[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WZQQ2K1HTDKD23T8QFZ316":3,"skill-same:01M6WZQQ2K1HTDKD23T8QFZ316":102},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":75,"commitSha":76,"skillDirectory":77,"forksCount":14,"repositoryHtmlUrl":78,"repositoryHomepageUrl":79,"ownerHtmlUrl":80,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":81,"install":82,"resources":95},"01M6WZQQ2K1HTDKD23T8QFZ316","process-management",null,"Manage Process entities — declarative sequences of steps with roles, gates, and a definition of done. Use when defining a reusable workflow — code review, release, incident response, onboarding — that the project wants to run consistently.","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\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.18.1\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fprocess-management\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"process management","process","management","when","code review","audit trail","definition","project","incident","done","log","work","ids","audit","code","run","workflow","definition of done","incident response","review","2026-11-10 10:12:30",false,"---\nname: process-management\ndescription: |\n  Manage Process entities — declarative sequences of steps with roles, gates, and a definition of done. Use when defining a reusable workflow — code review, release, incident response, onboarding — that the project wants to run consistently.\nmetadata:\n  processkit:\n    apiVersion: processkit.projectious.work\u002Fv1\n    id: SKILL-process-management\n    version: \"1.0.0\"\n    created: 2026-04-06T00:00:00Z\n    category: processkit\n    layer: 3\n    uses:\n      - skill: event-log\n        purpose: Log events to keep the audit trail accurate after every write.\n      - skill: role-management\n        purpose: Resolve Role IDs when entities need role-based assignment.\n      - skill: gate-management\n        purpose: Evaluate gate conditions before allowing transitions.\n    provides:\n      primitives: [Process]\n      templates: [process]\n---\n\n# Process Management\n\n## Intro\n\nA Process is a declarative definition of a workflow: a sequence of steps,\nthe roles involved, the gates that must pass, and the definition of done.\nprocesskit does NOT execute processes — agents and humans do. processkit\njust defines them.\n\n## Overview\n\n### Shape\n\n```yaml\n---\napiVersion: processkit.projectious.work\u002Fv1\nkind: Process\nmetadata:\n  id: PROC-code-review\n  created: 2026-04-06T00:00:00Z\nspec:\n  name: code-review\n  description: \"Review a pull request before merge.\"\n  triggers: [pr.opened, pr.review-requested]\n  roles: [developer, reviewer]\n  steps:\n    - name: author-self-check\n      role: developer\n      uses_skill: code-review\n      description: \"Author runs the self-review checklist.\"\n    - name: peer-review\n      role: reviewer\n      uses_skill: code-review\n      description: \"A different actor reviews the diff and leaves comments.\"\n      gates: [GATE-no-blocking-comments]\n    - name: approval\n      role: reviewer\n      description: \"Reviewer approves the PR.\"\n      gates: [GATE-code-review-passed]\n    - name: merge\n      role: developer\n      description: \"Author merges after approval and CI pass.\"\n      gates: [GATE-ci-passed, GATE-code-review-passed]\n  definition_of_done: \"PR merged with at least one approval, all CI gates passed.\"\n---\n```\n\n### Workflow\n\n1. Pick `PROC-\u003Cname>`.\n2. List `triggers` — events that kick off the process.\n3. List required `roles`.\n4. Define `steps` in order. Each step names the actor role, optional skill,\n   description, and gates.\n5. Write a clear `definition_of_done`.\n6. Save to `context\u002Fprocesses\u002F`.\n\n### Running a process\n\nAn agent running a process:\n1. Detects the trigger.\n2. Walks the steps in order.\n3. For each step, performs the action (often guided by `uses_skill`).\n4. Validates gates at each step — logs `gate.passed` \u002F `gate.failed`.\n5. Logs `process.step.started` \u002F `process.step.completed`.\n6. Exits when the last step completes or a blocking gate fails.\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Defining a Process without ownership.** Every Process needs an\n  owner Actor — the person or role responsible for keeping it\n  current. Unowned Processes drift and become \"the way we used to\n  do things\".\n- **Process with no termination criteria.** A Process must answer\n  \"how do I know this is done\". Open-ended processes that never\n  terminate become noise; the agent has no signal to stop\n  participating.\n- **Hand-waving \"automated steps\" that aren't actually wired.** If\n  a Process step says \"CI runs automatically\", verify the CI hook\n  exists. A Process that lies about its automation is worse than\n  one that admits everything is manual.\n- **Forgetting to version Process changes.** When a Process\n  definition changes, bump the version. Existing in-flight runs\n  should reference the version they started under, not silently\n  inherit the new rules mid-flight.\n- **Mixing Process steps with WorkItems.** A Process step\n  (\"review the PR\") is reusable across many runs; a WorkItem\n  (\"review BACK-1234\") is one specific instance. Don't put\n  workitem-specific data in the Process definition.\n- **Process documentation without examples.** A Process that says\n  \"follow the release checklist\" without linking to a worked\n  example of a past release is incomplete. Examples are the\n  difference between followable and theoretical.\n- **Authoring a Process for a one-off operation.** If you only run\n  it once, it's a runbook entry or a project log, not a Process.\n  Processes earn their cost through repetition.\n\n## Full reference\n\n### Fields\n\n| Field                | Type          | Notes                                              |\n|----------------------|---------------|----------------------------------------------------|\n| `name`               | string        | kebab-case identifier                              |\n| `description`        | string        | One sentence                                       |\n| `triggers`           | list[string]  | Event types that start the process                 |\n| `roles`              | list[string]  | Role names involved                                |\n| `steps`              | list[object]  | Ordered list; see below                            |\n| `definition_of_done` | string        | The acceptance criterion for the whole process     |\n| `parallel`           | bool          | Default false; true = steps run in parallel        |\n| `retryable`          | bool          | Can the process be re-run if it fails?             |\n\n### Step object\n\n```yaml\n- name: \u003Cstep-name>\n  role: \u003Crole-name>         # who performs this step\n  description: \u003Cone-sentence>\n  uses_skill: \u003Cskill-name>  # optional — skill that guides execution\n  inputs: [\u003Centity-ref>]    # optional — what this step needs\n  outputs: [\u003Centity-ref>]   # optional — what this step produces\n  gates: [\u003Cgate-id>]        # optional — gates that must pass\n  on_failure: \u003Caction>      # halt | retry | skip | escalate\n```\n\n### Parallel vs sequential\n\nDefault is sequential. Set `parallel: true` to run steps concurrently when\nthey are independent. For conditional branching, write multiple processes\nand trigger them conditionally rather than embedding complex logic.\n\n### Scoping a process\n\nUse a Binding (`type: process-scope`) to apply a process to a specific\nproject or team:\n\n```yaml\nkind: Binding\nspec:\n  type: process-scope\n  subject: PROC-code-review\n  target: SCOPE-project-x\n```\n\n### No workflow engine\n\nprocesskit does not ship an engine that executes processes. The Process\ndefinition is a contract between the definition and whoever runs it. Agents\nare the default runners; automation can take over specific steps.\n","# Process Management\n\n## Intro\n\nA Process is a declarative definition of a workflow: a sequence of steps,\nthe roles involved, the gates that must pass, and the definition of done.\nprocesskit does NOT execute processes — agents and humans do. processkit\njust defines them.\n\n## Overview\n\n### Shape\n\n```yaml\n---\napiVersion: processkit.projectious.work\u002Fv1\nkind: Process\nmetadata:\n  id: PROC-code-review\n  created: 2026-04-06T00:00:00Z\nspec:\n  name: code-review\n  description: \"Review a pull request before merge.\"\n  triggers: [pr.opened, pr.review-requested]\n  roles: [developer, reviewer]\n  steps:\n    - name: author-self-check\n      role: developer\n      uses_skill: code-review\n      description: \"Author runs the self-review checklist.\"\n    - name: peer-review\n      role: reviewer\n      uses_skill: code-review\n      description: \"A different actor reviews the diff and leaves comments.\"\n      gates: [GATE-no-blocking-comments]\n    - name: approval\n      role: reviewer\n      description: \"Reviewer approves the PR.\"\n      gates: [GATE-code-review-passed]\n    - name: merge\n      role: developer\n      description: \"Author merges after approval and CI pass.\"\n      gates: [GATE-ci-passed, GATE-code-review-passed]\n  definition_of_done: \"PR merged with at least one approval, all CI gates passed.\"\n---\n```\n\n### Workflow\n\n1. Pick `PROC-\u003Cname>`.\n2. List `triggers` — events that kick off the process.\n3. List required `roles`.\n4. Define `steps` in order. Each step names the actor role, optional skill,\n   description, and gates.\n5. Write a clear `definition_of_done`.\n6. Save to `context\u002Fprocesses\u002F`.\n\n### Running a process\n\nAn agent running a process:\n1. Detects the trigger.\n2. Walks the steps in order.\n3. For each step, performs the action (often guided by `uses_skill`).\n4. Validates gates at each step — logs `gate.passed` \u002F `gate.failed`.\n5. Logs `process.step.started` \u002F `process.step.completed`.\n6. Exits when the last step completes or a blocking gate fails.\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Defining a Process without ownership.** Every Process needs an\n  owner Actor — the person or role responsible for keeping it\n  current. Unowned Processes drift and become \"the way we used to\n  do things\".\n- **Process with no termination criteria.** A Process must answer\n  \"how do I know this is done\". Open-ended processes that never\n  terminate become noise; the agent has no signal to stop\n  participating.\n- **Hand-waving \"automated steps\" that aren't actually wired.** If\n  a Process step says \"CI runs automatically\", verify the CI hook\n  exists. A Process that lies about its automation is worse than\n  one that admits everything is manual.\n- **Forgetting to version Process changes.** When a Process\n  definition changes, bump the version. Existing in-flight runs\n  should reference the version they started under, not silently\n  inherit the new rules mid-flight.\n- **Mixing Process steps with WorkItems.** A Process step\n  (\"review the PR\") is reusable across many runs; a WorkItem\n  (\"review BACK-1234\") is one specific instance. Don't put\n  workitem-specific data in the Process definition.\n- **Process documentation without examples.** A Process that says\n  \"follow the release checklist\" without linking to a worked\n  example of a past release is incomplete. Examples are the\n  difference between followable and theoretical.\n- **Authoring a Process for a one-off operation.** If you only run\n  it once, it's a runbook entry or a project log, not a Process.\n  Processes earn their cost through repetition.\n\n## Full reference\n\n### Fields\n\n| Field                | Type          | Notes                                              |\n|----------------------|---------------|----------------------------------------------------|\n| `name`               | string        | kebab-case identifier                              |\n| `description`        | string        | One sentence                                       |\n| `triggers`           | list[string]  | Event types that start the process                 |\n| `roles`              | list[string]  | Role names involved                                |\n| `steps`              | list[object]  | Ordered list; see below                            |\n| `definition_of_done` | string        | The acceptance criterion for the whole process     |\n| `parallel`           | bool          | Default false; true = steps run in parallel        |\n| `retryable`          | bool          | Can the process be re-run if it fails?             |\n\n### Step object\n\n```yaml\n- name: \u003Cstep-name>\n  role: \u003Crole-name>         # who performs this step\n  description: \u003Cone-sentence>\n  uses_skill: \u003Cskill-name>  # optional — skill that guides execution\n  inputs: [\u003Centity-ref>]    # optional — what this step needs\n  outputs: [\u003Centity-ref>]   # optional — what this step produces\n  gates: [\u003Cgate-id>]        # optional — gates that must pass\n  on_failure: \u003Caction>      # halt | retry | skip | escalate\n```\n\n### Parallel vs sequential\n\nDefault is sequential. Set `parallel: true` to run steps concurrently when\nthey are independent. For conditional branching, write multiple processes\nand trigger them conditionally rather than embedding complex logic.\n\n### Scoping a process\n\nUse a Binding (`type: process-scope`) to apply a process to a specific\nproject or team:\n\n```yaml\nkind: Binding\nspec:\n  type: process-scope\n  subject: PROC-code-review\n  target: SCOPE-project-x\n```\n\n### No workflow engine\n\nprocesskit does not ship an engine that executes processes. The Process\ndefinition is a contract between the definition and whoever runs it. Agents\nare the default runners; automation can take over specific steps.\n",{"name":5,"metadata":52,"description":74},{"processkit":53},{"id":54,"uses":55,"layer":65,"created":66,"version":67,"category":68,"provides":69,"apiVersion":73},"SKILL-process-management",[56,59,62],{"skill":57,"purpose":58},"event-log","Log events to keep the audit trail accurate after every write.",{"skill":60,"purpose":61},"role-management","Resolve Role IDs when entities need role-based assignment.",{"skill":63,"purpose":64},"gate-management","Evaluate gate conditions before allowing transitions.",3,1775433600000,"1.0.0","processkit",{"templates":70,"primitives":71},[28],[72],"Process","processkit.projectious.work\u002Fv1","Manage Process entities — declarative sequences of steps with roles, gates, and a definition of done. Use when defining a reusable workflow — code review, release, incident response, onboarding — that the project wants to run consistently.\n","main","4876a92620ee792aac2ac9a1a806322d8a572367","archive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.18.1\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fprocess-management","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":83,"prompt":93,"zipAvailable":94},[84,87,90],{"tool":85,"command":86},"npx","npx skills add projectious-work\u002Fprocesskit --skill process-management",{"tool":88,"command":89},"bunx","bunx skills add projectious-work\u002Fprocesskit --skill process-management",{"tool":91,"command":92},"pnpm","pnpm dlx skills add projectious-work\u002Fprocesskit --skill process-management","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.18.1\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fprocess-management\u002FSKILL.md",true,[96],{"path":97,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":100,"sourceHtmlUrl":101},"assets\u002Fprocess.yaml","ASSET","资产文件",342,"https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.18.1\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fprocess-management\u002Fassets\u002Fprocess.yaml",[103,110,117,123,145,165],{"skillNo":104,"name":105,"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":106,"categories":107,"keywords":108,"publishedAt":109},"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":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":109},"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":118,"name":119,"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":120,"categories":121,"keywords":122,"publishedAt":109},"01M76650NN4T8P241021NBR64S","standard-agent-building","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-agent-building\u002FSKILL.md",[],[],{"skillNo":124,"name":125,"nameZh":6,"description":126,"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":130,"publishedAt":47},"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",[129],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[29,131,132,133,134,135,38,136,137,138,139,140,125,141,142,143,144],"skill management","ontology","v1","create","as","transition","get","manage","update","alpha","list","package","skill package","manifests",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":152,"publishedAt":47},"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",[151],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[153,154,29,155,156,157,158,159,160,161,162,163,38,137,138,140,164],"schema","schema management","contract","rebuild","contracts","workflows","wed","generated","MCP","validation","deterministic","mode",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":47},"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",[],[172,29,173,174,134,175,176,177,38,137,178,179,139,180,140,181,182,183,184,37],"proposition management","proposition","interface","claims","record","world","creation","event","WSJF","index","updates","query","facts"]