[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75TK2WS1QJACQS8N40TEMCG":3,"skill-same:01M75TK2WS1QJACQS8N40TEMCG":46},{"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":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M75TK2WS1QJACQS8N40TEMCG","interview-for-personalizing",null,"First step of bootstrapping a new workbench. Through a divergence-first, gap-based interview, draw out the user's persona (language, slug style, required issue elements, PR skeleton, label scheme, harvest fields, gate toggles) and draft it into a temporary .persona\u002F scratch that generate-workbench consumes. Use this whenever the user wants to set up, create, or personalize a workbench, or talks about \"their own rules \u002F conventions\" for one — even if they don't say the word \"interview\". Precedes generate-workbench; together they are the bootstrap flow.","YOOGOMJA\u002Fworkbench-kit","YOOGOMJA","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F15305733?v=4","01M75TJ5XZX463FQMWN86JSGX0","KyeongSoo Yoo","01M75TJ5YGAAVTA8RXPFEPCE6C",0,"MIT","https:\u002F\u002Fgithub.com\u002FYOOGOMJA\u002Fworkbench-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench-kit\u002Fskills\u002Finterview-for-personalizing\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: interview-for-personalizing\ndescription: >-\n  First step of bootstrapping a new workbench. Through a divergence-first, gap-based interview, draw out the user's persona (language, slug style, required issue elements, PR skeleton, label scheme, harvest fields, gate toggles) and draft it into a temporary .persona\u002F scratch that generate-workbench consumes. Use this whenever the user wants to set up, create, or personalize a workbench, or talks about \"their own rules \u002F conventions\" for one — even if they don't say the word \"interview\". Precedes generate-workbench; together they are the bootstrap flow.\n---\n\n# interview-for-personalizing\n\nBootstrap step 1. **Draw out the persona and draft it into a temporary `.persona\u002F`.**\nThe next step, `generate-workbench`, reads `.persona\u002F`, bakes it into the user's repo,\nthen discards it.\n\n> What is persona? Only *taste* the machine does not enforce. The mechanism\n> (disposable\u002Faccumulate, task meta rules, log format, docs wiki structure, …) is\n> framework-fixed (`AGENTS.core.md`), so **don't ask about it.** Ask only persona cells.\n\n## Where the defaults come from\n\nThis skill runs from the installed `workbench-kit` plugin, *before* a user workbench\nexists — so don't look for defaults in the cwd. Read the bundled starting point at\n`${CLAUDE_PLUGIN_ROOT}\u002Fscaffold\u002FAGENTS.overlay.md` (Codex: the plugin's\n`scaffold\u002FAGENTS.overlay.md`). Show it as \"here's the default — keep it?\" and let the\nuser override only what they care about.\n\n## persona cells (= what to ask)\n\n| Cell | What to ask | Default |\n|---|---|---|\n| language | language of operational output (prose, commits, issue\u002FPR, your docs) | English |\n| slug style | word count, case, separator | lowercase kebab, 2–4 words |\n| required issue elements | what to enforce in a ticket | Background·Goal·Done·Out-of-scope |\n| PR skeleton | PR body sections, AI callout | 5 sections + callout |\n| label scheme | priority system, type\u002Farea use | priority only, human-confirmed |\n| harvest fields | decision\u002Flesson\u002Frunbook format | templates default |\n| gate toggles | where to stop and ask | PR \u002F cleanup \u002F absorption all on |\n\n> **language** governs only operational output. The framework (skills, AGENTS.core)\n> stays English; filenames\u002Fidentifiers stay stable. Default is English; capture the\n> user's choice (e.g., `ko`, `ja`).\n\n## Flow\n\nThe discipline is the same as ticket-incubate's: **don't interrogate — diverge first,\nthen ask only what's missing.** Asking all 7 cells up front makes the user feel\nprocessed and produces shallow answers; letting them talk surfaces most cells for free.\n\n1. **Diverge.** Learn how the user works (tools, taste, what their projects are). Show\n   the default profile and ask \"this is the default — good as-is, or anything off?\"\n\n2. **Fast path — all defaults.** If the user says \"just use the defaults\" (or clearly\n   has no strong preferences), skip the interview: copy the defaults into `.persona\u002F`,\n   confirm once, and hand off. Don't manufacture questions.\n\n3. **Transition signal.** Otherwise, once you can draft 2+ cells from the conversation,\n   or the user signals \"let's build it,\" move to the gap interview.\n\n4. **Gap interview — empty cells only, one at a time.** Don't re-ask cells already\n   surfaced; just confirm (\"so, Korean for output — right?\"). Skip cells the default\n   covers. One question per turn.\n\n5. **Confirm.** Show the assembled persona (the 7 cells, defaults + overrides) and get\n   an explicit OK before writing — the user should see what they're about to generate\n   from, just like ticket-incubate shows the ticket before creating it.\n\n6. **Write `.persona\u002F`** (see schema\u002Fexamples below), then hand off to\n   `generate-workbench`. Don't keep digging — details can be refined after the\n   workbench exists.\n\n## `.persona\u002F` schema + examples (the contract with generate)\n\nOutput is **temporary** (dot rule — infra scratch; generate consumes then deletes it):\n\n```\n.persona\u002F\n  overlay.md       # filled AGENTS.overlay.md — same sections as scaffold default\n  codebases.yaml   # (optional) initial work targets — may be omitted\n  meta.yaml        # where\u002Fhow generate should place the workbench\n```\n\n**`.persona\u002Foverlay.md`** — the scaffold default with the user's overrides applied.\nOnly the changed cells need differ; keep the rest as default. Example (a Korean-output\nuser who otherwise took defaults):\n\n```markdown\n## Language\n- Operational output language: **Korean** (ko). Framework stays English; filenames stable.\n\n## slug style\n- lowercase kebab, 2–4 words.\n\n## Required issue elements\n- Background · Goal · Done criteria · Out of scope.\n  ... (remaining sections unchanged from default) ...\n```\n\n**`.persona\u002Fmeta.yaml`** — tells generate where to create the workbench:\n\n```yaml\n# exactly one of `repo` or `path`\nrepo: owner\u002Fmy-workbench      # create\u002Fuse this GitHub repo\n# path: ~\u002Fdev\u002Fmy-workbench    # or a local path\nlanguage: ko                  # mirrors overlay Language (generate reads it directly)\n```\n\n**`.persona\u002Fcodebases.yaml`** (optional) — initial targets, same format as the\nframework's `codebases.yaml`:\n\n```yaml\nmy-app: https:\u002F\u002Fgithub.com\u002Fowner\u002Fmy-app.git\n```\n\n## Boundaries\n\n- Don't ask about the mechanism (core) — only taste (overlay).\n- Output goes only to the disposable `.persona\u002F` — no user repo is created yet (that's generate).\n- Leaving mid-way is fine — re-invoke to resume from defaults.\n","# interview-for-personalizing\n\nBootstrap step 1. **Draw out the persona and draft it into a temporary `.persona\u002F`.**\nThe next step, `generate-workbench`, reads `.persona\u002F`, bakes it into the user's repo,\nthen discards it.\n\n> What is persona? Only *taste* the machine does not enforce. The mechanism\n> (disposable\u002Faccumulate, task meta rules, log format, docs wiki structure, …) is\n> framework-fixed (`AGENTS.core.md`), so **don't ask about it.** Ask only persona cells.\n\n## Where the defaults come from\n\nThis skill runs from the installed `workbench-kit` plugin, *before* a user workbench\nexists — so don't look for defaults in the cwd. Read the bundled starting point at\n`${CLAUDE_PLUGIN_ROOT}\u002Fscaffold\u002FAGENTS.overlay.md` (Codex: the plugin's\n`scaffold\u002FAGENTS.overlay.md`). Show it as \"here's the default — keep it?\" and let the\nuser override only what they care about.\n\n## persona cells (= what to ask)\n\n| Cell | What to ask | Default |\n|---|---|---|\n| language | language of operational output (prose, commits, issue\u002FPR, your docs) | English |\n| slug style | word count, case, separator | lowercase kebab, 2–4 words |\n| required issue elements | what to enforce in a ticket | Background·Goal·Done·Out-of-scope |\n| PR skeleton | PR body sections, AI callout | 5 sections + callout |\n| label scheme | priority system, type\u002Farea use | priority only, human-confirmed |\n| harvest fields | decision\u002Flesson\u002Frunbook format | templates default |\n| gate toggles | where to stop and ask | PR \u002F cleanup \u002F absorption all on |\n\n> **language** governs only operational output. The framework (skills, AGENTS.core)\n> stays English; filenames\u002Fidentifiers stay stable. Default is English; capture the\n> user's choice (e.g., `ko`, `ja`).\n\n## Flow\n\nThe discipline is the same as ticket-incubate's: **don't interrogate — diverge first,\nthen ask only what's missing.** Asking all 7 cells up front makes the user feel\nprocessed and produces shallow answers; letting them talk surfaces most cells for free.\n\n1. **Diverge.** Learn how the user works (tools, taste, what their projects are). Show\n   the default profile and ask \"this is the default — good as-is, or anything off?\"\n\n2. **Fast path — all defaults.** If the user says \"just use the defaults\" (or clearly\n   has no strong preferences), skip the interview: copy the defaults into `.persona\u002F`,\n   confirm once, and hand off. Don't manufacture questions.\n\n3. **Transition signal.** Otherwise, once you can draft 2+ cells from the conversation,\n   or the user signals \"let's build it,\" move to the gap interview.\n\n4. **Gap interview — empty cells only, one at a time.** Don't re-ask cells already\n   surfaced; just confirm (\"so, Korean for output — right?\"). Skip cells the default\n   covers. One question per turn.\n\n5. **Confirm.** Show the assembled persona (the 7 cells, defaults + overrides) and get\n   an explicit OK before writing — the user should see what they're about to generate\n   from, just like ticket-incubate shows the ticket before creating it.\n\n6. **Write `.persona\u002F`** (see schema\u002Fexamples below), then hand off to\n   `generate-workbench`. Don't keep digging — details can be refined after the\n   workbench exists.\n\n## `.persona\u002F` schema + examples (the contract with generate)\n\nOutput is **temporary** (dot rule — infra scratch; generate consumes then deletes it):\n\n```\n.persona\u002F\n  overlay.md       # filled AGENTS.overlay.md — same sections as scaffold default\n  codebases.yaml   # (optional) initial work targets — may be omitted\n  meta.yaml        # where\u002Fhow generate should place the workbench\n```\n\n**`.persona\u002Foverlay.md`** — the scaffold default with the user's overrides applied.\nOnly the changed cells need differ; keep the rest as default. Example (a Korean-output\nuser who otherwise took defaults):\n\n```markdown\n## Language\n- Operational output language: **Korean** (ko). Framework stays English; filenames stable.\n\n## slug style\n- lowercase kebab, 2–4 words.\n\n## Required issue elements\n- Background · Goal · Done criteria · Out of scope.\n  ... (remaining sections unchanged from default) ...\n```\n\n**`.persona\u002Fmeta.yaml`** — tells generate where to create the workbench:\n\n```yaml\n# exactly one of `repo` or `path`\nrepo: owner\u002Fmy-workbench      # create\u002Fuse this GitHub repo\n# path: ~\u002Fdev\u002Fmy-workbench    # or a local path\nlanguage: ko                  # mirrors overlay Language (generate reads it directly)\n```\n\n**`.persona\u002Fcodebases.yaml`** (optional) — initial targets, same format as the\nframework's `codebases.yaml`:\n\n```yaml\nmy-app: https:\u002F\u002Fgithub.com\u002Fowner\u002Fmy-app.git\n```\n\n## Boundaries\n\n- Don't ask about the mechanism (core) — only taste (overlay).\n- Output goes only to the disposable `.persona\u002F` — no user repo is created yet (that's generate).\n- Leaving mid-way is fine — re-invoke to resume from defaults.\n",{"name":5,"description":7},"main","de5b96abac47550446c5218df24bc825ebe89834","plugins\u002Fworkbench-kit\u002Fskills\u002Finterview-for-personalizing","https:\u002F\u002Fgithub.com\u002FYOOGOMJA\u002Fworkbench-kit","https:\u002F\u002Fgithub.com\u002FYOOGOMJA","http:\u002F\u002Fyoogomja.github.io","91. S.Korea, Seoul","2026-07-18 22:44:59",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add YOOGOMJA\u002Fworkbench-kit --skill interview-for-personalizing",{"tool":38,"command":39},"bunx","bunx skills add YOOGOMJA\u002Fworkbench-kit --skill interview-for-personalizing",{"tool":41,"command":42},"pnpm","pnpm dlx skills add YOOGOMJA\u002Fworkbench-kit --skill interview-for-personalizing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYOOGOMJA\u002Fworkbench-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench-kit\u002Fskills\u002Finterview-for-personalizing\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M75TN7BPKV278CKYJ8F8DT6P","ticket-incubate","Use to turn an idea that has no issue\u002Fticket yet into an actionable GitHub issue. Grow a vague notion by divergence, narrow only the gaps via a deficit-based interview, and create the issue once the four required elements (background, goal, done criteria, out-of-scope) are filled. Triggers on \"I have an idea\", \"let's make this a ticket\", \"create an issue\", \"interview me\", or describing something to make\u002Ffix\u002Fimprove without an issue number, even if the user never says the word \"ticket\". It is the front of the workbench lifecycle (idea -> ticket-incubate -> issue -> task-start). Distinct from brainstorming\u002Fdesign skills: those work out the how of what to build now; this captures the what of later work as a well-honed ticket.","https:\u002F\u002Fgithub.com\u002FYOOGOMJA\u002Fworkbench-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Fticket-incubate\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M75TN47B3HC1KT6P5EHFAW6W","task-tickets","Use to scan open workbench tickets joined with task branches and lifecycle events into unstarted \u002F claim-attempted \u002F in-progress \u002F awaiting-PR \u002F cleaned-up states. Read-only.","https:\u002F\u002Fgithub.com\u002FYOOGOMJA\u002Fworkbench-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Ftask-tickets\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M75TN28YAAPDYZAD3KS1Z1S0","task-submit","Use when the user asks to submit, wrap up, or extract from a task, or when work has reached a point to open a PR.","https:\u002F\u002Fgithub.com\u002FYOOGOMJA\u002Fworkbench-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Ftask-submit\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M75TMZ90692T90ENMZZ6N80E","task-status","Use to see local and remote task status at a glance and diagnose drift (unpushed, stale status, missed cleanup). When you want to know where everything stands before starting or submitting, or after a multi-device handoff.","https:\u002F\u002Fgithub.com\u002FYOOGOMJA\u002Fworkbench-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Ftask-status\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M75TMX5MEJ086EJ5YCZJ6Q53","task-start","Use when the user asks to start a task, pick up an issue, or begin a new attempt, or hands over an issue number to start work.","https:\u002F\u002Fgithub.com\u002FYOOGOMJA\u002Fworkbench-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Ftask-start\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M75TMVBKXW775S7XW9E332F8","task-done","Use when the user asks to clean up or discard a task, or to clear the workspace after a PR is merged.","https:\u002F\u002Fgithub.com\u002FYOOGOMJA\u002Fworkbench-kit\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Ftask-done\u002FSKILL.md",[],[]]