[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7234TTHJWZQPS0GQXR226MX":3,"skill-same:01M7234TTHJWZQPS0GQXR226MX":73},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M7234TTHJWZQPS0GQXR226MX","askit-onboard",null,"Assesses where an adopter stands with this toolkit's plugin and skills, then plans a personalized roadmap through a short interview and reports the next step on a return visit. Use when a user asks how to get started with this toolkit, wants a tailored adoption plan rather than generic docs, or comes back later asking what to do next; it routes to the existing assess, build, and migrate skills and to existing how-to and tutorial pages, and never scaffolds or fixes anything itself.","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-onboard\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: askit-onboard\ndescription: Assesses where an adopter stands with this toolkit's plugin and skills, then plans a personalized roadmap through a short interview and reports the next step on a return visit. Use when a user asks how to get started with this toolkit, wants a tailored adoption plan rather than generic docs, or comes back later asking what to do next; it routes to the existing assess, build, and migrate skills and to existing how-to and tutorial pages, and never scaffolds or fixes anything itself.\nmetadata:\n  version: 0.1.0\n  tier: universal\n  audience: beginner\n  chain: askit-explorer\n---\n\n# askit-onboard\n\n## Purpose\nOnboard a PERSON into using this toolkit well, over weeks rather than one session. Three modes:\n`assess` surveys where the adopter stands today; `plan` interviews briefly and writes a personalized\nroadmap file into the adopter's own repository, after they confirm it; `next` is the re-entry point\nthat reads that roadmap on a later visit and names one next step. Depth beyond this file lives in\n[references\u002Frouting-map.md](references\u002Frouting-map.md) (which skill or docs page answers which\nsituation) and [references\u002Froadmap-format.md](references\u002Froadmap-format.md) (the roadmap file's\nshape).\n\n## When to use\nWhen a user asks how to get started with this toolkit, wants a sequenced plan for adopting it rather\nthan reading everything at once, or returns to a repository that already has a roadmap and asks what\nis next.\n\n## The scope fence\n`askit-onboard` interviews, diagnoses, sequences, and tracks. **It routes INTO the existing skills and\ndocs pages and never duplicates their work.** It never scaffolds a component, never fixes a\ndescription, never writes a `library.json`, and never edits the adopter's skills or manifests - those\nare `askit-build-*`, `askit-migrate`, and `askit-evaluate`'s jobs. If a request is really \"fix this\" or\n\"build this now\" rather than \"where do I start\" or \"what's next\", name the skill that does it and stop;\ndo not do the work yourself. The moment this skill starts scaffolding or fixing, it has failed its own\nwhy-gate (recorded in `docs\u002Finternal\u002Fbacklog\u002Fenhancements.md`, entry E47).\n\n## Where this routes, and what it deliberately does not cover\nThis toolkit's own `docs\u002Fadoption\u002F` funnel does not exist (the nine-door design in\n`docs\u002Finternal\u002Frelease-plans\u002Fplan_onboarding-funnel\u002F` was never shipped). This skill routes only to the\npages that are actually on disk under [`docs\u002Fhow-to\u002F`](..\u002F..\u002Fdocs\u002Fhow-to\u002FREADME.md) and\n[`docs\u002Ftutorials\u002F`](..\u002F..\u002Fdocs\u002Ftutorials\u002FREADME.md), listed with their real titles in\n[references\u002Frouting-map.md](references\u002Frouting-map.md). It does not reference or imply a\n`docs\u002Fadoption\u002F` page.\n\n## assess mode\n1. Determine the adopter's repository root (the current working directory, unless the user names\n   another path).\n2. Survey it read-only: dispatch the `askit-explorer` subagent (the declared chain) when running in a\n   harness that can dispatch it; otherwise perform the walk inline with `Glob`\u002F`Grep`\u002F`Read`. Either\n   way, the question is the same: does a `library.json` exist, which component types are present and\n   where, which `agent-targets` are declared, and has the repo ever been graded.\n3. If a `library.json` exists, run `node scripts\u002Fevaluate.mjs \u003Crepo> --json` (via `askit-evaluate`) to\n   get the current tier and findings rather than re-deriving them. If none exists, report the\n   pre-manifest state the way `askit-migrate` (assess mode) does - this skill reads that state, it does\n   not write the fix.\n4. Report: current tier (or \"pre-manifest\"), component inventory, and which capability-map regions\n   (per `askit-capability-advisor` \u002F `askit-capability-gap-analysis`, if already run) the adopter has\n   and has not touched. This is the read-only survey; it produces no file.\n\n## plan mode\n1. Run (or reuse a fresh) `assess`, so the plan is grounded in the adopter's actual state rather than a\n   generic checklist.\n2. Interview briefly, in the voice of `askit-init-plugin`'s interview mode: what is the adopter trying\n   to do (ship a new plugin, migrate an existing repo, climb a tier, add one component type), how much\n   time do they have, and which of the doors in\n   [references\u002Frouting-map.md](references\u002Frouting-map.md) sound relevant. Skip questions whose answers\n   are already in context.\n3. Pick the matching doors and sequence them into an ordered roadmap: for each step, name the skill or\n   docs page that does it (never this skill), a one-line reason it is next, and what \"done\" looks like\n   for that step (reusing the done-condition style `docs\u002Finternal\u002Froadmap.md` uses for its own open\n   items).\n4. Show the adopter the roadmap and ask them to confirm before anything is written. **Only on\n   confirmation**, write it to `.askit\u002Fonboarding-roadmap.md` in the adopter's own repository, in the\n   shape [references\u002Froadmap-format.md](references\u002Froadmap-format.md) defines, so `next` mode can read\n   it back. Without confirmation, nothing is written.\n\n## next mode\n1. Read `.askit\u002Fonboarding-roadmap.md` from the adopter's repository. If it does not exist, say so and\n   suggest `plan` mode instead; `next` has nothing to re-enter without a roadmap.\n2. Find the first step not yet marked done. If the roadmap's own \"done\" condition for that step is\n   something this skill can check mechanically (a file now exists, `askit-evaluate` now reports a\n   higher tier), check it and mark completed steps along the way; otherwise ask the adopter to confirm.\n3. Name exactly one next step - the skill or docs page to go to, and why it is next - rather than\n   re-presenting the whole roadmap. Offer to re-run `plan` mode if the adopter's goals have changed\n   enough that the roadmap itself should be redone, rather than silently rewriting it here.\n\n## Scope\nClaude-only chain (`agents\u002F_chain-permitted.yaml` permits `askit-onboard` to dispatch `askit-explorer`);\nportable across Claude Code and Codex as a skill regardless, since the chain is an optional dispatch\ninside `assess` mode with an inline fallback (Standard sec 3.3). Depends on nothing that does not exist\non disk: it is sequenced after the toolkit's own docs quadrants (`docs\u002Fhow-to\u002F`, `docs\u002Ftutorials\u002F`)\nrather than after the unshipped `docs\u002Fadoption\u002F` funnel. See `docs\u002Finternal\u002Fbacklog\u002Fenhancements.md`\nentry E47 for the why-gate statement and the full delineation from `askit-init-plugin`,\n`askit-migrate`, and `askit-capability-advisor`.\n","# askit-onboard\n\n## Purpose\nOnboard a PERSON into using this toolkit well, over weeks rather than one session. Three modes:\n`assess` surveys where the adopter stands today; `plan` interviews briefly and writes a personalized\nroadmap file into the adopter's own repository, after they confirm it; `next` is the re-entry point\nthat reads that roadmap on a later visit and names one next step. Depth beyond this file lives in\n[references\u002Frouting-map.md](references\u002Frouting-map.md) (which skill or docs page answers which\nsituation) and [references\u002Froadmap-format.md](references\u002Froadmap-format.md) (the roadmap file's\nshape).\n\n## When to use\nWhen a user asks how to get started with this toolkit, wants a sequenced plan for adopting it rather\nthan reading everything at once, or returns to a repository that already has a roadmap and asks what\nis next.\n\n## The scope fence\n`askit-onboard` interviews, diagnoses, sequences, and tracks. **It routes INTO the existing skills and\ndocs pages and never duplicates their work.** It never scaffolds a component, never fixes a\ndescription, never writes a `library.json`, and never edits the adopter's skills or manifests - those\nare `askit-build-*`, `askit-migrate`, and `askit-evaluate`'s jobs. If a request is really \"fix this\" or\n\"build this now\" rather than \"where do I start\" or \"what's next\", name the skill that does it and stop;\ndo not do the work yourself. The moment this skill starts scaffolding or fixing, it has failed its own\nwhy-gate (recorded in `docs\u002Finternal\u002Fbacklog\u002Fenhancements.md`, entry E47).\n\n## Where this routes, and what it deliberately does not cover\nThis toolkit's own `docs\u002Fadoption\u002F` funnel does not exist (the nine-door design in\n`docs\u002Finternal\u002Frelease-plans\u002Fplan_onboarding-funnel\u002F` was never shipped). This skill routes only to the\npages that are actually on disk under [`docs\u002Fhow-to\u002F`](..\u002F..\u002Fdocs\u002Fhow-to\u002FREADME.md) and\n[`docs\u002Ftutorials\u002F`](..\u002F..\u002Fdocs\u002Ftutorials\u002FREADME.md), listed with their real titles in\n[references\u002Frouting-map.md](references\u002Frouting-map.md). It does not reference or imply a\n`docs\u002Fadoption\u002F` page.\n\n## assess mode\n1. Determine the adopter's repository root (the current working directory, unless the user names\n   another path).\n2. Survey it read-only: dispatch the `askit-explorer` subagent (the declared chain) when running in a\n   harness that can dispatch it; otherwise perform the walk inline with `Glob`\u002F`Grep`\u002F`Read`. Either\n   way, the question is the same: does a `library.json` exist, which component types are present and\n   where, which `agent-targets` are declared, and has the repo ever been graded.\n3. If a `library.json` exists, run `node scripts\u002Fevaluate.mjs \u003Crepo> --json` (via `askit-evaluate`) to\n   get the current tier and findings rather than re-deriving them. If none exists, report the\n   pre-manifest state the way `askit-migrate` (assess mode) does - this skill reads that state, it does\n   not write the fix.\n4. Report: current tier (or \"pre-manifest\"), component inventory, and which capability-map regions\n   (per `askit-capability-advisor` \u002F `askit-capability-gap-analysis`, if already run) the adopter has\n   and has not touched. This is the read-only survey; it produces no file.\n\n## plan mode\n1. Run (or reuse a fresh) `assess`, so the plan is grounded in the adopter's actual state rather than a\n   generic checklist.\n2. Interview briefly, in the voice of `askit-init-plugin`'s interview mode: what is the adopter trying\n   to do (ship a new plugin, migrate an existing repo, climb a tier, add one component type), how much\n   time do they have, and which of the doors in\n   [references\u002Frouting-map.md](references\u002Frouting-map.md) sound relevant. Skip questions whose answers\n   are already in context.\n3. Pick the matching doors and sequence them into an ordered roadmap: for each step, name the skill or\n   docs page that does it (never this skill), a one-line reason it is next, and what \"done\" looks like\n   for that step (reusing the done-condition style `docs\u002Finternal\u002Froadmap.md` uses for its own open\n   items).\n4. Show the adopter the roadmap and ask them to confirm before anything is written. **Only on\n   confirmation**, write it to `.askit\u002Fonboarding-roadmap.md` in the adopter's own repository, in the\n   shape [references\u002Froadmap-format.md](references\u002Froadmap-format.md) defines, so `next` mode can read\n   it back. Without confirmation, nothing is written.\n\n## next mode\n1. Read `.askit\u002Fonboarding-roadmap.md` from the adopter's repository. If it does not exist, say so and\n   suggest `plan` mode instead; `next` has nothing to re-enter without a roadmap.\n2. Find the first step not yet marked done. If the roadmap's own \"done\" condition for that step is\n   something this skill can check mechanically (a file now exists, `askit-evaluate` now reports a\n   higher tier), check it and mark completed steps along the way; otherwise ask the adopter to confirm.\n3. Name exactly one next step - the skill or docs page to go to, and why it is next - rather than\n   re-presenting the whole roadmap. Offer to re-run `plan` mode if the adopter's goals have changed\n   enough that the roadmap itself should be redone, rather than silently rewriting it here.\n\n## Scope\nClaude-only chain (`agents\u002F_chain-permitted.yaml` permits `askit-onboard` to dispatch `askit-explorer`);\nportable across Claude Code and Codex as a skill regardless, since the chain is an optional dispatch\ninside `assess` mode with an inline fallback (Standard sec 3.3). Depends on nothing that does not exist\non disk: it is sequenced after the toolkit's own docs quadrants (`docs\u002Fhow-to\u002F`, `docs\u002Ftutorials\u002F`)\nrather than after the unshipped `docs\u002Fadoption\u002F` funnel. See `docs\u002Finternal\u002Fbacklog\u002Fenhancements.md`\nentry E47 for the why-gate statement and the full delineation from `askit-init-plugin`,\n`askit-migrate`, and `askit-capability-advisor`.\n",{"name":5,"metadata":24,"description":7},{"tier":25,"chain":26,"version":27,"audience":28},"universal","askit-explorer","0.1.0","beginner","main","b0a696723b1155d08503a8441c981998f9d13c34","skills\u002Faskit-onboard",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":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add product-on-purpose\u002Fagent-skills-toolkit --skill askit-onboard",{"tool":43,"command":44},"bunx","bunx skills add product-on-purpose\u002Fagent-skills-toolkit --skill askit-onboard",{"tool":46,"command":47},"pnpm","pnpm dlx skills add product-on-purpose\u002Fagent-skills-toolkit --skill askit-onboard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-onboard\u002FSKILL.md",true,[51,57,61,65,69],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"evals\u002Faskit-onboard-triggering.eval.json","REFERENCE","参考文档",3147,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-onboard\u002Fevals\u002Faskit-onboard-triggering.eval.json",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"evals\u002FREADME.md",735,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-onboard\u002Fevals\u002FREADME.md",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"README.md",920,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-onboard\u002FREADME.md",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Froadmap-format.md",1891,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-onboard\u002Freferences\u002Froadmap-format.md",{"path":70,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Frouting-map.md",4835,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fagent-skills-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Faskit-onboard\u002Freferences\u002Frouting-map.md",[74,81,86,91,98,105],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":76,"nameZh":6,"description":77,"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},"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":87,"name":76,"nameZh":6,"description":77,"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},"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":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},"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":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},"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"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",[],[]]