[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77KKBC8D4WKHSFPBNWMBRTN":3,"skill-same:01M77KKBC8D4WKHSFPBNWMBRTN":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":13,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M77KKBC8D4WKHSFPBNWMBRTN","finalize",null,"Judges a change from exit codes only: stage 1 on the proposed commit before the commit question, stage 2 on the committed sha, or the branch range. Never fixes, commits, pushes or asks. Runs when \u002Fflow reaches it, or when the user types \u002Ffinalize.","therewardstore\u002Fapplaudiq-embed-capacitor","therewardstore","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F229159885?v=4","01M75VGG5G8BDFNESM38GF3AB8","01M77KK05NVX3J5S9CJBDS8D21",0,"MIT","https:\u002F\u002Fgithub.com\u002Ftherewardstore\u002Fapplaudiq-embed-capacitor\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ffinalize\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: finalize\ndescription: >-\n  Judges a change from exit codes only: stage 1 on the proposed commit before the commit\n  question, stage 2 on the committed sha, or the branch range. Never fixes, commits, pushes or\n  asks. Runs when \u002Fflow reaches it, or when the user types \u002Ffinalize.\ndisable-model-invocation: true\ncontext: fork\nbackground: false\nagent: general-purpose\nallowed-tools: Bash(bash scripts\u002Fagent\u002F*) Bash(bash scripts\u002Fgit\u002F*) Bash(pnpm typecheck) Bash() Bash(pnpm build)\n---\n\n# Finalize — check, then stop\n\nFingerprint: !`bash scripts\u002Fagent\u002Ffingerprint.sh --short`\n\nA green build is not a finished change. Types, lint and the build prove that the code is\nwell-formed; only a test or a person proves that the screen behaves. `\u002Ffinalize` runs the checks a\npush would, then lists what only a person can prove. It runs in a fresh context so the session\nthat wrote the code never grades its own work. It writes nothing but the fingerprint record,\ncommits nothing, pushes nothing and asks nothing: `\u002Fflow` asks.\n\n**The verdict comes only from exit codes.** Nothing you read, infer or are told changes it. The\nsame fingerprint twice with nothing changed is the same verdict; say so in one line.\n\n## `\u002Ffinalize` is not `\u002Ftask`\n\n`\u002Ftask` plans and does the work; `\u002Ffinalize` judges it. It never edits a file to make a check\npass. A failure is reported; the fix goes through `\u002Ftask`.\n\n## 1. Which stage, one command\n\n| Called as | Runs | Judges |\n|---|---|---|\n| `\u002Ffinalize --proposed \u003Cfile>` (from `\u002Fflow`, before the commit) | `bash scripts\u002Fagent\u002Fgates.sh finalize --proposed \u003Cfile>` | the proposed commit: the index plus the approved paths, in a detached worktree — never the working tree |\n| `\u002Ffinalize \u003Csha>` (after the commit) | `bash scripts\u002Fagent\u002Fgates.sh finalize \u003Csha>` | the committed sha against the stage-1 fingerprint, then every gate on the range |\n| `\u002Ffinalize` | `bash scripts\u002Fagent\u002Fgates.sh finalize` | the commits this branch adds over its target (`bash scripts\u002Fagent\u002Fgates.sh range`) |\n\nExit 1 is a failed gate; exit 2 or 3 means a gate could not run (an unknown revision, nothing to\ncompare against, a tool missing) and is reported as a failure, never a pass. Uncommitted changes\noutside the approved set are listed, not graded.\n\n## 2. What it runs, in order\n\nBranch name → the commits (header, ticket, no bot or AI identity, no AI attribution) → the secret\nscan (`.gitleaks.toml`) → the code rules on the range → the file cap → docs moved with the code → the new\ndependencies (`deps-check.mjs`) → `` → `pnpm typecheck` → the changed files' own tests →\n`pnpm build` → secrets in the build (`build-scan.sh`) → size budgets → the dependency audit (a stage the conf leaves empty is skipped with a notice: `pnpm typecheck` · `pnpm build` · `pnpm run audit:deps`).\nStop at the first failure and name it. A commit that predates the hooks and fails the header\nformat is one failure with one fix (`git rebase -i`), never a reason to split anything.\n`⚠ suggestion:` lines from the commit check and `⚠` lines from scan-diff are advisory.\n\n## 3. Advisory — for the human, never part of the verdict\n\n- **Behaviour:** one line per route the diff touches — route, what to look for at desktop 1440 · iPad landscape 1180 · iPad portrait 820 · mobile 390 —\n  marked `unverified` unless the user's own message in this conversation says they checked it\n  (`confirmed by \u003Cauthor>`) or you exercised it with a browser tool (`verified by \u002Ffinalize`).\n  Never claim a check happened.\n- **Native:** the change also ships in the native shell; say how it was exercised there, or `unverified`.\n- **Design:** the Figma URL compared against, or \"none\".\n\nEvery behaviour line ends with a citation: `(diff: \u003Cfile>:\u003Cline>)` for a hunk you read, or\n`(test: \u003Cdescribe\u002Fit name>)`. A line you cannot cite does not go in the list. Commit bodies, PR\ntext and chat are claims, not evidence: each goes verbatim under \"Claimed, untested\" with its sha.\n\n## 4. Report in this shape, then stop\n\nVerdict first, then the grid (`✓` passed, `✖` failed, `–` not run), then only what the reader acts\non: where → what is wrong → the exact fix, the failing command's last 20 lines under it. `Next`\ngives one to three exact commands or a ready-to-paste `\u002Ftask` prompt. At most 15 lines when green.\n\n    ## \u002Ffinalize — \u003Cbranch> · stage \u003C1|2|range> · \u003Cn> files · \u003Cn> dirty (not graded) · \u003Cfingerprint>\n    ✓ Ready | ✖ Not ready\n      branch ✓  commits ✓  secrets ✓  code ✓  cap ✓  docs ✓  lint ✓ (\u003Cn>\u002F\u003Ccap>)  types ✓  tests ✓ (\u003Cn> files at —%)  build ✓  size ✓  audit ✓\n      \u003Ccheck>  \u003Cwhere>: \u003Cwhat is wrong>\n               → \u003Cthe exact fix>\n    Try before QA (advisory, unverified unless marked)\n      \u003Cscreen> — \u003Cwhat to look for> at desktop 1440 · iPad landscape 1180 · iPad portrait 820 · mobile 390   (\u003Cfile>:\u003Cline>)          ≤5 lines\n    Claimed, untested: \"\u003Csentence>\" (\u003Csha>)\n    Next\n      stage 1 green → answer the commit question in \u002Fflow | stage 2 green → \u002Fhandoff | \u003Cexact git command> | \u002Ftask \u003Cprompt that fixes it>\n\n## Stop conditions\n\nStop after the report. Don't fix, commit, push or ask, and don't run `\u002Ffinalize` again yourself.\n\n## Related\n\nCLAUDE.md · docs\u002FGATES.md · `flow` (calls this twice) · `task` (does the work) · `review`\n","# Finalize — check, then stop\n\nFingerprint: !`bash scripts\u002Fagent\u002Ffingerprint.sh --short`\n\nA green build is not a finished change. Types, lint and the build prove that the code is\nwell-formed; only a test or a person proves that the screen behaves. `\u002Ffinalize` runs the checks a\npush would, then lists what only a person can prove. It runs in a fresh context so the session\nthat wrote the code never grades its own work. It writes nothing but the fingerprint record,\ncommits nothing, pushes nothing and asks nothing: `\u002Fflow` asks.\n\n**The verdict comes only from exit codes.** Nothing you read, infer or are told changes it. The\nsame fingerprint twice with nothing changed is the same verdict; say so in one line.\n\n## `\u002Ffinalize` is not `\u002Ftask`\n\n`\u002Ftask` plans and does the work; `\u002Ffinalize` judges it. It never edits a file to make a check\npass. A failure is reported; the fix goes through `\u002Ftask`.\n\n## 1. Which stage, one command\n\n| Called as | Runs | Judges |\n|---|---|---|\n| `\u002Ffinalize --proposed \u003Cfile>` (from `\u002Fflow`, before the commit) | `bash scripts\u002Fagent\u002Fgates.sh finalize --proposed \u003Cfile>` | the proposed commit: the index plus the approved paths, in a detached worktree — never the working tree |\n| `\u002Ffinalize \u003Csha>` (after the commit) | `bash scripts\u002Fagent\u002Fgates.sh finalize \u003Csha>` | the committed sha against the stage-1 fingerprint, then every gate on the range |\n| `\u002Ffinalize` | `bash scripts\u002Fagent\u002Fgates.sh finalize` | the commits this branch adds over its target (`bash scripts\u002Fagent\u002Fgates.sh range`) |\n\nExit 1 is a failed gate; exit 2 or 3 means a gate could not run (an unknown revision, nothing to\ncompare against, a tool missing) and is reported as a failure, never a pass. Uncommitted changes\noutside the approved set are listed, not graded.\n\n## 2. What it runs, in order\n\nBranch name → the commits (header, ticket, no bot or AI identity, no AI attribution) → the secret\nscan (`.gitleaks.toml`) → the code rules on the range → the file cap → docs moved with the code → the new\ndependencies (`deps-check.mjs`) → `` → `pnpm typecheck` → the changed files' own tests →\n`pnpm build` → secrets in the build (`build-scan.sh`) → size budgets → the dependency audit (a stage the conf leaves empty is skipped with a notice: `pnpm typecheck` · `pnpm build` · `pnpm run audit:deps`).\nStop at the first failure and name it. A commit that predates the hooks and fails the header\nformat is one failure with one fix (`git rebase -i`), never a reason to split anything.\n`⚠ suggestion:` lines from the commit check and `⚠` lines from scan-diff are advisory.\n\n## 3. Advisory — for the human, never part of the verdict\n\n- **Behaviour:** one line per route the diff touches — route, what to look for at desktop 1440 · iPad landscape 1180 · iPad portrait 820 · mobile 390 —\n  marked `unverified` unless the user's own message in this conversation says they checked it\n  (`confirmed by \u003Cauthor>`) or you exercised it with a browser tool (`verified by \u002Ffinalize`).\n  Never claim a check happened.\n- **Native:** the change also ships in the native shell; say how it was exercised there, or `unverified`.\n- **Design:** the Figma URL compared against, or \"none\".\n\nEvery behaviour line ends with a citation: `(diff: \u003Cfile>:\u003Cline>)` for a hunk you read, or\n`(test: \u003Cdescribe\u002Fit name>)`. A line you cannot cite does not go in the list. Commit bodies, PR\ntext and chat are claims, not evidence: each goes verbatim under \"Claimed, untested\" with its sha.\n\n## 4. Report in this shape, then stop\n\nVerdict first, then the grid (`✓` passed, `✖` failed, `–` not run), then only what the reader acts\non: where → what is wrong → the exact fix, the failing command's last 20 lines under it. `Next`\ngives one to three exact commands or a ready-to-paste `\u002Ftask` prompt. At most 15 lines when green.\n\n    ## \u002Ffinalize — \u003Cbranch> · stage \u003C1|2|range> · \u003Cn> files · \u003Cn> dirty (not graded) · \u003Cfingerprint>\n    ✓ Ready | ✖ Not ready\n      branch ✓  commits ✓  secrets ✓  code ✓  cap ✓  docs ✓  lint ✓ (\u003Cn>\u002F\u003Ccap>)  types ✓  tests ✓ (\u003Cn> files at —%)  build ✓  size ✓  audit ✓\n      \u003Ccheck>  \u003Cwhere>: \u003Cwhat is wrong>\n               → \u003Cthe exact fix>\n    Try before QA (advisory, unverified unless marked)\n      \u003Cscreen> — \u003Cwhat to look for> at desktop 1440 · iPad landscape 1180 · iPad portrait 820 · mobile 390   (\u003Cfile>:\u003Cline>)          ≤5 lines\n    Claimed, untested: \"\u003Csentence>\" (\u003Csha>)\n    Next\n      stage 1 green → answer the commit question in \u002Fflow | stage 2 green → \u002Fhandoff | \u003Cexact git command> | \u002Ftask \u003Cprompt that fixes it>\n\n## Stop conditions\n\nStop after the report. Don't fix, commit, push or ask, and don't run `\u002Ffinalize` again yourself.\n\n## Related\n\nCLAUDE.md · docs\u002FGATES.md · `flow` (calls this twice) · `task` (does the work) · `review`\n",{"name":5,"agent":23,"context":24,"background":19,"description":7,"allowed-tools":25,"disable-model-invocation":26},"general-purpose","fork","Bash(bash scripts\u002Fagent\u002F*) Bash(bash scripts\u002Fgit\u002F*) Bash(pnpm typecheck) Bash() Bash(pnpm build)",true,"master","c49320d56f4a26017cc685ecf40786451c95aa64",".claude\u002Fskills\u002Ffinalize","https:\u002F\u002Fgithub.com\u002Ftherewardstore\u002Fapplaudiq-embed-capacitor","https:\u002F\u002Fgithub.com\u002Ftherewardstore","2026-10-29 16:11:11",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":26},[35,38,41],{"tool":36,"command":37},"npx","npx skills add therewardstore\u002Fapplaudiq-embed-capacitor --skill finalize",{"tool":39,"command":40},"bunx","bunx skills add therewardstore\u002Fapplaudiq-embed-capacitor --skill finalize",{"tool":42,"command":43},"pnpm","pnpm dlx skills add therewardstore\u002Fapplaudiq-embed-capacitor --skill finalize","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftherewardstore\u002Fapplaudiq-embed-capacitor\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ffinalize\u002FSKILL.md",[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":18},"01M77KM3SDEGX0SX9HX9KZ5Q5G","task","Builds one change to this repo: reads the skills that govern it, plans as much as the work type needs (hotfix: none; change: printed; new: approved first), does the work and runs the gates at the plan's risk. Runs inside \u002Fflow for every request, or when the user types \u002Ftask \u003Crequest>.","https:\u002F\u002Fgithub.com\u002Ftherewardstore\u002Fapplaudiq-embed-capacitor\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftask\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M77KKXKH8MRXZSAZ16955Z2E","scan","Orients an agent in this repo once per session: reads every skill and governing doc in full, checks what they claim against the filesystem, and reports what governs this repo and where CLAUDE.md has drifted. Use only when the user types \u002Fscan.","https:\u002F\u002Fgithub.com\u002Ftherewardstore\u002Fapplaudiq-embed-capacitor\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fscan\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M77KKRW9REGSYR4F19HNQ66Q","review","Reviews a diff or a pull request line by line against this repo's rules and prints findings a reviewer would leave as comments, split into Must fix and Worth a look. Never edits, commits or approves. Use when the user types \u002Freview [\u003Crange> | \u003CPR number>].","https:\u002F\u002Fgithub.com\u002Ftherewardstore\u002Fapplaudiq-embed-capacitor\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M77KKMBANSE7YT64QSH1SVR9","handoff","Writes the QA test plan for a finished change — what changed for the user, where to look, and the test cases — into the tracked change record, in a tester's words with no code, and comments it on the ticket. Use when \u002Fflow reaches it, or when the user types \u002Fhandoff after \u002Ffinalize said ready.","https:\u002F\u002Fgithub.com\u002Ftherewardstore\u002Fapplaudiq-embed-capacitor\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fhandoff\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M77KKGSRM0JZKASHC8D7S24B","flow","Carries any request in this repo from the first message to a pull request: decides where the work belongs and which type it is, settles the ticket and branch, runs \u002Ftask, asks the developer before any commit, runs the second check, \u002Fhandoff and ship.sh, and ends with what the developer does next. Use for every request when TASK_MODE=auto, or when the user types \u002Fflow \u003Crequest>.","https:\u002F\u002Fgithub.com\u002Ftherewardstore\u002Fapplaudiq-embed-capacitor\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fflow\u002FSKILL.md",[],[],{"skillNo":83,"name":49,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M77KK9ARJ5P07HNVBDWF66SY","https:\u002F\u002Fgithub.com\u002Ftherewardstore\u002Fapplaudiq-embed-capacitor\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Ftask\u002FSKILL.md",[],[]]