[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7234NHQP6G5BDWVTY05196H":3,"skill-same:01M7234NHQP6G5BDWVTY05196H":60},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7234NHQP6G5BDWVTY05196H","askit-init-plugin",null,"Creates a starting plugin that satisfies the Bronze anatomy and onboards the maintainer, in three modes (interview, questionnaire, hybrid). Use when starting a new plugin from scratch, onboarding a maintainer, or generating a scaffolding questionnaire.","product-on-purpose\u002Fagent-skills-toolkit","product-on-purpose","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F253892650?v=4","01M7230Q4442AHBADCVFJCS277","Product on Purpose","01M7230Q4SFDBKY7586D5M7EFX",3,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-init-plugin\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: askit-init-plugin\ndescription: Creates a starting plugin that satisfies the Bronze anatomy and onboards the maintainer, in three modes (interview, questionnaire, hybrid). Use when starting a new plugin from scratch, onboarding a maintainer, or generating a scaffolding questionnaire.\nmetadata:\n  version: 0.1.0\n  tier: universal\n  audience: beginner\n---\n\n# askit-init-plugin\n\n## Purpose\nOnboard a maintainer and scaffold a starting point that is gradeable from the first commit. Three modes: `interview` runs a live conversational Q&A, then scaffolds; `questionnaire` emits the structured [onboarding template](..\u002F..\u002Ftemplates\u002Fonboarding-questionnaire.template.md) (with per-section maintainer-feedback and agent-response blocks) for the maintainer to fill async, then processes it; `hybrid` pre-fills that questionnaire with suggestions from chat context, still leaving the feedback blocks. All three scaffold the Bronze seed anatomy from [`templates\u002Fseed-plugin\u002F`](..\u002F..\u002Ftemplates\u002Fseed-plugin\u002F) (`library.json` with the five required fields + `AGENTS.md` + a minimal `.claude-plugin\u002Fplugin.json` (`name`, `version`, `description` only, ADR 0043) + README\u002FCHANGELOG starters) so the new plugin passes the conformance core immediately AND installs on Claude Code and Codex from the first commit. Fill `name`\u002F`description` identically in `library.json` and `.claude-plugin\u002Fplugin.json`, or U8 (manifest-drift) warns on the mismatch. `interview` mode additionally asks for an optional author, so a plugin scaffolded that way carries a real attribution and passes `claude plugin validate --strict` outright; declining leaves the manifest exactly as minimal as the template, still `--strict`-warning and correctly so (ADR 0043). Mode and anatomy detail are in [references\u002Fonboarding-modes.md](references\u002Fonboarding-modes.md).\n\n## When to use\nWhen starting a brand-new plugin from scratch, onboarding a maintainer, or generating a scaffolding questionnaire. (To adopt an EXISTING repo instead, use `askit-migrate`.)\n\n## interview mode\n1. Ask the maintainer the onboarding questions live (theme\u002Fscope, target agents, target tier, first components, and an optional author: a name, and optionally a url\u002Femail).\n2. Synthesize a starting config and scaffold from `templates\u002Fseed-plugin\u002F`, filling `name`\u002F`description` in BOTH `library.json` and `.claude-plugin\u002Fplugin.json` (the same values in both) and `AGENTS.md`. If the maintainer supplied an author, add `author: { name, [url], [email] }` (only `name` is required by the vendor's schema) to BOTH `library.json` (its existing OPTIONAL field, Standard sec 5.1, so a later Silver-tier regeneration via `gen-manifest.mjs` does not silently drop it) and `.claude-plugin\u002Fplugin.json`. If the maintainer declined or skipped, emit NO `author` key in either file - never a placeholder (ADR 0043; the same class of defect U5 already penalizes in descriptions).\n3. Hand off: `askit-build-skill` for the first skill, `askit-build-docs` for docs, `askit-evaluate` to confirm Bronze.\n\n## questionnaire mode\n1. Emit `templates\u002Fonboarding-questionnaire.template.md` for the maintainer to fill async.\n2. On return, process the maintainer-feedback blocks into a config and scaffold as above.\n\n## hybrid mode\n1. From chat context, emit a tailored questionnaire pre-filled with suggested answers (keeping the feedback blocks).\n2. Process the returned, corrected questionnaire and scaffold.\n\n## Scope\nThe seed scaffold is the minimal Bronze anatomy (the structural match the asserted test enforces, ADR 0023, not a byte-exact diff): it passes every Universal check with 0 errors. The minimal `.claude-plugin\u002Fplugin.json` is install recognition ONLY, not Silver's S6 (per-target emission): it does not carry `agent-targets`, `prefix`, a `components` index, or a second native manifest, so the seed does not claim Silver behavior it has not built (ADR 0043). The richer surfaces (a real README via `askit-build-docs`, CHANGELOG via `askit-release`, ADRs via `askit-decision`, backlogs via `askit-backlog`, and the full per-target manifests via `scripts\u002Fgenerators\u002Fgen-manifest.mjs` at Silver) are scaffolded by their own skills, so init composes the toolkit rather than duplicating it. Marketplace scaffolding is `askit-init-marketplace`.\n","# askit-init-plugin\n\n## Purpose\nOnboard a maintainer and scaffold a starting point that is gradeable from the first commit. Three modes: `interview` runs a live conversational Q&A, then scaffolds; `questionnaire` emits the structured [onboarding template](..\u002F..\u002Ftemplates\u002Fonboarding-questionnaire.template.md) (with per-section maintainer-feedback and agent-response blocks) for the maintainer to fill async, then processes it; `hybrid` pre-fills that questionnaire with suggestions from chat context, still leaving the feedback blocks. All three scaffold the Bronze seed anatomy from [`templates\u002Fseed-plugin\u002F`](..\u002F..\u002Ftemplates\u002Fseed-plugin\u002F) (`library.json` with the five required fields + `AGENTS.md` + a minimal `.claude-plugin\u002Fplugin.json` (`name`, `version`, `description` only, ADR 0043) + README\u002FCHANGELOG starters) so the new plugin passes the conformance core immediately AND installs on Claude Code and Codex from the first commit. Fill `name`\u002F`description` identically in `library.json` and `.claude-plugin\u002Fplugin.json`, or U8 (manifest-drift) warns on the mismatch. `interview` mode additionally asks for an optional author, so a plugin scaffolded that way carries a real attribution and passes `claude plugin validate --strict` outright; declining leaves the manifest exactly as minimal as the template, still `--strict`-warning and correctly so (ADR 0043). Mode and anatomy detail are in [references\u002Fonboarding-modes.md](references\u002Fonboarding-modes.md).\n\n## When to use\nWhen starting a brand-new plugin from scratch, onboarding a maintainer, or generating a scaffolding questionnaire. (To adopt an EXISTING repo instead, use `askit-migrate`.)\n\n## interview mode\n1. Ask the maintainer the onboarding questions live (theme\u002Fscope, target agents, target tier, first components, and an optional author: a name, and optionally a url\u002Femail).\n2. Synthesize a starting config and scaffold from `templates\u002Fseed-plugin\u002F`, filling `name`\u002F`description` in BOTH `library.json` and `.claude-plugin\u002Fplugin.json` (the same values in both) and `AGENTS.md`. If the maintainer supplied an author, add `author: { name, [url], [email] }` (only `name` is required by the vendor's schema) to BOTH `library.json` (its existing OPTIONAL field, Standard sec 5.1, so a later Silver-tier regeneration via `gen-manifest.mjs` does not silently drop it) and `.claude-plugin\u002Fplugin.json`. If the maintainer declined or skipped, emit NO `author` key in either file - never a placeholder (ADR 0043; the same class of defect U5 already penalizes in descriptions).\n3. Hand off: `askit-build-skill` for the first skill, `askit-build-docs` for docs, `askit-evaluate` to confirm Bronze.\n\n## questionnaire mode\n1. Emit `templates\u002Fonboarding-questionnaire.template.md` for the maintainer to fill async.\n2. On return, process the maintainer-feedback blocks into a config and scaffold as above.\n\n## hybrid mode\n1. From chat context, emit a tailored questionnaire pre-filled with suggested answers (keeping the feedback blocks).\n2. Process the returned, corrected questionnaire and scaffold.\n\n## Scope\nThe seed scaffold is the minimal Bronze anatomy (the structural match the asserted test enforces, ADR 0023, not a byte-exact diff): it passes every Universal check with 0 errors. The minimal `.claude-plugin\u002Fplugin.json` is install recognition ONLY, not Silver's S6 (per-target emission): it does not carry `agent-targets`, `prefix`, a `components` index, or a second native manifest, so the seed does not claim Silver behavior it has not built (ADR 0043). The richer surfaces (a real README via `askit-build-docs`, CHANGELOG via `askit-release`, ADRs via `askit-decision`, backlogs via `askit-backlog`, and the full per-target manifests via `scripts\u002Fgenerators\u002Fgen-manifest.mjs` at Silver) are scaffolded by their own skills, so init composes the toolkit rather than duplicating it. Marketplace scaffolding is `askit-init-marketplace`.\n",{"name":5,"metadata":24,"description":7},{"tier":25,"version":26,"audience":27},"universal","0.1.0","beginner","main","b0a696723b1155d08503a8441c981998f9d13c34","skills\u002Faskit-init-plugin",0,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit","https:\u002F\u002Fproduct-on-purpose.github.io\u002Fagent-skills-toolkit","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose","2026-11-14 15:02:57",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add product-on-purpose\u002Fagent-skills-toolkit --skill askit-init-plugin",{"tool":42,"command":43},"bunx","bunx skills add product-on-purpose\u002Fagent-skills-toolkit --skill askit-init-plugin",{"tool":45,"command":46},"pnpm","pnpm dlx skills add product-on-purpose\u002Fagent-skills-toolkit --skill askit-init-plugin","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-init-plugin\u002FSKILL.md",true,[50,56],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"README.md","REFERENCE","参考文档",515,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-init-plugin\u002FREADME.md",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fonboarding-modes.md",4537,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-init-plugin\u002Freferences\u002Fonboarding-modes.md",[61,68,73,78,85,92],{"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},"01M723BRSVFQ2KRQ8KKY42R6XB","fx-demo","A fixture skill that exists so the re-derived manifest has a component list to compare. Use only from tests\u002Funit\u002Fself-consistency.test.mjs.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fself-consistency\u002Frepaired\u002Fskills\u002Ffx-demo\u002FSKILL.md",[],[],{"skillNo":69,"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":70,"categories":71,"keywords":72,"publishedAt":19},"01M723BPZ1NQDZSEF21D3YP2VF","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fself-consistency\u002Fpre-fix\u002Fskills\u002Ffx-demo\u002FSKILL.md",[],[],{"skillNo":74,"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":75,"categories":76,"keywords":77,"publishedAt":19},"01M723BNCZXT3BM577HJYESV08","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fself-consistency\u002Fbody-drift\u002Fskills\u002Ffx-demo\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M723BKWKX9JG10YQ6NK79ZB6","sf-caller","Calls the worker subagent to do a thing. Use when delegating work to sf-worker.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fsubagent-fixture\u002Fskills\u002Fsf-caller\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M723BJNDZHEJTNBJP6ZJA8WM","sf-do-thing","Converts CSV input into a formatted summary. Use when the user asks to summarize or tabulate spreadsheet data.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fsilver-fixture\u002Fskills\u002Fsf-do-thing\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M723BH7BYXT0A05PG6QH6B98","root-skill-plugin","Summarizes a changelog section into one release-note sentence. Use when the user asks to condense a list of changelog bullets into a single announcement line.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Froot-skill-plugin\u002FSKILL.md",[],[]]