[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ATYRBEEB980RJCXVZ9V2FP":3,"skill-same:01M7ATYRBEEB980RJCXVZ9V2FP":52},{"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},"01M7ATYRBEEB980RJCXVZ9V2FP","specrew-review",null,"Run live continuous co-review or replay persisted reviewer evidence for an iteration.","alonf\u002FKeyContextAI","alonf","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F554150?v=4","01M7ATEPSCNKG13BVTKA74VG59","Alon Fliess","01M7ATEPSZ4YMBM9W25SKM3GES",0,"MIT","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.cursor\u002Frules\u002Fspecrew-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: specrew-review\ndescription: Run live continuous co-review or replay persisted reviewer evidence for an iteration.\n---\n\n# specrew-review\n\n**Type**: Operational Skill\n**Schema**: v1\n**Status**: Active\n**Namespace**: `\u002Fspecrew`\n**Canonical command**: `\u002Fspecrew-review`\n\n## Purpose\n\nTrigger or inspect the Specrew review-oriented workflow. Use live mode to run the continuous co-review runtime and persist reviewer evidence under `.specrew\u002Freview\u002Finline\u002F\u003Crun-id>\u002F`; use replay mode to inspect an existing reviewer closeout packet for a completed iteration.\n\n## When to Use\n\n- When a reviewer needs a live continuous co-review run before or during a review boundary.\n- When a reviewer wants to inspect the review summary for a completed iteration.\n- When replaying the reviewer closeout packet.\n- Invoke this skill when the user says: \"Run the reviewer\", \"Run live review\", \"Show the review summary\", \"Review the iteration\", \"Show reviewer output\".\n\n## Boundary Safety\n\nThis skill **supports review work** but does **not** bypass the required human decision point. A human reviewer must still explicitly approve lifecycle advancement. Invoking `\u002Fspecrew-review` is not equivalent to approving an iteration for closure or advancement.\n\n**Feature 016 rule**: Humans remain the approval authority for major boundary transitions. This command may not imply authorization to advance from any lifecycle boundary.\n\n## Coexistence Contract\n\nThis skill is part of the `\u002Fspecrew-*` command surface. It coexists with `\u002Fspeckit.*` review-related commands without collision or shadow. Using `\u002Fspecrew-review` does not substitute for `\u002Fspeckit.*` lifecycle actions that require explicit human authorization.\n\n## Invocation\n\n```text\n\u002Fspecrew-review [\u003Citeration>] [--project-path \u003Cpath>] [--feature \u003Cid>]\n                 [--iteration \u003CNNN>] [--quiet] [--json] [--open]\n\u002Fspecrew-review --live [--baseline-ref \u003Cgit-ref>] [--project-path \u003Cpath>]   # baseline auto-anchors for signoff; an explicit --baseline-ref run is exploratory-only\n                 [--checkpoint-id \u003Cid>] [--run-id \u003Cid>] [--host \u003Chost>]\n                 [--model \u003Cmodel>] [--effort \u003Ceffort>] [--authorization-ref \u003Cref>]\n                 [--code-writer-host \u003Chost>]\n                 [--design-context-ref \u003Cpath>] [--allowed-path \u003Cpath>]\n                 [--forbidden-path \u003Cpath>] [--exclude-path \u003Cpath>]\n                 [--reviewer-config \u003Cpath>] [--schema-root \u003Cpath>]\n                 [--run-root \u003Cpath>] [--timeout-seconds \u003CN>]\n                 [--fallback-policy \u003Cnone|one-authorized-availability-fallback>]\n                 [--preserve-debug]\n\u002Fspecrew-review --reconcile-run \u003Crun-id> [--project-path \u003Cpath>]\n```\n\nBacked by: `specrew review` \u002F `scripts\u002Fspecrew-review.ps1`\n\n## Inputs\n\n| Input | Type | Required | Description |\n| ----- | ---- | -------- | ----------- |\n| `\u003Citeration>` | string (positional) | No | Iteration number to replay (defaults to most recent closed iteration) |\n| `--project-path` | string | No | Target Specrew project path (defaults to current directory) |\n| `--feature` | string | No | Restrict lookup to one feature directory under `specs\\` |\n| `--iteration` | string | No | Replay a specific iteration directory |\n| `--quiet` | flag | No | Emit only the stable machine-parseable digest line |\n| `--json` | flag | No | Emit JSON summary instead of the visual reviewer summary |\n| `--open` | flag | No | Open reviewer-index.md and review-diagrams.md when present |\n| `--live` | flag | No | Run the continuous co-review runtime instead of replaying prior closeout state |\n| `--baseline-ref` | string | Yes for `--live` | Git ref used to compute the review change set |\n| `--checkpoint-id` | string | No | Stable checkpoint identifier for the live review request |\n| `--run-id` | string | No | Explicit run id for evidence under `.specrew\u002Freview\u002Finline\u002F\u003Crun-id>\u002F` |\n| `--host` | string | No | Reviewer host to request (`claude`, `codex`, `copilot`, `cursor-agent`, or `antigravity`) |\n| `--model` | string | No | Reviewer model override; non-default models require `--authorization-ref` |\n| `--effort` | string | No | Optional host-specific reviewer reasoning\u002Feffort label persisted in evidence |\n| `--authorization-ref` | string | No | Human authorization reference for host\u002Fmodel selection |\n| `--code-writer-host` | string | No | Implementation host (`claude`, `codex`, etc.) used to prefer an independent peer reviewer |\n| `--design-context-ref` | string | No | Design or lifecycle artifact to include in the review request context |\n| `--allowed-path` | string | No | Add a mutable path allowlist entry for this live review run |\n| `--forbidden-path` | string | No | Add a protected path entry for this live review run |\n| `--exclude-path` | string | No | Add a change-set exclusion entry for this live review run |\n| `--reviewer-config` | string | No | JSON reviewer host configuration for deterministic or authorized hosts |\n| `--schema-root` | string | No | Contract schema root for `ReviewRequest` and `FindingsResult` validation |\n| `--run-root` | string | No | Override the evidence output root; defaults to `.specrew\u002Freview\u002Finline` |\n| `--timeout-seconds` | number | No | Live reviewer host timeout |\n| `--fallback-policy` | string | No | Host fallback policy (`none` or `one-authorized-availability-fallback`) |\n| `--preserve-debug` | flag | No | Preserve debug artifacts from the live review run |\n| `--reconcile-run` | string | No | Resume one interrupted campaign run without invoking or retrying a provider |\n\n## Outputs\n\n- Live `ReviewRequest`, prompt bundle, host invocation metadata, `FindingsResult`, gate verdict, and run index under `.specrew\u002Freview\u002Finline\u002F\u003Crun-id>\u002F` when `--live` is used.\n- Reviewer closeout packet for the specified iteration when replay mode is used.\n- Raw\u002Fnative output from the underlying `specrew review` workflow with minimal wrapper context.\n\n## Argument Whitelist\n\nOnly the arguments listed above are accepted in v1. Unknown arguments are rejected with command-specific help guidance.\n\n## Failure Guidance\n\n| Failure mode | Behavior |\n| --- | --- |\n| Unsupported argument | Rejected immediately with command-specific help guidance |\n| Missing `--baseline-ref` in live mode | Error explaining that live review needs a baseline ref |\n| Unauthorized reviewer host\u002Fmodel | Infrastructure failure with reviewer authorization guidance; do not treat this as reviewer approval |\n| No iteration found | Error with guidance to check `specs\u002F` directory structure |\n| Missing project setup | Stop with `specrew init` remediation |\n\n## See Also\n\n- `\u002Fspecrew-where` — current project status (live, not review replay)\n- `\u002Fspecrew-help` — catalog fallback and full command list\n","# specrew-review\n\n**Type**: Operational Skill\n**Schema**: v1\n**Status**: Active\n**Namespace**: `\u002Fspecrew`\n**Canonical command**: `\u002Fspecrew-review`\n\n## Purpose\n\nTrigger or inspect the Specrew review-oriented workflow. Use live mode to run the continuous co-review runtime and persist reviewer evidence under `.specrew\u002Freview\u002Finline\u002F\u003Crun-id>\u002F`; use replay mode to inspect an existing reviewer closeout packet for a completed iteration.\n\n## When to Use\n\n- When a reviewer needs a live continuous co-review run before or during a review boundary.\n- When a reviewer wants to inspect the review summary for a completed iteration.\n- When replaying the reviewer closeout packet.\n- Invoke this skill when the user says: \"Run the reviewer\", \"Run live review\", \"Show the review summary\", \"Review the iteration\", \"Show reviewer output\".\n\n## Boundary Safety\n\nThis skill **supports review work** but does **not** bypass the required human decision point. A human reviewer must still explicitly approve lifecycle advancement. Invoking `\u002Fspecrew-review` is not equivalent to approving an iteration for closure or advancement.\n\n**Feature 016 rule**: Humans remain the approval authority for major boundary transitions. This command may not imply authorization to advance from any lifecycle boundary.\n\n## Coexistence Contract\n\nThis skill is part of the `\u002Fspecrew-*` command surface. It coexists with `\u002Fspeckit.*` review-related commands without collision or shadow. Using `\u002Fspecrew-review` does not substitute for `\u002Fspeckit.*` lifecycle actions that require explicit human authorization.\n\n## Invocation\n\n```text\n\u002Fspecrew-review [\u003Citeration>] [--project-path \u003Cpath>] [--feature \u003Cid>]\n                 [--iteration \u003CNNN>] [--quiet] [--json] [--open]\n\u002Fspecrew-review --live [--baseline-ref \u003Cgit-ref>] [--project-path \u003Cpath>]   # baseline auto-anchors for signoff; an explicit --baseline-ref run is exploratory-only\n                 [--checkpoint-id \u003Cid>] [--run-id \u003Cid>] [--host \u003Chost>]\n                 [--model \u003Cmodel>] [--effort \u003Ceffort>] [--authorization-ref \u003Cref>]\n                 [--code-writer-host \u003Chost>]\n                 [--design-context-ref \u003Cpath>] [--allowed-path \u003Cpath>]\n                 [--forbidden-path \u003Cpath>] [--exclude-path \u003Cpath>]\n                 [--reviewer-config \u003Cpath>] [--schema-root \u003Cpath>]\n                 [--run-root \u003Cpath>] [--timeout-seconds \u003CN>]\n                 [--fallback-policy \u003Cnone|one-authorized-availability-fallback>]\n                 [--preserve-debug]\n\u002Fspecrew-review --reconcile-run \u003Crun-id> [--project-path \u003Cpath>]\n```\n\nBacked by: `specrew review` \u002F `scripts\u002Fspecrew-review.ps1`\n\n## Inputs\n\n| Input | Type | Required | Description |\n| ----- | ---- | -------- | ----------- |\n| `\u003Citeration>` | string (positional) | No | Iteration number to replay (defaults to most recent closed iteration) |\n| `--project-path` | string | No | Target Specrew project path (defaults to current directory) |\n| `--feature` | string | No | Restrict lookup to one feature directory under `specs\\` |\n| `--iteration` | string | No | Replay a specific iteration directory |\n| `--quiet` | flag | No | Emit only the stable machine-parseable digest line |\n| `--json` | flag | No | Emit JSON summary instead of the visual reviewer summary |\n| `--open` | flag | No | Open reviewer-index.md and review-diagrams.md when present |\n| `--live` | flag | No | Run the continuous co-review runtime instead of replaying prior closeout state |\n| `--baseline-ref` | string | Yes for `--live` | Git ref used to compute the review change set |\n| `--checkpoint-id` | string | No | Stable checkpoint identifier for the live review request |\n| `--run-id` | string | No | Explicit run id for evidence under `.specrew\u002Freview\u002Finline\u002F\u003Crun-id>\u002F` |\n| `--host` | string | No | Reviewer host to request (`claude`, `codex`, `copilot`, `cursor-agent`, or `antigravity`) |\n| `--model` | string | No | Reviewer model override; non-default models require `--authorization-ref` |\n| `--effort` | string | No | Optional host-specific reviewer reasoning\u002Feffort label persisted in evidence |\n| `--authorization-ref` | string | No | Human authorization reference for host\u002Fmodel selection |\n| `--code-writer-host` | string | No | Implementation host (`claude`, `codex`, etc.) used to prefer an independent peer reviewer |\n| `--design-context-ref` | string | No | Design or lifecycle artifact to include in the review request context |\n| `--allowed-path` | string | No | Add a mutable path allowlist entry for this live review run |\n| `--forbidden-path` | string | No | Add a protected path entry for this live review run |\n| `--exclude-path` | string | No | Add a change-set exclusion entry for this live review run |\n| `--reviewer-config` | string | No | JSON reviewer host configuration for deterministic or authorized hosts |\n| `--schema-root` | string | No | Contract schema root for `ReviewRequest` and `FindingsResult` validation |\n| `--run-root` | string | No | Override the evidence output root; defaults to `.specrew\u002Freview\u002Finline` |\n| `--timeout-seconds` | number | No | Live reviewer host timeout |\n| `--fallback-policy` | string | No | Host fallback policy (`none` or `one-authorized-availability-fallback`) |\n| `--preserve-debug` | flag | No | Preserve debug artifacts from the live review run |\n| `--reconcile-run` | string | No | Resume one interrupted campaign run without invoking or retrying a provider |\n\n## Outputs\n\n- Live `ReviewRequest`, prompt bundle, host invocation metadata, `FindingsResult`, gate verdict, and run index under `.specrew\u002Freview\u002Finline\u002F\u003Crun-id>\u002F` when `--live` is used.\n- Reviewer closeout packet for the specified iteration when replay mode is used.\n- Raw\u002Fnative output from the underlying `specrew review` workflow with minimal wrapper context.\n\n## Argument Whitelist\n\nOnly the arguments listed above are accepted in v1. Unknown arguments are rejected with command-specific help guidance.\n\n## Failure Guidance\n\n| Failure mode | Behavior |\n| --- | --- |\n| Unsupported argument | Rejected immediately with command-specific help guidance |\n| Missing `--baseline-ref` in live mode | Error explaining that live review needs a baseline ref |\n| Unauthorized reviewer host\u002Fmodel | Infrastructure failure with reviewer authorization guidance; do not treat this as reviewer approval |\n| No iteration found | Error with guidance to check `specs\u002F` directory structure |\n| Missing project setup | Stop with `specrew init` remediation |\n\n## See Also\n\n- `\u002Fspecrew-where` — current project status (live, not review replay)\n- `\u002Fspecrew-help` — catalog fallback and full command list\n",{"name":5,"description":7},"main","176da577bfd98859f793bdd1312690c6c3940c67",".cursor\u002Frules\u002Fspecrew-review","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI","https:\u002F\u002Fgithub.com\u002Falonf","http:\u002F\u002Falonfliess.me","CTO & Founder of Zionet.\r\nMicrosoft Regional Director and Foundry MVP.\r\n","2026-08-28 05:21:35",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add alonf\u002FKeyContextAI --skill specrew-review",{"tool":38,"command":39},"bunx","bunx skills add alonf\u002FKeyContextAI --skill specrew-review",{"tool":41,"command":42},"pnpm","pnpm dlx skills add alonf\u002FKeyContextAI --skill specrew-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.cursor\u002Frules\u002Fspecrew-review\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},".specrew-managed","OTHER","其他",71,"https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.cursor\u002Frules\u002Fspecrew-review\u002F.specrew-managed",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7AVHRWWXA0BQ5PXNA8FG30W","windows-compatibility","Cross-platform path handling and command patterns","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fwindows-compatibility\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7AVHABPRYXYM3GWJY1RW92A","versioning-policy","Semver versioning rules for Squad SDK and CLI — prevents prerelease version incidents","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fversioning-policy\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7AVH4KNP3TCVQDRVS70VP19","tiered-memory","Three-tier agent memory model (hot\u002Fcold\u002Fwiki) for context reduction per spawn","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftiered-memory\u002FSKILL.md",[],[],{"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},"01M7AVH18JDSA55Z7KK2GH6X49","test-discipline","Update tests when changing APIs — no exceptions","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftest-discipline\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7AVGVGWYD7NBNXAV4PAZJ92","squad","Squad's command catalog and interactive menu. Invoke via \u002Fsquad (slash command) or natural language (\"squad commands\", \"what can squad do\", \"show me squad options\"). Presents categorized operations (Install & Upgrade, Team Management, Issues & PRs, Plugins & Skills, Model & Cost, Sessions & State) as an interactive picker. Routes to the right squad CLI command or the Squad coordinator agent.","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fsquad\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7AVGPSFT1WHW3PK35DHS5XK","squad-version-check","Internals of how @bradygaster\u002Fsquad-cli stamps its version, how `squad upgrade` works (what it preserves vs overwrites), and how to probe the npm registry for the latest version from a coordinator prompt.","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fsquad-version-check\u002FSKILL.md",[],[]]