[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C7TKPCMB003TJ2JT3G2KGR":3,"skill-same:01M7C7TKPCMB003TJ2JT3G2KGR":66},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":13,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7C7TKPCMB003TJ2JT3G2KGR","highway-controls",null,"Manages the repository-wide control baseline. Use when highway-setup delegates the control baseline, after Objectives finish or when setup runs again.","jacob623\u002Fhighway-skills","jacob623","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9532643?v=4","01M7C7HA4F52SFFC164SQ76BC6","01M7C7HA57FCG77W7TGPX5R706",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills\u002Fblob\u002Fmain\u002Fhighway-agent-plugin\u002Fskills\u002Fhighway-controls\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: highway-controls\ndescription: \"Manages the repository-wide control baseline. Use when highway-setup delegates the control baseline, after Objectives finish or when setup runs again.\"\nlicense: Apache-2.0\nmetadata:\n  version: 8.8.0\n  usage: \"Run highway-controls.\"\n---\n\n# highway-controls\n\n## Purpose\n\nCollects controls when setup delegates this skill.\n\n## When to use\n\n- `highway-setup` delegates this skill after Objectives returns `Finished`.\n- `highway-setup` delegates this skill when setup runs again.\n\n## When not to use\n\nDo not create Objectives, NFRs, Capabilities, or governance rules.\nDo not treat a recommendation or a queued title as a captured Control.\nDo not report Status, Summary, Next Action, Blocking Reason, Missing, Complete, or Blocked.\nDo not emit Setup's safeguard transition. Setup already emitted it.\n\n## Inputs\n\n- `library\u002Fknowledge\u002Fprofile.md` when present.\n- `library\u002Fgovernance\u002Fobjectives.md` and `library\u002Fobjectives\u002F` when present.\n- `library\u002Fgovernance\u002Fcontrols.md` when present.\n- `library\u002Fgovernance\u002Fcontrols\u002FCTL*.md` when present.\n- `assets\u002Fcontrol-record.md`.\n- `assets\u002Fcontrol-catalog.md`.\n- The highway-experience skill, activated first.\n- Delegation from `highway-setup`.\n\n## Outputs\n\nThe complete structure is `assets\u002Fcontrol-record.md` and `assets\u002Fcontrol-catalog.md`.\n\n- Updated Control records and catalog after a review edit.\n- New Control records and catalog after the guided flow writes them.\n- `Finished` returned to `highway-setup` after review acceptance or a successful guided write.\n- `Finished` is not shown to the person.\n- One closing line after review acceptance or a successful guided write, when the person ran this skill directly.\n\n## Procedure\n\nActivate the highway-experience skill before any output the person sees, and follow it for Highway's identity, the Experience Standard, and the storage contract.\n\nUser-visible interaction follows the Highway Experience Standard. Repository ownership stays with the person.\n\nEmit only the active template. Follow this order: `review` when the catalog exists; otherwise `recommend`, then `queue` or `ask`, then `capture`, then `identifier`, `title` when needed, and `write`. Both paths end at `close`. Follow the Highway Experience Standard for attribution and acceptance wording. Use the accepted Organization Name from the Profile. Use Repository Name when no Organization Name is accepted. Do not ask for Profile or Objective facts already accepted.\n\nA Control is an enforceable safeguard: what must remain true. Do not write an Objective, a metric, or an implementation plan.\n\nBefore a step in this table, read its file and follow it to the end.\n\n| File | Steps |\n| --- | --- |\n| `references\u002Fproposal.md` | `recommend`, `more`, `queue`, `ask`, `capture` |\n| `references\u002Frecord.md` | `identifier`, `title`, `write` |\n\n### Entry\n\n1. Read `library\u002Fgovernance\u002Fcontrols.md`. Then read each active record it indexes at `library\u002Fgovernance\u002Fcontrols\u002F[ID].md`, with \"Read a file\".\n2. If the catalog is present and readable, and every active row has a readable record, go to `review`.\n3. If the catalog is absent, go to `recommend` when `profile.md` and `library\u002Fgovernance\u002Fobjectives.md` are readable. Otherwise go to `ask`.\n4. If the catalog is unreadable, or an active row has no readable record, stop. Say the Controls could not be read. Leave every file unchanged. Do not return `Finished`.\n\nA removed row has no record file. Do not treat that as unreadable.\n\n### Classify\n\nClassify the latest reply before any other action.\n\n- `select-all`: affirms every recommendation in the current set and adds no separate safeguard.\n- `select`: names one or more recommendations in the current set, by title or by number.\n- `own`: supplies a safeguard that is not a displayed title.\n- `more`: asks for more suggestions.\n- `review-now`: asks to review the queue, or affirms a queue prompt that asks whether to review.\n- `edit`: adds, removes, corrects, splits, combines, or replaces substance.\n- `accept`: affirms the current capture or review body and adds no fact.\n- `unknown`: the person says they do not know.\n- `question`: the person asks for an explanation.\n- `decline`: the person explicitly drops the active set.\n\nOn a recommendation set, \"looks good\" is `select-all`. On a queue prompt that asks whether to review, \"looks good\" and \"let's review\" are `review-now`. On a capture or on `review`, \"looks good\" is `accept`.\n\n### review\n\nShow every active Control in catalog order. Omit frontmatter, omit the catalog, and omit removed rows. For each Control emit:\n\n**[Title]:** [Statement]\n\n**Why it matters:** [Rationale]\n\n---\n\nPut `---` between Controls. Do not put `---` after the last Control.\n\nWhen no active Control is recorded, emit: No controls are recorded yet.\n\nThen emit the validation block.\n\n- `edit`: emit one consequence sentence. Apply the edit to the named Control. Preserve every Control the person left unchanged. An added safeguard becomes a new record. A removed Control deletes that record file and keeps its catalog row with status `removed`, so the id stays taken. Derive the id before writing. When the id is taken for a different title, go to `title` and do not write yet. Otherwise rewrite the affected records and the catalog. Show the updated Controls and emit the validation block. Stay on `review`.\n- `accept`: go to `close`.\n- `unknown`: show the Controls and emit the validation block. Stay on `review`.\n- `question`: answer in one sentence. Show the Controls and emit the validation block. Stay on `review`.\n\nValidation block:\n\n**What would you add, correct, or remove?**\n\nIf this is accurate, just say so.\n\n### close\n\nWhen `highway-setup` delegated this skill, return `Finished`. Emit nothing else.\n\nOtherwise emit one line and stop. When at least one Control is active, emit:\n\nYour Controls are recorded.\n\nWhen no Control is active, emit:\n\nNo Controls are recorded yet. Run highway-controls when you have one to add.\n\n## Verification\n\n- An existing readable catalog is shown with **What would you add, correct, or remove?**\n- Acceptance of that review goes to `close`.\n- Run by `highway-setup`, `close` returns `Finished` and emits nothing else. Run directly, it emits one closing line and no question.\n- A review edit rewrites the affected record and catalog, then shows the updated Controls with the same question.\n- An absent catalog and readable Profile and Objectives begin with a recommendation set.\n- Records and the catalog are written once, after the set is accepted or declined.\n- Written records match `assets\u002Fcontrol-record.md`.\n- The written catalog matches `assets\u002Fcontrol-catalog.md`.\n- Setup receives `Finished` and the person does not see that word.\n\n## Error Handling\n\n- An unreadable catalog or active record stops the skill, leaves every file unchanged, and does not return `Finished`.\n- A failed review rewrite leaves every file unchanged, says what failed in terms the person can act on, and stays on `review`.\n- A failed guided write leaves the baseline unchanged, says what failed in terms the person can act on, and stays on `write`.\n- An absent or unreadable Profile or Objectives catalog uses `ask` and does not invent organizational facts.\n\n## Example\n\n`\u002Fhighway-setup`","# highway-controls\n\n## Purpose\n\nCollects controls when setup delegates this skill.\n\n## When to use\n\n- `highway-setup` delegates this skill after Objectives returns `Finished`.\n- `highway-setup` delegates this skill when setup runs again.\n\n## When not to use\n\nDo not create Objectives, NFRs, Capabilities, or governance rules.\nDo not treat a recommendation or a queued title as a captured Control.\nDo not report Status, Summary, Next Action, Blocking Reason, Missing, Complete, or Blocked.\nDo not emit Setup's safeguard transition. Setup already emitted it.\n\n## Inputs\n\n- `library\u002Fknowledge\u002Fprofile.md` when present.\n- `library\u002Fgovernance\u002Fobjectives.md` and `library\u002Fobjectives\u002F` when present.\n- `library\u002Fgovernance\u002Fcontrols.md` when present.\n- `library\u002Fgovernance\u002Fcontrols\u002FCTL*.md` when present.\n- `assets\u002Fcontrol-record.md`.\n- `assets\u002Fcontrol-catalog.md`.\n- The highway-experience skill, activated first.\n- Delegation from `highway-setup`.\n\n## Outputs\n\nThe complete structure is `assets\u002Fcontrol-record.md` and `assets\u002Fcontrol-catalog.md`.\n\n- Updated Control records and catalog after a review edit.\n- New Control records and catalog after the guided flow writes them.\n- `Finished` returned to `highway-setup` after review acceptance or a successful guided write.\n- `Finished` is not shown to the person.\n- One closing line after review acceptance or a successful guided write, when the person ran this skill directly.\n\n## Procedure\n\nActivate the highway-experience skill before any output the person sees, and follow it for Highway's identity, the Experience Standard, and the storage contract.\n\nUser-visible interaction follows the Highway Experience Standard. Repository ownership stays with the person.\n\nEmit only the active template. Follow this order: `review` when the catalog exists; otherwise `recommend`, then `queue` or `ask`, then `capture`, then `identifier`, `title` when needed, and `write`. Both paths end at `close`. Follow the Highway Experience Standard for attribution and acceptance wording. Use the accepted Organization Name from the Profile. Use Repository Name when no Organization Name is accepted. Do not ask for Profile or Objective facts already accepted.\n\nA Control is an enforceable safeguard: what must remain true. Do not write an Objective, a metric, or an implementation plan.\n\nBefore a step in this table, read its file and follow it to the end.\n\n| File | Steps |\n| --- | --- |\n| `references\u002Fproposal.md` | `recommend`, `more`, `queue`, `ask`, `capture` |\n| `references\u002Frecord.md` | `identifier`, `title`, `write` |\n\n### Entry\n\n1. Read `library\u002Fgovernance\u002Fcontrols.md`. Then read each active record it indexes at `library\u002Fgovernance\u002Fcontrols\u002F[ID].md`, with \"Read a file\".\n2. If the catalog is present and readable, and every active row has a readable record, go to `review`.\n3. If the catalog is absent, go to `recommend` when `profile.md` and `library\u002Fgovernance\u002Fobjectives.md` are readable. Otherwise go to `ask`.\n4. If the catalog is unreadable, or an active row has no readable record, stop. Say the Controls could not be read. Leave every file unchanged. Do not return `Finished`.\n\nA removed row has no record file. Do not treat that as unreadable.\n\n### Classify\n\nClassify the latest reply before any other action.\n\n- `select-all`: affirms every recommendation in the current set and adds no separate safeguard.\n- `select`: names one or more recommendations in the current set, by title or by number.\n- `own`: supplies a safeguard that is not a displayed title.\n- `more`: asks for more suggestions.\n- `review-now`: asks to review the queue, or affirms a queue prompt that asks whether to review.\n- `edit`: adds, removes, corrects, splits, combines, or replaces substance.\n- `accept`: affirms the current capture or review body and adds no fact.\n- `unknown`: the person says they do not know.\n- `question`: the person asks for an explanation.\n- `decline`: the person explicitly drops the active set.\n\nOn a recommendation set, \"looks good\" is `select-all`. On a queue prompt that asks whether to review, \"looks good\" and \"let's review\" are `review-now`. On a capture or on `review`, \"looks good\" is `accept`.\n\n### review\n\nShow every active Control in catalog order. Omit frontmatter, omit the catalog, and omit removed rows. For each Control emit:\n\n**[Title]:** [Statement]\n\n**Why it matters:** [Rationale]\n\n---\n\nPut `---` between Controls. Do not put `---` after the last Control.\n\nWhen no active Control is recorded, emit: No controls are recorded yet.\n\nThen emit the validation block.\n\n- `edit`: emit one consequence sentence. Apply the edit to the named Control. Preserve every Control the person left unchanged. An added safeguard becomes a new record. A removed Control deletes that record file and keeps its catalog row with status `removed`, so the id stays taken. Derive the id before writing. When the id is taken for a different title, go to `title` and do not write yet. Otherwise rewrite the affected records and the catalog. Show the updated Controls and emit the validation block. Stay on `review`.\n- `accept`: go to `close`.\n- `unknown`: show the Controls and emit the validation block. Stay on `review`.\n- `question`: answer in one sentence. Show the Controls and emit the validation block. Stay on `review`.\n\nValidation block:\n\n**What would you add, correct, or remove?**\n\nIf this is accurate, just say so.\n\n### close\n\nWhen `highway-setup` delegated this skill, return `Finished`. Emit nothing else.\n\nOtherwise emit one line and stop. When at least one Control is active, emit:\n\nYour Controls are recorded.\n\nWhen no Control is active, emit:\n\nNo Controls are recorded yet. Run highway-controls when you have one to add.\n\n## Verification\n\n- An existing readable catalog is shown with **What would you add, correct, or remove?**\n- Acceptance of that review goes to `close`.\n- Run by `highway-setup`, `close` returns `Finished` and emits nothing else. Run directly, it emits one closing line and no question.\n- A review edit rewrites the affected record and catalog, then shows the updated Controls with the same question.\n- An absent catalog and readable Profile and Objectives begin with a recommendation set.\n- Records and the catalog are written once, after the set is accepted or declined.\n- Written records match `assets\u002Fcontrol-record.md`.\n- The written catalog matches `assets\u002Fcontrol-catalog.md`.\n- Setup receives `Finished` and the person does not see that word.\n\n## Error Handling\n\n- An unreadable catalog or active record stops the skill, leaves every file unchanged, and does not return `Finished`.\n- A failed review rewrite leaves every file unchanged, says what failed in terms the person can act on, and stays on `review`.\n- A failed guided write leaves the baseline unchanged, says what failed in terms the person can act on, and stays on `write`.\n- An absent or unreadable Profile or Objectives catalog uses `ask` and does not invent organizational facts.\n\n## Example\n\n`\u002Fhighway-setup`",{"name":5,"license":14,"metadata":23,"description":7},{"usage":24,"version":25},"Run highway-controls.","8.8.0","main","40844ce31770431531f69285c7c0b5372161e0f4","highway-agent-plugin\u002Fskills\u002Fhighway-controls","https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills","https:\u002F\u002Fgithub.com\u002Fjacob623","2026-11-15 03:33:56",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add jacob623\u002Fhighway-skills --skill highway-controls",{"tool":38,"command":39},"bunx","bunx skills add jacob623\u002Fhighway-skills --skill highway-controls",{"tool":41,"command":42},"pnpm","pnpm dlx skills add jacob623\u002Fhighway-skills --skill highway-controls","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills\u002Fblob\u002Fmain\u002Fhighway-agent-plugin\u002Fskills\u002Fhighway-controls\u002FSKILL.md",true,[46,52,56,62],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"assets\u002Fcontrol-catalog.md","ASSET","资产文件",913,"https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills\u002Fblob\u002Fmain\u002Fhighway-agent-plugin\u002Fskills\u002Fhighway-controls\u002Fassets\u002Fcontrol-catalog.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"assets\u002Fcontrol-record.md",1713,"https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills\u002Fblob\u002Fmain\u002Fhighway-agent-plugin\u002Fskills\u002Fhighway-controls\u002Fassets\u002Fcontrol-record.md",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fproposal.md","REFERENCE","参考文档",7741,"https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills\u002Fblob\u002Fmain\u002Fhighway-agent-plugin\u002Fskills\u002Fhighway-controls\u002Freferences\u002Fproposal.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Frecord.md",3852,"https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills\u002Fblob\u002Fmain\u002Fhighway-agent-plugin\u002Fskills\u002Fhighway-controls\u002Freferences\u002Frecord.md",[67,74,81,87,93,100],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7C7Z5YQ3BWYB6H1P0ZDY484","valid-skill","A fully conformant fixture skill used only by the tests to validate the authoring framework. Use when the tests exercise the validator.","https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fvalid-skill\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7C7YQQ3HSFB6DWS47BNYK95","invalid_skill_bad_id","Fixture whose directory name is not kebab-case, to test the id failure path. Use when the tests exercise the validator.","https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finvalid_skill_bad_id\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7C7YJWDD4GWB5VYBXWNBVK0","invalid-skill-undeclared-key","https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finvalid-skill-undeclared-key\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":6,"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},"01M7C7YFDNBRCDRGSV496BHESC","invalid-skill-short-description","https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finvalid-skill-short-description\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},"01M7C7YB56VE90KD00WMYY84XF","invalid-skill-relative-link","Fixture whose body carries a relative Markdown link target, to test the P8.7 failure path. Use when the tests exercise the validator.","https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finvalid-skill-relative-link\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},"01M7C7Y6XJ9DXY6KVNYVB1VC7W","invalid-skill-nondeterministic-criterion","Fixture whose decision criteria depend on when they are read, to test the P6.4 failure path. Use when the tests exercise the validator.","https:\u002F\u002Fgithub.com\u002Fjacob623\u002Fhighway-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finvalid-skill-nondeterministic-criterion\u002FSKILL.md",[],[]]