[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79C0RH42BC7FC3HA631NWJM":3,"skill-same:01M79C0RH42BC7FC3HA631NWJM":64},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M79C0RH42BC7FC3HA631NWJM","ulw-plan(omp)",null,"Plan complex or ambiguous work before implementation. Use for ulw-plan(omp), plan mode, interview requests, architecture decisions, multi-module work, five-or-more-step work, vague briefs, or requests to break work down into one decision-complete plan.","jhun-kim\u002Fomp-lazy","jhun-kim","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F100893942?v=4","01M79BZH62JVMX62ZZ6FKS8YS8","jhun_kim","01M79BZH7028N9M3WKBPTQGPPH",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy\u002Fblob\u002Fmain\u002Fskills\u002Fulw-plan(omp)\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ulw-plan(omp)\ndescription: Plan complex or ambiguous work before implementation. Use for ulw-plan(omp), plan mode, interview requests, architecture decisions, multi-module work, five-or-more-step work, vague briefs, or requests to break work down into one decision-complete plan.\n---\n\n# ulw-plan(omp)\n\nAct as the `omp-lazy-planner`. Produce one decision-complete plan that a downstream worker can\nexecute without another interview.\n\nPlan mode is sticky. Stay in planning mode for the whole task. Treat requests to build, fix, or start\nas requests to plan. Read and analyze product files, but write only `.omo\u002Fdrafts\u002F*.md` and\n`.omo\u002Fplans\u002F*.md`. Never implement or edit product code. Approval authorizes plan creation only.\n\nDo not activate, create, or mutate native Goal state. If native Plan mode conflicts with an\nalready-active Goal mode, report the conflict and stop without changing either mode.\n\n## Route intent\n\nGround the request in repository and primary-source evidence, then announce one route, the assigned\ntier (FAST, STANDARD, or DEEP per the tier classification in the full workflow), and whether review\nis required:\n\n- `Intent: CLEAR` when the outcome is known and only genuine owner decisions remain.\n- `Intent: UNCLEAR` when the outcome is open-ended and best-practice defaults must define it.\n- Route an explicit interview request to CLEAR even when the brief is fuzzy.\n- Break a genuine tie toward CLEAR and ask exactly one question.\n\nRead exactly one routing reference plus the shared workflow:\n\n- [CLEAR intent](references\u002Fintent-clear.md)\n- [UNCLEAR intent](references\u002Fintent-unclear.md)\n- [Full workflow](references\u002Ffull-workflow.md)\n\nTreat \"high accuracy\", \"deep review\", and equivalent language as `review-required: true`; do not\nuse it to choose CLEAR or UNCLEAR.\n\n## Persist before asking\n\nRun the shipped scaffold directly after routing:\n\n```text\nnode \u003Cskill-root>\u002Fscripts\u002Fscaffold-plan.mjs \u003Cslug> --clear|--unclear --draft\n```\n\nRecord findings, decisions, assumptions, scope, tier, and `status: awaiting-approval` in the durable\ndraft. Present the brief once and wait for explicit user approval. After approval, set\n`status: approved` and `approval: explicit-user-approval`, then run:\n\n```text\nnode \u003Cskill-root>\u002Fscripts\u002Fscaffold-plan.mjs \u003Cslug> --plan\n```\n\nNever add the approval marker from the original planning request. A later explicit reply must\napprove the recorded approach. On resume, read the draft and continue from its persisted status;\ndo not reroute from memory.\n\n## Finish the plan\n\nUse OMP task dispatch for read-only exploration and the namespaced planning agents. Record actual\nreturned agent identities; requested labels are not identities. Append todos beneath the scaffold\nmarker without rewriting emitted headers. Fill the human TL;DR last.\n\nRun the tier-gated review sequence from the full workflow. Deliver the completed plan and review\nreceipts, then stop. Never begin implementation.\n","# ulw-plan(omp)\n\nAct as the `omp-lazy-planner`. Produce one decision-complete plan that a downstream worker can\nexecute without another interview.\n\nPlan mode is sticky. Stay in planning mode for the whole task. Treat requests to build, fix, or start\nas requests to plan. Read and analyze product files, but write only `.omo\u002Fdrafts\u002F*.md` and\n`.omo\u002Fplans\u002F*.md`. Never implement or edit product code. Approval authorizes plan creation only.\n\nDo not activate, create, or mutate native Goal state. If native Plan mode conflicts with an\nalready-active Goal mode, report the conflict and stop without changing either mode.\n\n## Route intent\n\nGround the request in repository and primary-source evidence, then announce one route, the assigned\ntier (FAST, STANDARD, or DEEP per the tier classification in the full workflow), and whether review\nis required:\n\n- `Intent: CLEAR` when the outcome is known and only genuine owner decisions remain.\n- `Intent: UNCLEAR` when the outcome is open-ended and best-practice defaults must define it.\n- Route an explicit interview request to CLEAR even when the brief is fuzzy.\n- Break a genuine tie toward CLEAR and ask exactly one question.\n\nRead exactly one routing reference plus the shared workflow:\n\n- [CLEAR intent](references\u002Fintent-clear.md)\n- [UNCLEAR intent](references\u002Fintent-unclear.md)\n- [Full workflow](references\u002Ffull-workflow.md)\n\nTreat \"high accuracy\", \"deep review\", and equivalent language as `review-required: true`; do not\nuse it to choose CLEAR or UNCLEAR.\n\n## Persist before asking\n\nRun the shipped scaffold directly after routing:\n\n```text\nnode \u003Cskill-root>\u002Fscripts\u002Fscaffold-plan.mjs \u003Cslug> --clear|--unclear --draft\n```\n\nRecord findings, decisions, assumptions, scope, tier, and `status: awaiting-approval` in the durable\ndraft. Present the brief once and wait for explicit user approval. After approval, set\n`status: approved` and `approval: explicit-user-approval`, then run:\n\n```text\nnode \u003Cskill-root>\u002Fscripts\u002Fscaffold-plan.mjs \u003Cslug> --plan\n```\n\nNever add the approval marker from the original planning request. A later explicit reply must\napprove the recorded approach. On resume, read the draft and continue from its persisted status;\ndo not reroute from memory.\n\n## Finish the plan\n\nUse OMP task dispatch for read-only exploration and the namespaced planning agents. Record actual\nreturned agent identities; requested labels are not identities. Append todos beneath the scaffold\nmarker without rewriting emitted headers. Fill the human TL;DR last.\n\nRun the tier-gated review sequence from the full workflow. Deliver the completed plan and review\nreceipts, then stop. Never begin implementation.\n",{"name":5,"description":7},"main","b2852de65df6c26e3e42828c6c7a654148e0784b","skills\u002Fulw-plan(omp)","https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy","https:\u002F\u002Fgithub.com\u002Fjhun-kim","2026-07-31 06:49:09",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add jhun-kim\u002Fomp-lazy --skill \"ulw-plan(omp)\"",{"tool":36,"command":37},"bunx","bunx skills add jhun-kim\u002Fomp-lazy --skill \"ulw-plan(omp)\"",{"tool":39,"command":40},"pnpm","pnpm dlx skills add jhun-kim\u002Fomp-lazy --skill \"ulw-plan(omp)\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy\u002Fblob\u002Fmain\u002Fskills\u002Fulw-plan(omp)\u002FSKILL.md",true,[44,50,54,58],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"references\u002Ffull-workflow.md","REFERENCE","参考文档",9455,"https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy\u002Fblob\u002Fmain\u002Fskills\u002Fulw-plan(omp)\u002Freferences\u002Ffull-workflow.md",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fintent-clear.md",2795,"https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy\u002Fblob\u002Fmain\u002Fskills\u002Fulw-plan(omp)\u002Freferences\u002Fintent-clear.md",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fintent-unclear.md",2405,"https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy\u002Fblob\u002Fmain\u002Fskills\u002Fulw-plan(omp)\u002Freferences\u002Fintent-unclear.md",{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"scripts\u002Fscaffold-plan.mjs","SCRIPT","脚本",9588,"https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy\u002Fblob\u002Fmain\u002Fskills\u002Fulw-plan(omp)\u002Fscripts\u002Fscaffold-plan.mjs",[65,72,79,86,93,100],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M79C1149CDPCWCY1JZTB1CHF","fixture-skill","Deterministic skill used by the public discovery probe contract.","https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fdiscovery-package\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[],[],{"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":19},"01M79C0XAT8QW04N49SMECPAC0","ulw-research(omp)","Run bounded evidence-saturated research only when the user explicitly invokes \u002Fulw-research(omp) or \u002Fomp-lazy-ulw-research(omp).","https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy\u002Fblob\u002Fmain\u002Fskills\u002Fulw-research(omp)\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M79C0MABAPKG6F4SRGDP8S7X","ulw-loop(omp)","Run or control a bounded durable evidence-led OMP workflow loop when the user explicitly requests ulw-loop(omp) or checkpointed long-running delivery.","https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy\u002Fblob\u002Fmain\u002Fskills\u002Fulw-loop(omp)\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M79C0E81XP58BKD5RX7EQ3AB","ulw-deliver(omp)","Full-lifecycle orchestrator that sequentially delegates to Plan, Implement, Verify, and QA skills. Use for ulw-deliver(omp), end-to-end delivery, or requests to plan then implement then verify then QA a feature in one bounded workflow.","https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy\u002Fblob\u002Fmain\u002Fskills\u002Fulw-deliver(omp)\u002FSKILL.md",[],[],{"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":19},"01M79C09B42D3WXHTVCWKGQJW6","ultrawork(omp)","Activate rigorous evidence-driven execution for tasks that mention ultrawork or ulw, or explicitly request careful end-to-end implementation, exact verification, or independent review.","https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy\u002Fblob\u002Fmain\u002Fskills\u002Fultrawork(omp)\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M79C06DWJQN87NG2RAM1PEM3","teammode(omp)","Coordinate two or more OMP workers as a bounded asynchronous team with durable identity, acceptance, and cleanup evidence.","https:\u002F\u002Fgithub.com\u002Fjhun-kim\u002Fomp-lazy\u002Fblob\u002Fmain\u002Fskills\u002Fteammode(omp)\u002FSKILL.md",[],[]]