[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CYAHA1E8QJ9194AP7W5GHM":3,"skill-same:01M7CYAHA1E8QJ9194AP7W5GHM":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},"01M7CYAHA1E8QJ9194AP7W5GHM","decision-review",null,"Lists what a human should check after a build: the builder's assumptions, spec deviations, workarounds and judgment calls. Read-only. pr-describe runs it for every PR; run it by hand for an earlier look. Use when asked what decisions were made, what to check, or what needs attention on a finished build.","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\u002Fdecision-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: decision-review\ndescription: >-\n  Lists what a human should check after a build: the builder's assumptions, spec deviations,\n  workarounds and judgment calls. Read-only. pr-describe runs it for every PR; run it by\n  hand for an earlier look. Use when asked what decisions were made, what to check, or what\n  needs attention on a finished build.\nuser-invocable: true\nargument-hint: \"[path to the feature's plan folder, optional]\"\n---\n\n# decision-review\n\n`feature-build` runs unsupervised across many tasks. Each `builder` dispatch reports back\n\"any decision the plan left implicit that it had to make,\" and the loop logs those to\n`DECISION-LOG.md` (see that skill's step 6). In a fully autonomous run, the PR is the one\ncheckpoint guaranteed to get a human look, so `pr-describe` always invokes this skill while\nwriting that PR — nobody has to remember to trigger a separate review step. This skill doesn't\ndecide anything itself; it decides what's worth *the user's* attention and hands back a short,\nranked list.\n\n## Scope\n\n- IN: read `DECISION-LOG.md`, `BUILD-LOG.md`, and the feature's diff since it branched from\n  trunk; surface the subset worth a human's eyes; rank them.\n- OUT: fixing anything (no `Edit`\u002F`Write` needed — this is a report), gating a commit (that's\n  `reviewer`'s job, already done per task inside the loop), writing the PR description (that's\n  `pr-describe` — hand this skill's output to its \"Your call\" callout instead of duplicating\n  the digest in a second file).\n\n## Preflight\n\n1. Resolve the plan folder: the path given in the argument; else match the current\n   branch\u002Fworktree name against a plan folder the way `feature-build` does (see the project's\n   `CLAUDE.md`); else stop and ask.\n2. Confirm `BUILD-LOG.md` has at least one entry. If it's empty or missing, nothing has been\n   built yet — say so and stop rather than reviewing an empty diff.\n\n## What counts as worth surfacing\n\nFlag something only if a different, equally reasonable choice existed and the outcome could\nplausibly matter to the person who owns the feature. Five categories:\n\n- **Assumption** — filled a gap the plan or spec left open, without asking.\n- **Deviation** — the implementation does something other than what `SPEC.md` or\n  `ARCHITECTURE.md` says it does.\n- **Workaround** — routed around a bug, a missing dependency, a CMS-version gap, or a flaky\n  test, instead of a clean fix. (A weakened or skipped spec is already an automatic `reviewer`\n  `FAIL` inside the loop, so a surviving one here means it slipped through — call that out\n  as the top-priority item, not just another workaround.)\n- **Judgment call** — ambiguous plan wording resolved one way among several defensible ones.\n- **Addition** — built something `SPEC.md` and `ARCHITECTURE.md` never mention. The spec is\n  still met, so nothing reads as a deviation, but nobody asked for it.\n\nSome changes are always worth a look, logged or not, even when the spec is met:\n\n- a new database table or migration\n- a new package dependency\n- a change to the public API: a type or member added, removed, renamed, or made internal\n- a new notification handler, background job, or scheduled task\n- a new setting\n- a new extension point or manifest type\n- behavior that runs outside the feature's own screen or endpoint\n\nSkip pure implementation mechanics — variable names, which loop construct, formatting, file\nlayout inside an already-agreed extension point. Nobody needs to sign off on those.\n\n## Workflow\n\n1. Read `DECISION-LOG.md` end to end. Keep only entries timestamped from this feature's build\n   phase (from when `feature-build` cut the branch onward). Earlier entries belong to\n   `feature-explore`\u002F`feature-design`\u002F`feature-plan` — the user already weighed in during those phases'\n   interviews; don't re-surface settled ground. Drop build entries marked `user` too: the user\n   made that call during the build.\n2. Read `BUILD-LOG.md` for what each task claimed to verify, as context for the entries above.\n3. Read the full diff since the branch point (`git diff \u003Cbase>...HEAD`), with enough\n   surrounding code to judge each flagged item in context, not just the changed lines.\n4. Cross-check the diff against `SPEC.md`\u002F`ARCHITECTURE.md` for anything that reads as a\n   deviation but was never logged — the builder is supposed to report these, but this step\n   catches what leaked through rather than trusting the log is complete. Then go through the\n   diff for every change on the always-worth-a-look list above, and flag each one neither\n   file mentions as an Addition. For a built screen, compare its screenshot with its mockup\n   (`mockups\u002F\u003Cscreen>.png`) for layout, controls and wording.\n5. Sort each surviving item into one of three groups:\n   - **Must fix**: broken. It won't build, it fails at runtime, or a test the build log\n     claims isn't there. Something built differently from `SPEC.md` is a deviation, not a\n     Must fix, unless it breaks something. The gate should have caught these, so this group\n     is usually empty.\n   - **Your call**: a real choice, where a reviewer could reasonably pick either way.\n   - **Checked and fine**: logged or found, and no reason to change it.\n\n   When unsure whether something is broken or a choice, put it under Your call.\n6. Write each Your call item as:\n   - **Type**: `Design` (how it's built: tables, packages, public API, new services or\n     handlers), `Behavior` (what it does: rules, limits, defaults, access), or `UI` (what a\n     screen shows or says).\n   - **Plan said**: what `SPEC.md`, `ARCHITECTURE.md` or the mockup says, in a few words, or\n     \"Nothing about \u003Ctopic>\" for an Addition.\n   - **Built**: what the code does, with `file:line`.\n   - **Options**: two or three, lettered, the recommended one first. Removing or reverting\n     the change is an option whenever it's a real one.\n   - For a UI item on a screen with a mockup, the mockup and screenshot file names\n     (`mockups\u002F\u003Cscreen>.png`, `screenshots\u002F\u003Cscreen>.png`).\n\n   Write a Must fix or Checked and fine item as one line with `file:line`.\n7. Sort Your call by type: Design, then Behavior, then UI. Within a type, the one with the\n   widest effect first: a public API or stored data above code inside the feature. Put an\n   unmitigated FAIL-worthy workaround at the top of Must fix.\n\n## Report\n\nPrint the groups directly in the reply, in the order Must fix, Your call, Checked and fine —\ndon't create a new file in the plan folder. Leave out a group with nothing in it. Write each\nitem following `plain-writing`. If nothing survives steps 1–4, say plainly \"nothing needs\nyour review\" and stop; don't pad an empty result with the search process.\n\n## Hand off\n\nSuggested next: a Must fix item goes back to `feature-build` as a fix round first. Then\n`pr-describe`, which puts Your call at the top of the PR, then open the PR per\n`git-workflow`.\n\nThis is the post-build half of plan scrutiny; `feature-interrogate` is the pre-build half,\nrun by hand before `feature-build` on a plan worth the extra confidence. Neither replaces the\nother: this one reads what actually got decided during a real build, that one stress-tests\nintent before any code exists.\n","# decision-review\n\n`feature-build` runs unsupervised across many tasks. Each `builder` dispatch reports back\n\"any decision the plan left implicit that it had to make,\" and the loop logs those to\n`DECISION-LOG.md` (see that skill's step 6). In a fully autonomous run, the PR is the one\ncheckpoint guaranteed to get a human look, so `pr-describe` always invokes this skill while\nwriting that PR — nobody has to remember to trigger a separate review step. This skill doesn't\ndecide anything itself; it decides what's worth *the user's* attention and hands back a short,\nranked list.\n\n## Scope\n\n- IN: read `DECISION-LOG.md`, `BUILD-LOG.md`, and the feature's diff since it branched from\n  trunk; surface the subset worth a human's eyes; rank them.\n- OUT: fixing anything (no `Edit`\u002F`Write` needed — this is a report), gating a commit (that's\n  `reviewer`'s job, already done per task inside the loop), writing the PR description (that's\n  `pr-describe` — hand this skill's output to its \"Your call\" callout instead of duplicating\n  the digest in a second file).\n\n## Preflight\n\n1. Resolve the plan folder: the path given in the argument; else match the current\n   branch\u002Fworktree name against a plan folder the way `feature-build` does (see the project's\n   `CLAUDE.md`); else stop and ask.\n2. Confirm `BUILD-LOG.md` has at least one entry. If it's empty or missing, nothing has been\n   built yet — say so and stop rather than reviewing an empty diff.\n\n## What counts as worth surfacing\n\nFlag something only if a different, equally reasonable choice existed and the outcome could\nplausibly matter to the person who owns the feature. Five categories:\n\n- **Assumption** — filled a gap the plan or spec left open, without asking.\n- **Deviation** — the implementation does something other than what `SPEC.md` or\n  `ARCHITECTURE.md` says it does.\n- **Workaround** — routed around a bug, a missing dependency, a CMS-version gap, or a flaky\n  test, instead of a clean fix. (A weakened or skipped spec is already an automatic `reviewer`\n  `FAIL` inside the loop, so a surviving one here means it slipped through — call that out\n  as the top-priority item, not just another workaround.)\n- **Judgment call** — ambiguous plan wording resolved one way among several defensible ones.\n- **Addition** — built something `SPEC.md` and `ARCHITECTURE.md` never mention. The spec is\n  still met, so nothing reads as a deviation, but nobody asked for it.\n\nSome changes are always worth a look, logged or not, even when the spec is met:\n\n- a new database table or migration\n- a new package dependency\n- a change to the public API: a type or member added, removed, renamed, or made internal\n- a new notification handler, background job, or scheduled task\n- a new setting\n- a new extension point or manifest type\n- behavior that runs outside the feature's own screen or endpoint\n\nSkip pure implementation mechanics — variable names, which loop construct, formatting, file\nlayout inside an already-agreed extension point. Nobody needs to sign off on those.\n\n## Workflow\n\n1. Read `DECISION-LOG.md` end to end. Keep only entries timestamped from this feature's build\n   phase (from when `feature-build` cut the branch onward). Earlier entries belong to\n   `feature-explore`\u002F`feature-design`\u002F`feature-plan` — the user already weighed in during those phases'\n   interviews; don't re-surface settled ground. Drop build entries marked `user` too: the user\n   made that call during the build.\n2. Read `BUILD-LOG.md` for what each task claimed to verify, as context for the entries above.\n3. Read the full diff since the branch point (`git diff \u003Cbase>...HEAD`), with enough\n   surrounding code to judge each flagged item in context, not just the changed lines.\n4. Cross-check the diff against `SPEC.md`\u002F`ARCHITECTURE.md` for anything that reads as a\n   deviation but was never logged — the builder is supposed to report these, but this step\n   catches what leaked through rather than trusting the log is complete. Then go through the\n   diff for every change on the always-worth-a-look list above, and flag each one neither\n   file mentions as an Addition. For a built screen, compare its screenshot with its mockup\n   (`mockups\u002F\u003Cscreen>.png`) for layout, controls and wording.\n5. Sort each surviving item into one of three groups:\n   - **Must fix**: broken. It won't build, it fails at runtime, or a test the build log\n     claims isn't there. Something built differently from `SPEC.md` is a deviation, not a\n     Must fix, unless it breaks something. The gate should have caught these, so this group\n     is usually empty.\n   - **Your call**: a real choice, where a reviewer could reasonably pick either way.\n   - **Checked and fine**: logged or found, and no reason to change it.\n\n   When unsure whether something is broken or a choice, put it under Your call.\n6. Write each Your call item as:\n   - **Type**: `Design` (how it's built: tables, packages, public API, new services or\n     handlers), `Behavior` (what it does: rules, limits, defaults, access), or `UI` (what a\n     screen shows or says).\n   - **Plan said**: what `SPEC.md`, `ARCHITECTURE.md` or the mockup says, in a few words, or\n     \"Nothing about \u003Ctopic>\" for an Addition.\n   - **Built**: what the code does, with `file:line`.\n   - **Options**: two or three, lettered, the recommended one first. Removing or reverting\n     the change is an option whenever it's a real one.\n   - For a UI item on a screen with a mockup, the mockup and screenshot file names\n     (`mockups\u002F\u003Cscreen>.png`, `screenshots\u002F\u003Cscreen>.png`).\n\n   Write a Must fix or Checked and fine item as one line with `file:line`.\n7. Sort Your call by type: Design, then Behavior, then UI. Within a type, the one with the\n   widest effect first: a public API or stored data above code inside the feature. Put an\n   unmitigated FAIL-worthy workaround at the top of Must fix.\n\n## Report\n\nPrint the groups directly in the reply, in the order Must fix, Your call, Checked and fine —\ndon't create a new file in the plan folder. Leave out a group with nothing in it. Write each\nitem following `plain-writing`. If nothing survives steps 1–4, say plainly \"nothing needs\nyour review\" and stop; don't pad an empty result with the search process.\n\n## Hand off\n\nSuggested next: a Must fix item goes back to `feature-build` as a fix round first. Then\n`pr-describe`, which puts Your call at the top of the PR, then open the PR per\n`git-workflow`.\n\nThis is the post-build half of plan scrutiny; `feature-interrogate` is the pre-build half,\nrun by hand before `feature-build` on a plan worth the extra confidence. Neither replaces the\nother: this one reads what actually got decided during a real build, that one stress-tests\nintent before any code exists.\n",{"name":5,"description":7,"argument-hint":24,"user-invocable":25},"[path to the feature's plan folder, optional]",true,"main","a2f9c28bc56802b4e6db01e03972e497b30ad001","plugins\u002Fumbraco-devkit\u002Fskills\u002Fdecision-review",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 decision-review",{"tool":41,"command":42},"bunx","bunx skills add mattbrailsford\u002Fumbraco-devkit --skill decision-review",{"tool":44,"command":45},"pnpm","pnpm dlx skills add mattbrailsford\u002Fumbraco-devkit --skill decision-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmattbrailsford\u002Fumbraco-devkit\u002Fblob\u002Fmain\u002Fplugins\u002Fumbraco-devkit\u002Fskills\u002Fdecision-review\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",[],[]]