[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ART73D38PTGX5AE1STQPSM":3,"skill-same:01M7ART73D38PTGX5AE1STQPSM":62},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":43},"01M7ART73D38PTGX5AE1STQPSM","create-verification-skill",null,"Create project-local behavior verification skills and adapters when asked to build repeatable UI, CLI, mobile, or service checks.","gutierrezje\u002Fjstack","gutierrezje","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F32502846?v=4","01M7ARSJH934J0XXNJC02Y6PB0","Jesus E. Gutierrez","01M7ARSJJ8PN0AGVX140JK202H",0,"MIT","https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: create-verification-skill\ndescription: \"Create project-local behavior verification skills and adapters when asked to build repeatable UI, CLI, mobile, or service checks.\"\ndisable-model-invocation: true\n---\n\n# Create verification skill\n\nRead and follow the [project verification contract](..\u002Fjesus-mode\u002Freferences\u002Fverification.md).\n\n1. Inspect every user-facing surface, its launch path, user journeys, existing\n   tests, shared services, authentication, mutable data, and available control\n   tooling.\n2. Split verification skills when surfaces have materially different control,\n   authentication, state, data-safety, or evidence boundaries. Create one\n   `verify-\u003Csurface>` skill per boundary. Keep one skill only when the same setup,\n   driver, fixtures, cleanup, and proof contract genuinely apply.\n3. Choose the real harness for each surface: `$cursor-team-kit:control-ui`,\n   `$cursor-team-kit:control-cli`, browser\u002Fchrome\u002Fcomputer-use, or a project-native\n   driver. Reuse an existing environment-setup skill instead of copying its\n   process-management instructions.\n4. Create each project-local `.agents\u002Fskills\u002Fverify-\u003Csurface>\u002F` skill with\n   `$skill-creator` and `$writing-for-agents`.\n5. Drive the first path manually to learn the real sequence. When repeated\n   project-specific setup, control, observation, or cleanup remains, build the\n   smallest executable adapter that satisfies the shared contract. Test it\n   through its public commands rather than its implementation.\n6. Include exact target identity, setup, launch, a deterministic read-only or\n   disposable happy path, evidence capture, mutation authority, cleanup, failure\n   interpretation, and a feature map under `features\u002F`.\n   Make launch reach a usable state from an empty data directory, including\n   migrations and seed data. Ready means usable, not only that a process or port\n   answers; a database health check can pass while init scripts still run.\n   When seed data lacks a precondition a journey needs, the journey reports a\n   failure and the reason goes in that feature's `Gotchas`; never weaken the\n   journey to make it pass.\n   For requested video or temporal behavior, follow the\n   [video evidence contract](..\u002Fjesus-mode\u002Freferences\u002Fvideo-evidence.md); document\n   recorder capabilities, finalization, receipt coverage, and the recipe's\n   required versus optional video proof.\n7. Seed the top three to five user-facing features in each skill using\n   `references\u002Ffeature-map-example\u002F`. Inventory every discovered entry point in\n   the map as covered or explicitly excluded, and name feature IDs so a PR\n   workflow can select only the journeys affected by a change.\n8. Run every adapter or adopted project-native controller against the real\n   product, inspect its receipt, fix the instructions, and validate every\n   generated skill. When the proof ran in a stand-in for the real target (a\n   container for a fresh VM, a local stack for a remote one), list every setup\n   step the stand-in did that the target will not, and keep those steps\n   unverified until a run on the real target covers them.\n\nCompletion means a cold agent can select the correct verification skill, bind it\nto the exact target, discover the control interface through help, drive one real\nfeature per surface, recognize success from a machine-readable receipt, and\nrestore or account for mutated state.\n","# Create verification skill\n\nRead and follow the [project verification contract](..\u002Fjesus-mode\u002Freferences\u002Fverification.md).\n\n1. Inspect every user-facing surface, its launch path, user journeys, existing\n   tests, shared services, authentication, mutable data, and available control\n   tooling.\n2. Split verification skills when surfaces have materially different control,\n   authentication, state, data-safety, or evidence boundaries. Create one\n   `verify-\u003Csurface>` skill per boundary. Keep one skill only when the same setup,\n   driver, fixtures, cleanup, and proof contract genuinely apply.\n3. Choose the real harness for each surface: `$cursor-team-kit:control-ui`,\n   `$cursor-team-kit:control-cli`, browser\u002Fchrome\u002Fcomputer-use, or a project-native\n   driver. Reuse an existing environment-setup skill instead of copying its\n   process-management instructions.\n4. Create each project-local `.agents\u002Fskills\u002Fverify-\u003Csurface>\u002F` skill with\n   `$skill-creator` and `$writing-for-agents`.\n5. Drive the first path manually to learn the real sequence. When repeated\n   project-specific setup, control, observation, or cleanup remains, build the\n   smallest executable adapter that satisfies the shared contract. Test it\n   through its public commands rather than its implementation.\n6. Include exact target identity, setup, launch, a deterministic read-only or\n   disposable happy path, evidence capture, mutation authority, cleanup, failure\n   interpretation, and a feature map under `features\u002F`.\n   Make launch reach a usable state from an empty data directory, including\n   migrations and seed data. Ready means usable, not only that a process or port\n   answers; a database health check can pass while init scripts still run.\n   When seed data lacks a precondition a journey needs, the journey reports a\n   failure and the reason goes in that feature's `Gotchas`; never weaken the\n   journey to make it pass.\n   For requested video or temporal behavior, follow the\n   [video evidence contract](..\u002Fjesus-mode\u002Freferences\u002Fvideo-evidence.md); document\n   recorder capabilities, finalization, receipt coverage, and the recipe's\n   required versus optional video proof.\n7. Seed the top three to five user-facing features in each skill using\n   `references\u002Ffeature-map-example\u002F`. Inventory every discovered entry point in\n   the map as covered or explicitly excluded, and name feature IDs so a PR\n   workflow can select only the journeys affected by a change.\n8. Run every adapter or adopted project-native controller against the real\n   product, inspect its receipt, fix the instructions, and validate every\n   generated skill. When the proof ran in a stand-in for the real target (a\n   container for a fresh VM, a local stack for a remote one), list every setup\n   step the stand-in did that the target will not, and keep those steps\n   unverified until a run on the real target covers them.\n\nCompletion means a cold agent can select the correct verification skill, bind it\nto the exact target, discover the control interface through help, drive one real\nfeature per surface, recognize success from a machine-readable receipt, and\nrestore or account for mutated state.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","bbac2ca2c2f494880dc8aa5d58dc4f768501f290","skills\u002Fcreate-verification-skill","https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack","https:\u002F\u002Fgithub.com\u002Fgutierrezje","2026-11-11 14:57:12",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":24},[33,36,39],{"tool":34,"command":35},"npx","npx skills add gutierrezje\u002Fjstack --skill create-verification-skill",{"tool":37,"command":38},"bunx","bunx skills add gutierrezje\u002Fjstack --skill create-verification-skill",{"tool":40,"command":41},"pnpm","pnpm dlx skills add gutierrezje\u002Fjstack --skill create-verification-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[44,50,54,58],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"agents\u002Fopenai.yaml","REFERENCE","参考文档",243,"https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fcreate-verification-skill\u002Fagents\u002Fopenai.yaml",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Ffeature-map-example\u002Fcreate-note.md",3236,"https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fcreate-verification-skill\u002Freferences\u002Ffeature-map-example\u002Fcreate-note.md",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Ffeature-map-example\u002FREADME.md",4365,"https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fcreate-verification-skill\u002Freferences\u002Ffeature-map-example\u002FREADME.md",{"path":59,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Ffeature-map-example\u002Fsearch.md",3763,"https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fcreate-verification-skill\u002Freferences\u002Ffeature-map-example\u002Fsearch.md",[63,70,77,84,91,98],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7ARWNBDTFSVCHWFQ4BYWQSX","why","Why code is this way: design rationale, regressions, and history from evidence. For runtime: how.","https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7ARWKP5P795ZTFRJQJNK9ZK","unslop","Edit prose to remove AI writing patterns when polishing text or asked to make it sound natural.","https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7ARWG34VZRC0FZTP4Z1VXFH","typescript-best-practices","Use when writing or reviewing .ts\u002F.tsx code: types, validation boundaries, and API signatures.","https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7ARWBBKAMRHVJH929D2TSW1","sync-pstack","Analyze upstream cursor\u002Fplugins pstack changes and guide semantic ports into Codex-native Jstack without overwriting local skills. Use when the user says \"sync pstack\", \"check pstack updates\", or asks to update Jstack from upstream.","https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fsync-pstack\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7ARW853DBZYE9ETT0ZZHP9J","swarm","Fan out N parallel workers, drain them, and return one report. Use for \u002Fswarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.","https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fswarm\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7ARW5Y0CMDJCAJ1P3KKBDV8","statechart","Check a finite TLA+ model and explain its paths and rule failures as a statechart.","https:\u002F\u002Fgithub.com\u002Fgutierrezje\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fstatechart\u002FSKILL.md",[],[]]