[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CYBHBHB2DGNMSAAAP8ZCDT":3,"skill-same:01M7CYBHBHB2DGNMSAAAP8ZCDT":48},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7CYBHBHB2DGNMSAAAP8ZCDT","feature-explore",null,"Interviews for the problem behind a new Umbraco feature or package: what, for whom, why, and what's out of scope, written to BRIEF.md. Use when starting a feature, package or add-on, or when a request is too vague to design yet.","mattbrailsford\u002Fumbraco-devkit","mattbrailsford","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F527305?v=4","01M7CY974D4XX1P90YSXQC1T39","Matt Brailsford","01M7CY9751PSRA3EHBH03G936J",3,"MIT","https:\u002F\u002Fgithub.com\u002Fmattbrailsford\u002Fumbraco-devkit\u002Fblob\u002Fmain\u002Fplugins\u002Fumbraco-devkit\u002Fskills\u002Ffeature-explore\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: feature-explore\ndescription: >-\n  Interviews for the problem behind a new Umbraco feature or package: what, for whom, why,\n  and what's out of scope, written to BRIEF.md. Use when starting a feature, package or\n  add-on, or when a request is too vague to design yet.\nuser-invocable: true\nargument-hint: \"[one-line idea, optional]\"\n---\n\n# feature-explore\n\nThink through an idea before touching the solution space. By the end, the feature's `BRIEF.md`\nsays what's being built and for whom, honestly including what isn't known yet.\n\n## Where this writes\n\nThe project's per-feature plan folder — see the root `CLAUDE.md` for the path convention\n(default `docs\u002Fplans\u002F\u003Cfeature-slug>\u002F`; a monorepo or worktree-based project may scope it\ndifferently). If no convention is written down anywhere, ask once, then propose one and add it\nto `CLAUDE.md` so the next phase doesn't have to ask again.\n\nOwns exactly one file: `BRIEF.md`. Never edit `ARCHITECTURE.md`, `SPEC.md`, `STORIES.md`,\n`PLAN.md`, or `BUILD-LOG.md` — those belong to later phases.\n\n**Also creates `README.md`, the folder's read-order index — the one time any phase creates\nit.** Every later phase updates its own line in this file when it finishes (same append-only\ndiscipline as `DECISION-LOG.md`): never recreate it if it already exists, and never edit a line\nthat isn't `BRIEF.md`'s own.\n\n**Stays uncommitted, stays on trunk.** `feature-explore` never runs `git commit`, never creates a\nbranch. The plan folder is just plain files on disk until `feature-build` decides the feature\nis actually being built — see \"Branch\u002Fworktree per feature\" in `git-workflow` for why. If the\nfeature never gets built, nothing ever touched git history.\n\n**Why one file per phase, not one shared doc:** re-running a phase must never silently\noverwrite another phase's decisions, and two files can't collide the way two sections in one\nshared file can — a phase editing its own file is safe to run concurrently with another phase\n(or another session) touching a different one. If a project already has its own plan-folder\nconvention, match it for consistency, but keep the same discipline (one owner per file) rather\nthan going fully freeform.\n\n## Scope\n\n- IN: the problem, the user (an editor? a developer integrating the package? an end site\n  visitor?), the why-now, in\u002Fout scope, what success looks like, unknowns, light research\n  where a fact is needed to proceed.\n- OUT: architecture, CMS extension points to use, data model, package structure — all\n  `feature-design`. If a solution idea comes up mid-interview, pass it on in the hand-off\n  for `feature-design` rather than deciding it here or writing it into the brief.\n\n## Preflight\n\n1. Resolve which feature this run is for. If more than one plan folder exists, prefer a match\n   between the current branch\u002Fworktree name and a folder name (see `CLAUDE.md`'s \"Finding the\n   current feature's plan folder\" rule) — this is the normal case for a refinement run once\n   `feature-build` has started. If nothing matches and only one plan folder exists, or the\n   argument names a brand-new idea, use that instead; ask only if it's still ambiguous. If\n   the argument is a tracker issue (title, body, triage findings, repro, notes), treat it as\n   a brand-new feature and use it to answer interview questions up front. A bug's repro goes\n   in `BRIEF.md`'s `Repro` section. If the argument is an idea file (see `CLAUDE.md`'s\n   \"Ideas\"), treat it the same way: it's a brand-new feature, and the idea answers questions\n   up front. An idea can cover more than one feature, so ask which part this one builds.\n   Refer to the idea by its name alone, never its path (see \"Ideas\").\n   If\n   `BRIEF.md` already exists in the resolved folder, read it. Summarize current state in 1–2\n   lines (\"problem defined, no success metric yet\"). Re-entrant: refine, don't restart. **Skip\n   step 2 below** when refining an existing `BRIEF.md`.\n2. **Only for a brand-new feature (no `BRIEF.md` yet):** confirm the current branch is the\n   project's trunk branch (see `CLAUDE.md`'s Feature workflow section; default the repo's\n   default branch). If it isn't, stop and tell the user — starting a new plan folder from an\n   unrelated branch is how plan folders end up scattered across branches they don't belong to.\n   Let them override if they confirm it's intentional (e.g. planning a sub-feature inside a\n   monorepo product's own long-lived line). Also check the archive (see `CLAUDE.md`'s\n   \"Feature workflow\" section) for a closed plan with the same slug. If one exists, pick a\n   different slug: the slug is also the branch name, and an archived plan's links and PR\n   still use it.\n3. Read the project's `CLAUDE.md` and any existing architecture docs for prior context —\n   don't re-litigate a decision already on record.\n4. If this is a package\u002Fadd-on (not a feature inside an existing product), check whether it's\n   extending an existing Umbraco extension point (property editor, dashboard, content app,\n   notification handler) or introducing a new one — that framing shapes several of the\n   interview questions below.\n5. Check `BRIEF.md` and `README.md` for open review comments, following `markdown-preview`'s\n   \"Open comments on your files\". Each one is input to this run.\n\n## Assume, then show\n\nNot every topic below needs a spoken question. Before asking:\n\n1. **Check whether it's a checkable fact** — does Umbraco core already expose this, how does\n   a sibling package handle it — and go find it instead of asking.\n2. **If it's a judgment call and a wrong guess is cheap to correct once it's written down**\n   (a scope boundary, a success metric, the smallest shippable slice), write it as a guess in\n   the list at the top of `BRIEF.md` instead of asking, and let the human correct it when they\n   read the brief. Correcting a written-down guess costs them a\n   sentence; answering a live question costs them a context switch.\n3. **Ask directly only when a wrong guess is expensive to undo here** — which CMS version(s)\n   to support (locks in a compatibility promise you'd have to walk back), or anything only the\n   human can actually know (why this, now; what would kill it).\n\nThis doesn't relax \"stop, don't guess\" — that rule is about a phase's *required input* being\nmissing (no prior phase's file to read). This is about which of *this* phase's own questions\nyou put to the human versus answer yourself and show your work.\n\n## Interview\n\nUp to ~10 questions, adaptive — only ask what's missing **and fails the filter above**. Batch\nwhat's left (4 at a time, 2–3 rounds, not an interrogation):\n\n1. What problem, concretely? What does an editor\u002Fdeveloper do today without it?\n2. Who is it for? Backoffice editors, developers consuming the package, front-end site\n   visitors, or some mix? Who is explicitly *not* the audience?\n3. Why now?\n4. What's explicitly **out** of scope?\n5. What does success look like — observable, ideally measurable?\n6. Hard constraints: which Umbraco CMS version(s) must this support? Any locked\n   dependencies?\n7. What's the riskiest unknown — a CMS API that might not do what's assumed, a UUI\n   component that might not exist yet, a performance ceiling?\n8. What's the smallest version that's still worth shipping?\n9. Is this replacing or extending something that already exists in Umbraco core or another\n   package?\n10. What would make you kill this?\n\nDo targeted research only when an answer hinges on a checkable fact (e.g. does Umbraco core\nalready expose the extension point this needs). Check Umbraco's docs with `umbraco-docs`\nand the CMS itself with `umbraco-cms-source`.\n\n## Produce\n\nWrite every file this phase produces following `plain-writing`: a person reads it before the\nnext phase runs, so it should be quick to read without leaving anything out.\n\n**First run only (`README.md` doesn't exist yet):** create it as the folder's index. Rows\nrun in read order:\n\n```md\n# \u003CFeature name>\n\n| File | In one line | Needs you |\n|---|---|---|\n| ⬜ [Brief](.\u002FBRIEF.md) | | |\n| ⬜ [Architecture](.\u002FARCHITECTURE.md) | | |\n| ⬜ [Spec](.\u002FSPEC.md) | | |\n| ⬜ [Stories](.\u002FSTORIES.md) | | |\n| ⬜ [Plan](.\u002FPLAN.md) | | |\n\nWhat was built: [BUILD-LOG.md](.\u002FBUILD-LOG.md) · Why things changed: [DECISION-LOG.md](.\u002FDECISION-LOG.md)\n```\n\nEvery run (first run or a refinement), update only the Brief row: `⬜` becomes `✅`, \"In one\nline\" gets the problem in a few words (the table has to fit a phone), and \"Needs you\" gets\nthe count from the top of `BRIEF.md` (\"2 guesses\", \"1 open question\"), or stays empty. Never\ntouch another phase's row. A folder from before this layout has a numbered list instead:\nupdate your own line in it the same way, and don't convert the list.\n\nWhen revising an existing `BRIEF.md`, rewrite the affected sections to reflect the current\nunderstanding only — don't leave the old answer in place alongside a note about what\nchanged. This file is a snapshot of the current problem definition, not a changelog. Past\nanswers and why they changed belong in `DECISION-LOG.md`.\n\nWrite\u002Fupdate `BRIEF.md`. It says why and for whom, never how: anything about extension\npoints, tables or screens belongs to `feature-design`.\n\n```md\n# Brief: \u003Cfeature name>\n\n\u003COne or two sentences: the problem, and who has it.>\n\nSource idea: `\u003Cidea-name>`, \u003Cwhich part of it this feature builds>\n\u003Conly when the feature started from an idea. Leave the line out otherwise.>\n\n> [!IMPORTANT]\n> **\u003CN> guesses need your OK.**\n>\n> 1. \u003Cthe guess>\\\n>    *If not:* \u003Cwhat changes>\n> 2. **Open:** \u003Ca question with no sensible guess>\\\n>    *Options:* \u003Cthe choices>\n\n\u003CPer `plain-writing`'s \"What needs the reader goes first\". Count questions in the heading\ntoo (\"2 guesses and 1 open question need you\"). Leave the callout out when there's nothing.\nEvery guess goes here, whichever section it's about: a guessed measure under \"Done when\", a\nconstraint under \"Must work with\", an item under \"Not doing\", a likely answer to an\n\"Unknowns\" line. The section below may point to\nit (\"see guess 3\") but never states a guess of its own, marked \"(guess)\" or \"assumed\" or not.\nOne callout item per guess, never one item saying a whole section is guessed.>\n\n## Why now\n- \u003Cone reason per line, as given. No reason given is an open question in the callout.>\n\n## Done when\n- \u003Cwhat the user can observably do, ideally measurable>\n\n## Must work with\n- \u003CCMS versions, databases, hosting such as load balancing, locked dependencies, as given.>\n\n## Unknowns\n- \u003Cwhat might not work as hoped, for `feature-design` to check first. Leave out if none.>\n\n## Not doing\n- **\u003Citem>.** \u003Cwhy. Only what the human ruled out. A cut you'd add yourself is a guess.>\n\n## Repro\n\u003Conly for a reported bug: the steps or test that show it. The finished work must make it\npass. Leave the section out otherwise.>\n```\n\nAppend a dated entry to `DECISION-LOG.md` for anything decided here worth remembering later\n(a scope cut, a killed alternative), one line each with the why. If a decision is project-wide\nrather than scoped to this feature (a constraint that will bind every future feature too, not\njust this one), write it to `.claude\u002Fmemory\u002F` instead (type: `decision`) — see\n`.claude\u002Fmemory\u002FREADME.md` for the format.\n\n## Hand off\n\nState any open question still in the brief. Offer to open `BRIEF.md` in a live preview,\nfollowing `markdown-preview`'s \"Offering a preview\". With a preview open, ask for approval on\n`BRIEF.md`, following its \"Approval\". Then: `Suggested next: \u002Fclear, then feature-design\n\u003Cfeature-slug> — or re-run feature-explore to close open questions first.` Everything the\nnext phase needs is in the plan folder, so a fresh session loses nothing and starts the next\nphase with room to work.\n","# feature-explore\n\nThink through an idea before touching the solution space. By the end, the feature's `BRIEF.md`\nsays what's being built and for whom, honestly including what isn't known yet.\n\n## Where this writes\n\nThe project's per-feature plan folder — see the root `CLAUDE.md` for the path convention\n(default `docs\u002Fplans\u002F\u003Cfeature-slug>\u002F`; a monorepo or worktree-based project may scope it\ndifferently). If no convention is written down anywhere, ask once, then propose one and add it\nto `CLAUDE.md` so the next phase doesn't have to ask again.\n\nOwns exactly one file: `BRIEF.md`. Never edit `ARCHITECTURE.md`, `SPEC.md`, `STORIES.md`,\n`PLAN.md`, or `BUILD-LOG.md` — those belong to later phases.\n\n**Also creates `README.md`, the folder's read-order index — the one time any phase creates\nit.** Every later phase updates its own line in this file when it finishes (same append-only\ndiscipline as `DECISION-LOG.md`): never recreate it if it already exists, and never edit a line\nthat isn't `BRIEF.md`'s own.\n\n**Stays uncommitted, stays on trunk.** `feature-explore` never runs `git commit`, never creates a\nbranch. The plan folder is just plain files on disk until `feature-build` decides the feature\nis actually being built — see \"Branch\u002Fworktree per feature\" in `git-workflow` for why. If the\nfeature never gets built, nothing ever touched git history.\n\n**Why one file per phase, not one shared doc:** re-running a phase must never silently\noverwrite another phase's decisions, and two files can't collide the way two sections in one\nshared file can — a phase editing its own file is safe to run concurrently with another phase\n(or another session) touching a different one. If a project already has its own plan-folder\nconvention, match it for consistency, but keep the same discipline (one owner per file) rather\nthan going fully freeform.\n\n## Scope\n\n- IN: the problem, the user (an editor? a developer integrating the package? an end site\n  visitor?), the why-now, in\u002Fout scope, what success looks like, unknowns, light research\n  where a fact is needed to proceed.\n- OUT: architecture, CMS extension points to use, data model, package structure — all\n  `feature-design`. If a solution idea comes up mid-interview, pass it on in the hand-off\n  for `feature-design` rather than deciding it here or writing it into the brief.\n\n## Preflight\n\n1. Resolve which feature this run is for. If more than one plan folder exists, prefer a match\n   between the current branch\u002Fworktree name and a folder name (see `CLAUDE.md`'s \"Finding the\n   current feature's plan folder\" rule) — this is the normal case for a refinement run once\n   `feature-build` has started. If nothing matches and only one plan folder exists, or the\n   argument names a brand-new idea, use that instead; ask only if it's still ambiguous. If\n   the argument is a tracker issue (title, body, triage findings, repro, notes), treat it as\n   a brand-new feature and use it to answer interview questions up front. A bug's repro goes\n   in `BRIEF.md`'s `Repro` section. If the argument is an idea file (see `CLAUDE.md`'s\n   \"Ideas\"), treat it the same way: it's a brand-new feature, and the idea answers questions\n   up front. An idea can cover more than one feature, so ask which part this one builds.\n   Refer to the idea by its name alone, never its path (see \"Ideas\").\n   If\n   `BRIEF.md` already exists in the resolved folder, read it. Summarize current state in 1–2\n   lines (\"problem defined, no success metric yet\"). Re-entrant: refine, don't restart. **Skip\n   step 2 below** when refining an existing `BRIEF.md`.\n2. **Only for a brand-new feature (no `BRIEF.md` yet):** confirm the current branch is the\n   project's trunk branch (see `CLAUDE.md`'s Feature workflow section; default the repo's\n   default branch). If it isn't, stop and tell the user — starting a new plan folder from an\n   unrelated branch is how plan folders end up scattered across branches they don't belong to.\n   Let them override if they confirm it's intentional (e.g. planning a sub-feature inside a\n   monorepo product's own long-lived line). Also check the archive (see `CLAUDE.md`'s\n   \"Feature workflow\" section) for a closed plan with the same slug. If one exists, pick a\n   different slug: the slug is also the branch name, and an archived plan's links and PR\n   still use it.\n3. Read the project's `CLAUDE.md` and any existing architecture docs for prior context —\n   don't re-litigate a decision already on record.\n4. If this is a package\u002Fadd-on (not a feature inside an existing product), check whether it's\n   extending an existing Umbraco extension point (property editor, dashboard, content app,\n   notification handler) or introducing a new one — that framing shapes several of the\n   interview questions below.\n5. Check `BRIEF.md` and `README.md` for open review comments, following `markdown-preview`'s\n   \"Open comments on your files\". Each one is input to this run.\n\n## Assume, then show\n\nNot every topic below needs a spoken question. Before asking:\n\n1. **Check whether it's a checkable fact** — does Umbraco core already expose this, how does\n   a sibling package handle it — and go find it instead of asking.\n2. **If it's a judgment call and a wrong guess is cheap to correct once it's written down**\n   (a scope boundary, a success metric, the smallest shippable slice), write it as a guess in\n   the list at the top of `BRIEF.md` instead of asking, and let the human correct it when they\n   read the brief. Correcting a written-down guess costs them a\n   sentence; answering a live question costs them a context switch.\n3. **Ask directly only when a wrong guess is expensive to undo here** — which CMS version(s)\n   to support (locks in a compatibility promise you'd have to walk back), or anything only the\n   human can actually know (why this, now; what would kill it).\n\nThis doesn't relax \"stop, don't guess\" — that rule is about a phase's *required input* being\nmissing (no prior phase's file to read). This is about which of *this* phase's own questions\nyou put to the human versus answer yourself and show your work.\n\n## Interview\n\nUp to ~10 questions, adaptive — only ask what's missing **and fails the filter above**. Batch\nwhat's left (4 at a time, 2–3 rounds, not an interrogation):\n\n1. What problem, concretely? What does an editor\u002Fdeveloper do today without it?\n2. Who is it for? Backoffice editors, developers consuming the package, front-end site\n   visitors, or some mix? Who is explicitly *not* the audience?\n3. Why now?\n4. What's explicitly **out** of scope?\n5. What does success look like — observable, ideally measurable?\n6. Hard constraints: which Umbraco CMS version(s) must this support? Any locked\n   dependencies?\n7. What's the riskiest unknown — a CMS API that might not do what's assumed, a UUI\n   component that might not exist yet, a performance ceiling?\n8. What's the smallest version that's still worth shipping?\n9. Is this replacing or extending something that already exists in Umbraco core or another\n   package?\n10. What would make you kill this?\n\nDo targeted research only when an answer hinges on a checkable fact (e.g. does Umbraco core\nalready expose the extension point this needs). Check Umbraco's docs with `umbraco-docs`\nand the CMS itself with `umbraco-cms-source`.\n\n## Produce\n\nWrite every file this phase produces following `plain-writing`: a person reads it before the\nnext phase runs, so it should be quick to read without leaving anything out.\n\n**First run only (`README.md` doesn't exist yet):** create it as the folder's index. Rows\nrun in read order:\n\n```md\n# \u003CFeature name>\n\n| File | In one line | Needs you |\n|---|---|---|\n| ⬜ [Brief](.\u002FBRIEF.md) | | |\n| ⬜ [Architecture](.\u002FARCHITECTURE.md) | | |\n| ⬜ [Spec](.\u002FSPEC.md) | | |\n| ⬜ [Stories](.\u002FSTORIES.md) | | |\n| ⬜ [Plan](.\u002FPLAN.md) | | |\n\nWhat was built: [BUILD-LOG.md](.\u002FBUILD-LOG.md) · Why things changed: [DECISION-LOG.md](.\u002FDECISION-LOG.md)\n```\n\nEvery run (first run or a refinement), update only the Brief row: `⬜` becomes `✅`, \"In one\nline\" gets the problem in a few words (the table has to fit a phone), and \"Needs you\" gets\nthe count from the top of `BRIEF.md` (\"2 guesses\", \"1 open question\"), or stays empty. Never\ntouch another phase's row. A folder from before this layout has a numbered list instead:\nupdate your own line in it the same way, and don't convert the list.\n\nWhen revising an existing `BRIEF.md`, rewrite the affected sections to reflect the current\nunderstanding only — don't leave the old answer in place alongside a note about what\nchanged. This file is a snapshot of the current problem definition, not a changelog. Past\nanswers and why they changed belong in `DECISION-LOG.md`.\n\nWrite\u002Fupdate `BRIEF.md`. It says why and for whom, never how: anything about extension\npoints, tables or screens belongs to `feature-design`.\n\n```md\n# Brief: \u003Cfeature name>\n\n\u003COne or two sentences: the problem, and who has it.>\n\nSource idea: `\u003Cidea-name>`, \u003Cwhich part of it this feature builds>\n\u003Conly when the feature started from an idea. Leave the line out otherwise.>\n\n> [!IMPORTANT]\n> **\u003CN> guesses need your OK.**\n>\n> 1. \u003Cthe guess>\\\n>    *If not:* \u003Cwhat changes>\n> 2. **Open:** \u003Ca question with no sensible guess>\\\n>    *Options:* \u003Cthe choices>\n\n\u003CPer `plain-writing`'s \"What needs the reader goes first\". Count questions in the heading\ntoo (\"2 guesses and 1 open question need you\"). Leave the callout out when there's nothing.\nEvery guess goes here, whichever section it's about: a guessed measure under \"Done when\", a\nconstraint under \"Must work with\", an item under \"Not doing\", a likely answer to an\n\"Unknowns\" line. The section below may point to\nit (\"see guess 3\") but never states a guess of its own, marked \"(guess)\" or \"assumed\" or not.\nOne callout item per guess, never one item saying a whole section is guessed.>\n\n## Why now\n- \u003Cone reason per line, as given. No reason given is an open question in the callout.>\n\n## Done when\n- \u003Cwhat the user can observably do, ideally measurable>\n\n## Must work with\n- \u003CCMS versions, databases, hosting such as load balancing, locked dependencies, as given.>\n\n## Unknowns\n- \u003Cwhat might not work as hoped, for `feature-design` to check first. Leave out if none.>\n\n## Not doing\n- **\u003Citem>.** \u003Cwhy. Only what the human ruled out. A cut you'd add yourself is a guess.>\n\n## Repro\n\u003Conly for a reported bug: the steps or test that show it. The finished work must make it\npass. Leave the section out otherwise.>\n```\n\nAppend a dated entry to `DECISION-LOG.md` for anything decided here worth remembering later\n(a scope cut, a killed alternative), one line each with the why. If a decision is project-wide\nrather than scoped to this feature (a constraint that will bind every future feature too, not\njust this one), write it to `.claude\u002Fmemory\u002F` instead (type: `decision`) — see\n`.claude\u002Fmemory\u002FREADME.md` for the format.\n\n## Hand off\n\nState any open question still in the brief. Offer to open `BRIEF.md` in a live preview,\nfollowing `markdown-preview`'s \"Offering a preview\". With a preview open, ask for approval on\n`BRIEF.md`, following its \"Approval\". Then: `Suggested next: \u002Fclear, then feature-design\n\u003Cfeature-slug> — or re-run feature-explore to close open questions first.` Everything the\nnext phase needs is in the plan folder, so a fresh session loses nothing and starts the next\nphase with room to work.\n",{"name":5,"description":7,"argument-hint":24,"user-invocable":25},"[one-line idea, optional]",true,"main","a2f9c28bc56802b4e6db01e03972e497b30ad001","plugins\u002Fumbraco-devkit\u002Fskills\u002Ffeature-explore",1,"https:\u002F\u002Fgithub.com\u002Fmattbrailsford\u002Fumbraco-devkit","https:\u002F\u002Fgithub.com\u002Fmattbrailsford","https:\u002F\u002Fmattbrailsford.dev","AI Staff Engineer @umbraco ","2026-11-12 18:33:53",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":25},[37,40,43],{"tool":38,"command":39},"npx","npx skills add mattbrailsford\u002Fumbraco-devkit --skill feature-explore",{"tool":41,"command":42},"bunx","bunx skills add mattbrailsford\u002Fumbraco-devkit --skill feature-explore",{"tool":44,"command":45},"pnpm","pnpm dlx skills add mattbrailsford\u002Fumbraco-devkit --skill feature-explore","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmattbrailsford\u002Fumbraco-devkit\u002Fblob\u002Fmain\u002Fplugins\u002Fumbraco-devkit\u002Fskills\u002Ffeature-explore\u002FSKILL.md",[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7CYGRPVNP8H9YNHGMZ6CP3C","user-stories","Writes, splits and refines user stories with Given\u002FWhen\u002FThen acceptance criteria in STORIES.md, feeding bdd-specs. Use when turning a feature request or a vague ask into a testable backlog entry.","https:\u002F\u002Fgithub.com\u002Fmattbrailsford\u002Fumbraco-devkit\u002Fblob\u002Fmain\u002Fplugins\u002Fumbraco-devkit\u002Fskills\u002Fuser-stories\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7CYGJB26N83DXKMDEKY2X48","umbraco-security","What Umbraco provides for keeping a package secure, on the server and in the backoffice: Management API authorization and policies, settings that hold secrets, endpoints outside the Management API, sanitizeHTML and escapeHTML, DOMPurify rules for custom elements, and umbHttpClient instead of handling tokens in the browser. Use when writing or reviewing a Management API controller, a secret setting, a custom endpoint, a backoffice template that uses unsafeHTML, or frontend code that calls an API.","https:\u002F\u002Fgithub.com\u002Fmattbrailsford\u002Fumbraco-devkit\u002Fblob\u002Fmain\u002Fplugins\u002Fumbraco-devkit\u002Fskills\u002Fumbraco-security\u002FSKILL.md",[],[],{"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},"01M7CYGBEZ2Q4AXDDNADWW4Q9H","umbraco-performance","Keeping a package fast on the sites that install it: the published cache over the services layer, tree traversal, caching lookups and clearing them, data type config and converter cache levels, output cache eviction, light hot paths, and backoffice screens that don't over-fetch. Use when writing, changing or reviewing code that runs per request, per save, per indexed item or at startup (property value converters, notification handlers, indexing), code that loops over every content item (a full rebuild, an import, a sync), or a list or search screen. Not for a site's own templates.","https:\u002F\u002Fgithub.com\u002Fmattbrailsford\u002Fumbraco-devkit\u002Fblob\u002Fmain\u002Fplugins\u002Fumbraco-devkit\u002Fskills\u002Fumbraco-performance\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},"01M7CYG59CZN1K2KERB0SSDGSY","umbraco-package-conventions","Backend conventions for an Umbraco package: async naming, internal by default, Attempt-based results for routine failures, public-API backwards compatibility, and where extension methods live. Use when naming a method, choosing visibility, shaping a service's result, changing a public signature (including adding a dependency to a public class's constructor), or organizing extension methods. For extension mechanisms, see `umbraco-extensibility`.","https:\u002F\u002Fgithub.com\u002Fmattbrailsford\u002Fumbraco-devkit\u002Fblob\u002Fmain\u002Fplugins\u002Fumbraco-devkit\u002Fskills\u002Fumbraco-package-conventions\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},"01M7CYG0J10QH8J2GS825WTTET","umbraco-marketplace","Gets a finished package listed on the Umbraco Marketplace: the NuGet tag, the dependency Marketplace reads version support from, the v14+ compatibility gotcha, and umbraco-marketplace.json. Use when a package is ready to publish, or when reviewing its packaging.","https:\u002F\u002Fgithub.com\u002Fmattbrailsford\u002Fumbraco-devkit\u002Fblob\u002Fmain\u002Fplugins\u002Fumbraco-devkit\u002Fskills\u002Fumbraco-marketplace\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},"01M7CYFT7MSYW4GRDSQRDPG020","umbraco-extensibility","Umbraco's extension mechanisms (Composers, collection builders, notification handlers, attribute discovery) and a catalogue of backend CMS extension points: property value converters, Management API endpoints, content finders, health checks, search indexing, package migrations, background jobs, and more. Use when making a feature extensible or choosing which extension point fits. Not for property editor UI, dashboards, sections or trees, which the official Backoffice Skills plugin covers.","https:\u002F\u002Fgithub.com\u002Fmattbrailsford\u002Fumbraco-devkit\u002Fblob\u002Fmain\u002Fplugins\u002Fumbraco-devkit\u002Fskills\u002Fumbraco-extensibility\u002FSKILL.md",[],[]]