publishedAt":22},"01M6X5MTC89B4ZGXW3JVSQCPF8","skill-management","Manage Skill package manifests as v1 ontology entities.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fskill-management\u002FSKILL.md",[75],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[81,82,83,84,85,86,87,88,89,90,91,92,71,93,94,95,96],"management","skill management","ontology","v1","create","as","work","transition","get","manage","update","alpha","list","package","skill package","manifests",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":104,"publishedAt":22},"01M6X5MCV74NHW5MEDNHZRF2C8","schema-management","Manage generated processkit schema contracts through deterministic MCP rebuild and inspection workflows.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fschema-management\u002FSKILL.md",[103],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},[105,106,81,107,108,109,110,111,112,113,114,115,87,89,90,92,116],"schema","schema management","contract","rebuild","contracts","workflows","wed","generated","MCP","validation","deterministic","mode",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":22},"01M6X5M5G6YJ96AMZGSCZJ1D13","proposition-management","Record claims, risks, beliefs, world facts, WSJF estimates, and assumptions through the Proposition interface.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fproposition-management\u002FSKILL.md",[],[124,81,125,126,85,127,128,129,87,89,130,131,91,132,92,133,134,135,136,137],"proposition management","proposition","interface","claims","record","world","creation","event","WSJF","index","updates","query","facts","log"]