[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DM1E34825DPJ7M3FT57JEA":3,"skill-same:01M7DM1E34825DPJ7M3FT57JEA":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":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7DM1E34825DPJ7M3FT57JEA","land",null,"Drive a pull request all the way to merged. Loops review → fix → resolve threads → push → wait for CI → re-review → merge, one step at a time, until the PR is merged or genuinely blocked; root-causes CI failures instead of re-running them, answers every review thread, and merges only when CI is green, the current commit is reviewed ✅, and the owner said merging is OK. Use after opening a PR, when asked to land\u002Ffinish\u002Fbabysit\u002Fget a PR merged, or when CI or a reviewer comments on a PR.","foxinthehenhouse\u002Fapp-in-a-box","foxinthehenhouse","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F144333692?v=4","01M7DKXRK1CCGY9F45FYGWVD29","Kyle Fox","01M7DKXRKNG8A1ADJFXVH15RXT",0,"MIT","https:\u002F\u002Fgithub.com\u002Ffoxinthehenhouse\u002Fapp-in-a-box\u002Fblob\u002Fmain\u002Fplugins\u002Fapp-in-a-box\u002Ftemplate\u002F.agents\u002Fskills\u002Fland\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: land\ndescription: Drive a pull request all the way to merged. Loops review → fix → resolve threads → push → wait for CI → re-review → merge, one step at a time, until the PR is merged or genuinely blocked; root-causes CI failures instead of re-running them, answers every review thread, and merges only when CI is green, the current commit is reviewed ✅, and the owner said merging is OK. Use after opening a PR, when asked to land\u002Ffinish\u002Fbabysit\u002Fget a PR merged, or when CI or a reviewer comments on a PR.\nargument-hint: \"[PR number] [--merge-ok]\"\n---\n\n# Land a PR\n\n`pr-review` judges one commit. `land` gets the PR from \"opened\" to \"merged\" across\npushes, CI runs and review comments, without the owner reading a diff.\n\n## The loop\n\nAsk the script what's next, do exactly that one thing, repeat:\n\n```\npython3 .agents\u002Fskills\u002Fland\u002Fland.py \u003CPR> [--merge-ok]\n```\n\nPass `--merge-ok` only when the owner has said, in this conversation or in\n`AGENTS.md`, that green ✅ PRs may be merged without asking. It prints JSON with an\n`action`. Do it, then run the script again. Stop on `done`, `ask_owner` or `blocked`.\n\n| action | do this |\n|---|---|\n| `resolve_conflict` | `git fetch origin \u003Cbase> && git merge origin\u002F\u003Cbase>` on the PR branch. Resolve by intent, regenerate lockfiles with their tool (never by hand), run the gates, commit, push. Ask the owner only when both sides changed the same behaviour and either choice loses something. |\n| `fix_ci` | Open each failed check's log (`gh run view \u003Cid> --log-failed`). Find the **root cause**. Reproduce it locally, fix it, show the same check passing locally, commit, push. A failure in code this PR didn't touch: say so in one PR comment naming the check and why, then continue. \"Flaky\" is not a root cause. |\n| `address_threads` | For each thread: if it's right, fix it and reply with the commit; if it's wrong, reply with why (evidence, one or two lines). Then resolve the thread. Reply to every thread, including bot findings. A design-level ask that's bigger than this PR goes to the owner as a question, not into the diff. |\n| `wait_ci` | Wait for the checks on this head: `gh pr checks \u003CPR> --watch --fail-fast` (give it up to 20 minutes). Then loop. |\n| `review` | Run the `pr-review` skill on the current head. Its verdict comment carries the `appbox-verdict` marker, which is how this loop knows the head was reviewed. Every push needs a new review. |\n| `fix_findings` | Fix the blockers from the latest verdict, push, loop (the push triggers a fresh review). |\n| `mark_ready` | Only if the owner asked to land it: `gh pr ready \u003CPR>`. Otherwise ask. |\n| `merge` | `gh pr merge \u003CPR> --squash --delete-branch --match-head-commit \u003Chead>`. Then confirm `done`. |\n| `ask_owner` | Tell the owner where the PR stands in one short paragraph and what you need (see below). |\n| `blocked` | Say exactly what's missing (gh login, no PR for this branch) and stop. |\n\n**Waiting between events.** In Claude Code, prefer being woken: subscribe to the PR's\nactivity if your environment offers it, or schedule a check-in with a Routine\n(`routines` skill) instead of sitting in a sleep loop. In Codex, `gh pr checks --watch`\nis the wait. Never poll faster than CI can change.\n\n## Never\n\n- Skip, delete, weaken or quarantine a test to get green.\n- Push an empty commit, or close and reopen the PR, to re-trigger CI.\n- Rewrite history on a branch someone else works on: no rebase, amend or force-push.\n  Merge the base in instead.\n- Bypass a hook or a required check.\n- Merge a draft, a red head, an unreviewed head, or with an open blocking thread.\n- Leave a review thread unanswered.\n\nEach push is proven first: run the gates the changed files touch, re-read your own\ndiff for what would make CI reject it, and push once. One validated push beats three\nguesses.\n\n## Ask the owner\n\nFollow `.agents\u002Frules\u002Fproduct-judgement.md`: ask with a structured question\n(recommended option first), never decide these silently. In this skill that means:\nmerging when they haven't said review-and-merge is OK; a ⚠️ verdict; a reviewer's\nrequest that changes product behaviour, scope or the data model; and a conflict\nwhere both sides changed the same behaviour. Report the PR's state in plain words\n(what it does, what's green, what's waiting), then the one question.\n","# Land a PR\n\n`pr-review` judges one commit. `land` gets the PR from \"opened\" to \"merged\" across\npushes, CI runs and review comments, without the owner reading a diff.\n\n## The loop\n\nAsk the script what's next, do exactly that one thing, repeat:\n\n```\npython3 .agents\u002Fskills\u002Fland\u002Fland.py \u003CPR> [--merge-ok]\n```\n\nPass `--merge-ok` only when the owner has said, in this conversation or in\n`AGENTS.md`, that green ✅ PRs may be merged without asking. It prints JSON with an\n`action`. Do it, then run the script again. Stop on `done`, `ask_owner` or `blocked`.\n\n| action | do this |\n|---|---|\n| `resolve_conflict` | `git fetch origin \u003Cbase> && git merge origin\u002F\u003Cbase>` on the PR branch. Resolve by intent, regenerate lockfiles with their tool (never by hand), run the gates, commit, push. Ask the owner only when both sides changed the same behaviour and either choice loses something. |\n| `fix_ci` | Open each failed check's log (`gh run view \u003Cid> --log-failed`). Find the **root cause**. Reproduce it locally, fix it, show the same check passing locally, commit, push. A failure in code this PR didn't touch: say so in one PR comment naming the check and why, then continue. \"Flaky\" is not a root cause. |\n| `address_threads` | For each thread: if it's right, fix it and reply with the commit; if it's wrong, reply with why (evidence, one or two lines). Then resolve the thread. Reply to every thread, including bot findings. A design-level ask that's bigger than this PR goes to the owner as a question, not into the diff. |\n| `wait_ci` | Wait for the checks on this head: `gh pr checks \u003CPR> --watch --fail-fast` (give it up to 20 minutes). Then loop. |\n| `review` | Run the `pr-review` skill on the current head. Its verdict comment carries the `appbox-verdict` marker, which is how this loop knows the head was reviewed. Every push needs a new review. |\n| `fix_findings` | Fix the blockers from the latest verdict, push, loop (the push triggers a fresh review). |\n| `mark_ready` | Only if the owner asked to land it: `gh pr ready \u003CPR>`. Otherwise ask. |\n| `merge` | `gh pr merge \u003CPR> --squash --delete-branch --match-head-commit \u003Chead>`. Then confirm `done`. |\n| `ask_owner` | Tell the owner where the PR stands in one short paragraph and what you need (see below). |\n| `blocked` | Say exactly what's missing (gh login, no PR for this branch) and stop. |\n\n**Waiting between events.** In Claude Code, prefer being woken: subscribe to the PR's\nactivity if your environment offers it, or schedule a check-in with a Routine\n(`routines` skill) instead of sitting in a sleep loop. In Codex, `gh pr checks --watch`\nis the wait. Never poll faster than CI can change.\n\n## Never\n\n- Skip, delete, weaken or quarantine a test to get green.\n- Push an empty commit, or close and reopen the PR, to re-trigger CI.\n- Rewrite history on a branch someone else works on: no rebase, amend or force-push.\n  Merge the base in instead.\n- Bypass a hook or a required check.\n- Merge a draft, a red head, an unreviewed head, or with an open blocking thread.\n- Leave a review thread unanswered.\n\nEach push is proven first: run the gates the changed files touch, re-read your own\ndiff for what would make CI reject it, and push once. One validated push beats three\nguesses.\n\n## Ask the owner\n\nFollow `.agents\u002Frules\u002Fproduct-judgement.md`: ask with a structured question\n(recommended option first), never decide these silently. In this skill that means:\nmerging when they haven't said review-and-merge is OK; a ⚠️ verdict; a reviewer's\nrequest that changes product behaviour, scope or the data model; and a conflict\nwhere both sides changed the same behaviour. Report the PR's state in plain words\n(what it does, what's green, what's waiting), then the one question.\n",{"name":5,"description":7,"argument-hint":24},"[PR number] [--merge-ok]","main","82b5819f074e18b5d31db7a122e1f0ae5f5abbf7","plugins\u002Fapp-in-a-box\u002Ftemplate\u002F.agents\u002Fskills\u002Fland","https:\u002F\u002Fgithub.com\u002Ffoxinthehenhouse\u002Fapp-in-a-box","https:\u002F\u002Fgithub.com\u002Ffoxinthehenhouse","Not a developer","2026-10-06 17:24:46",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add foxinthehenhouse\u002Fapp-in-a-box --skill land",{"tool":38,"command":39},"bunx","bunx skills add foxinthehenhouse\u002Fapp-in-a-box --skill land",{"tool":41,"command":42},"pnpm","pnpm dlx skills add foxinthehenhouse\u002Fapp-in-a-box --skill land","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffoxinthehenhouse\u002Fapp-in-a-box\u002Fblob\u002Fmain\u002Fplugins\u002Fapp-in-a-box\u002Ftemplate\u002F.agents\u002Fskills\u002Fland\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"land.py","SCRIPT","脚本",7332,"https:\u002F\u002Fgithub.com\u002Ffoxinthehenhouse\u002Fapp-in-a-box\u002Fblob\u002Fmain\u002Fplugins\u002Fapp-in-a-box\u002Ftemplate\u002F.agents\u002Fskills\u002Fland\u002Fland.py",[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},"01M7DM2EPAFBTFNV5EW5GHKD5Q","ship","Release checklist for getting a build to testers or the stores. Runs the risk gate first (refuses while a risk item is open) and walks the owner through the compliance checklist. Covers the version bump, EAS build and submit, OTA updates and when they're safe, changelog, store listing, privacy nutrition label \u002F data safety form, the Accessibility Nutrition Labels, and the account-deletion requirement. Guidance-level; it never handles signing secrets. Use when asked to ship, release, submit to TestFlight \u002F App Store \u002F Play, or push an OTA update.","https:\u002F\u002Fgithub.com\u002Ffoxinthehenhouse\u002Fapp-in-a-box\u002Fblob\u002Fmain\u002Fplugins\u002Fapp-in-a-box\u002Ftemplate\u002F.agents\u002Fskills\u002Fship\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},"01M7DM2AGRJ822B3C8NQCDK3JG","routines","Put the project's recurring rituals on a schedule, with the owner's consent. Weekly north-star report, monthly market watch, dependency triage, Supabase advisor sweep, reflect and harness-optimize. Uses Claude Code Routines (cloud cron) where they fit, and documents the Codex \u002F local cron equivalent. Use when asked to automate, schedule or \"keep the project moving on its own\", or after setup finishes.","https:\u002F\u002Fgithub.com\u002Ffoxinthehenhouse\u002Fapp-in-a-box\u002Fblob\u002Fmain\u002Fplugins\u002Fapp-in-a-box\u002Ftemplate\u002F.agents\u002Fskills\u002Froutines\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},"01M7DM27C3K1Y7FM0NZSBRSVEN","reflect","Consolidate what recent sessions learned into the project's long-term memory (.agents\u002Fmemory). Use at the end of a substantial session, after a correction from the user, after a painful debugging session, when the session-start healthcheck says reflect is overdue or a pending-reflection seed is waiting, or when MEMORY.md exceeds its budget.","https:\u002F\u002Fgithub.com\u002Ffoxinthehenhouse\u002Fapp-in-a-box\u002Fblob\u002Fmain\u002Fplugins\u002Fapp-in-a-box\u002Ftemplate\u002F.agents\u002Fskills\u002Freflect\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},"01M7DM2146TCNYXVVS2QXF08GS","pr-review","Review a pull request on the owner's behalf and fix what's safe to fix. Runs the deterministic gates first, then correctness\u002Fsecurity, design-system, accessibility and analytics review passes, verifies each blocking finding, applies safe fixes, re-checks, and ends with a plain-English verdict. Use when a PR is opened, when asked to review a PR, a branch or a pasted diff, or before merging anything.","https:\u002F\u002Fgithub.com\u002Ffoxinthehenhouse\u002Fapp-in-a-box\u002Fblob\u002Fmain\u002Fplugins\u002Fapp-in-a-box\u002Ftemplate\u002F.agents\u002Fskills\u002Fpr-review\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},"01M7DM1X6QP3QAT47ET852S0P8","north-star-report","Weekly product-analytics and reliability readout. Pulls the funnel of the brief's 5 north-star events from PostHog, finds the biggest drop-offs and errors, checks each SLO in docs\u002Fslo.yaml against its error budget, compares with last week, and proposes (then, with a yes, files) tickets that target them. Use weekly, when the session-start line says it's overdue, when the backlog is empty, or when asked \"how is the app doing?\".","https:\u002F\u002Fgithub.com\u002Ffoxinthehenhouse\u002Fapp-in-a-box\u002Fblob\u002Fmain\u002Fplugins\u002Fapp-in-a-box\u002Ftemplate\u002F.agents\u002Fskills\u002Fnorth-star-report\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},"01M7DM1QX8F3D95JSTEHC0P9QA","next","Decide the single next best thing to work on, with two alternates. Reads setup progress, work in progress, open PRs and failing CI, the backlog (GitHub Issues or Linear), overdue harness rituals, product decisions parked until now, and north-star analytics if PostHog is connected. Use when someone asks \"what next?\", \"what should I work on?\", at the start of a session, or after a PR merges.","https:\u002F\u002Fgithub.com\u002Ffoxinthehenhouse\u002Fapp-in-a-box\u002Fblob\u002Fmain\u002Fplugins\u002Fapp-in-a-box\u002Ftemplate\u002F.agents\u002Fskills\u002Fnext\u002FSKILL.md",[],[]]