GetKits
KitSkillsBotsDotsBundles料金ガイド
Kit/開発/開発アウターループ Kit
Bundle開発GetKits 公式

開発アウターループ Kit

チームのアウターループを回します:日次トリアージ、CI の判定、リリースノート、ポストモーテム。

出品者:GetKits

$49 の価値がある理由

肩代わりする仕事

アウターループ担当の作業は 1 日約 15 分。9:00 に Bot がトリアージし、9:15 に Dot がリードへ決定事項のリストを送り、各エンジニアの Skill が PR 説明文とレビュー準備を書きます。

初日から使えるもの

  • Skill、Bot、Dot が 10 種類の出力ブロックを共有
  • 役割、7 つのガードレール、受け渡し表を含むプレイブック
  • 時間をずらして運用:Bot は 9:00、Dot は 9:15、スタンドアップは 9:30
  • 目標つきの 4 つの指標と、週ごとの最初の 30 日計画
  • 全体のセットアップは 2 日間で約 50 分

自分で作らずに済むもの

Bot の投稿を誰が承認するかを決め、何かが書き込む前にガードレールを敷き、同じトリアージを二度しないよう 3 つのツールの時間を調整する作業。単品には含まれないプレイブックの部分です。

この 3 つの Kit は個別に買うと $57。まとめて $49 なので、$8 お得です。

3つのパーツが連携して動く様子

頼めば Skill が仕事をこなし、Bot が Grok でルーティンを回し、Dot が ChatGPT で見守り続けます。各ステップは、この Kit に含まれる実際のビフォー・アフターです。

実例 · 開発アウターループ Kit

ビフォー

ブランチ feat/ENG-482-webhook-retries。コミット:「wip retries」「fix tests」。差分は webhook_deliveries にリトライ用カラムと CREATE INDEX を追加、30秒から倍増するバックオフで最大8回、WEBHOOK_RETRY_ENABLED の裏にワーカー。CI の実行結果は共有なし。

アフター

要約:失敗した Webhook 配信を再試行するようになります。30秒から倍増する間隔で最大8回(約64分)、WEBHOOK_RETRY_ENABLED の裏で、デフォルトはオフ。リスク:高。webhook_deliveries への新しいインデックス(サイズ不明)、配信が at-least-once になります。ロールバック:WEBHOOK_RETRY_ENABLED=false を設定。安全。必読 1. [Tier 1] retry-worker.ts:FOR UPDATE SKIP LOCKED がトランザクション外で実行されるため、2つの実行が同じ配信を二重送信する可能性があります。

雑なブランチから、PR 説明文とレビューの焦点へこの Skill を見る

その違いをご覧ください

赤くなった main を31分で緑に

ビフォー

11:12。northwind/web の main が #877(保存フィルター)のマージ直後に赤になる: error: relation "saved_filters" does not exist Bot、Cursor の Skill、リードの Dot がすべて稼働中。

アフター

判定:本物(確信度 高)。#877 は saved_filters を参照しますが、それを作るマイグレーションがありません。担当:Jonas。12:00 時点で main がまだ赤なら、人間が #877 をリバートします。 11:31 Jonas、Cursor の Skill:fix(orders): add the missing saved_filters migration。ロールバック:#877 と一緒にリバート、安全、テーブルは空です。 11:43 main が緑に。緑に戻るまで:31分。 翌朝、Dot:モデルがマイグレーションなしで変わったら失敗する CI チェックを追加しますか?推奨:今スプリントで追加。#877 ではレビューが見逃しました。

Risky migration PR split before the release cut

ビフォー

Wed 2026-10-14, 3:40 PM ET, northwind/platform. Priya pushes feat/PLAT-362-line-tax-rate. PLAT-362: EU invoices must show the tax rate on each line by Mon 2026-11-02. Diff, 7 files: - migration: ALTER TABLE invoice_line_items ADD COLUMN tax_rate numeric(6,4); then UPDATE invoice_line_items li SET tax_rate = i.tax_rate FROM invoices i WHERE li.invoice_id = i.id - src/billing/totals.ts and the invoice PDF read tax_rate and fall back to the invoice rate when it is NULL - 4 tests invoice_line_items holds about 38 million rows. CODEOWNERS: src/billing/ is Marco. Release cut Thursday 3:00 PM. The team runs the Skill in Cursor, the Bot's 9:00 triage and the lead's Dot at 9:15.

アフター

3:52 PM Priya, Skill in Cursor REVIEW PREP PR: platform#2011 feat(billing): show the tax rate on each invoice line Change types: Migration, Logic Risk: High because one UPDATE rewrites about 38 million rows inside the migration. Size: M, about 170 meaningful lines in 7 files. Review time about 30 to 45 minutes Must review (ranked): 1. [Tier 1] Migration, ALTER TABLE then UPDATE in one transaction. The ALTER's exclusive lock is held until commit, so every read and write on invoice_line_items waits for the whole 38 million row backfill. Move the backfill to a job: batches of 5,000 rows, idempotent, resumable from the last id, run after the deploy. 2. [Tier 1] Migration, no lock_timeout. Add SET lock_timeout = '5s' so the ALTER fails fast instead of queuing writes behind a long query. 3. [Tier 2] src/billing/totals.ts, the NULL fallback. Confirm finalized invoices keep their totals when re-rendered. 4. [Tier 3] No test mixes lines with and without tax_rate on one invoice. Can skim: invoice PDF template, test fixtures. ADD COLUMN with no default is metadata-only. Questions for the author: - Should invoices finalized before the release show a per-line rate? Missing: batched backfill job, lock_timeout. Suggested reviewers: Marco (CODEOWNERS, src/billing/) 4:35 PM Priya splits it: #2011 (column, lock_timeout, code with the NULL fallback) and #2013 (batched backfill job), both for Marco. Thu 9:00 AM Bot REPO TRIAGE Thu 2026-10-15 9:00 AM ET northwind/platform, northwind/web Main: platform green. web green. Needs review (oldest first, SLA 24 h): - platform#2011 feat(billing): show the tax rate on each invoice line. Priya, waiting 16 h, M, reviewer Marco - platform#2013 chore(billing): backfill invoice line tax rates in batches. Priya, waiting 16 h, S, reviewer Marco Sources: GitHub northwind/platform, northwind/web; Linear PLAT, WEB. Nothing missing. Approval needed: post this to #eng-outer-loop? Reply post, or edit. 9:06 Dana, outer loop owner: post 9:15 AM Dot, Slack DM to the lead DECISIONS NEEDED 1. Decision: Merge order for PLAT-362 around today's 3:00 PM release cut? Options: A) #2011 in today's release, then run the #2013 backfill Friday morning. B) Both after the cut, shipping Thursday 10/22. Recommendation: A. #2011 is additive and safe with NULL, and a backfill run this week leaves time to check it before 11/02. By when: noon today, so Marco can review #2011 before the cut Links: platform#2011, platform#2013, PLAT-362, the Bot's 9:00 triage

Incident channel to follow-ups in Linear

ビフォー

#inc-2026-09-17 export, times in ET: 10:02 deploy 2026-09-17.3 starts 10:09 checkout error rate 0.2% to 11% (dashboard) 10:21 page: checkout_5xx_rate > 5% for 10 min 10:24 Priya acks 10:31 rollback started 10:35 errors back to 0.3% Cause: new config set db pool_size to 5 instead of 50. Pipeline does not validate config values. 1,840 checkouts failed per dashboard. Ideas in thread: validate config, faster alert.

アフター

Incident lead, Skill INCIDENT SUMMARY Title: Checkout failed for 11% of requests after a config change Severity: SEV2 [confirm] Status: Resolved Duration: 14:09 to 14:35 UTC (26 minutes). Time to detect 12 minutes, time to mitigate 14 minutes Impact: 1,840 failed checkouts (dashboard). Revenue impact [confirm] Timeline (UTC): - 14:02 Deploy 2026-09-17.3 starts (deploy log) - 14:09 Error rate rises from 0.2% to 11%, impact starts (dashboard) - 14:21 Page fires: checkout_5xx_rate > 5% for 10 min, detected (pager) - 14:24 Priya acknowledges (pager) - 14:31 Rollback starts (Slack) - 14:35 Error rate back to 0.3%, mitigated (dashboard) Trigger: Deploy 2026-09-17.3 set db pool_size to 5 instead of 50. Root cause: The deploy pipeline accepts config values without range checks, so a pool too small for checkout traffic reached production. Contributing factors: - The page needs 10 minutes above 5%, so detection took 12 minutes. What went well: Service recovered 4 minutes after rollback started. Where we got lucky: [confirm in review] Follow-ups: - [prevent] Validate pool_size range in the CI config schema check. Owner [confirm owner]. Due 2026-10-01. Ticket [create] - [detect] Page on checkout_5xx_rate > 2% for 3 minutes. Owner Priya [confirm]. Due 2026-10-01. Ticket [create] Open questions: What happened in the 7 minutes between acknowledgment and rollback? Bot ISSUE TRIAGE 1. Issue: Incident 2026-09-17 follow-up: validate pool_size in CI config schema check Type: task Priority: High. Prevent item from a SEV2. Team: PLAT Labels: incident-follow-up Duplicate of: none found Missing: owner Proposed action: create a PLAT issue, due 2026-10-01, linked to the postmortem 2. Issue: Incident 2026-09-17 follow-up: page on checkout_5xx_rate > 2% for 3 minutes Type: task Priority: High. Detect item from a SEV2. Team: PLAT Labels: incident-follow-up Duplicate of: none found Missing: none Proposed action: create a PLAT issue for Priya, due 2026-10-01 Approval needed: create both Linear issues? Reply approve, or edit.

Monday hygiene sweep to the lead's decisions

ビフォー

Mon 2026-10-05, 9:00 AM ET, the first Monday of October. Weekday triage runs with the hygiene sweep for northwind/platform and northwind/web, 30-day window. In the window: 3 failed-then-passed runs of checkout.spec.ts:88 on main, all since last Monday, 6 open Dependabot or Renovate PRs, web#842 still a draft, platform#1890 untouched since Ana moved teams. The lead's Dot checks in at 9:15.

アフター

Bot HYGIENE REPORT Window: 30 days to Mon 2026-10-05 9:00 AM ET (first Monday of the month), northwind/platform and northwind/web Stale PRs: - Close: web#842 spike: new chart library. Draft, 25 days idle, no reply to last week's ping - Hand over: platform#1890 feat: bulk invoice export. 15 days idle, author moved teams Dependency PRs: - Security: web#879 next (advisory linked in PR). CI green, open 15 days - Major: platform#1975 pg-boss 9 to 10. A human must read the changelog - Minor and patch, CI green: platform#1971, platform#1972, web#895, web#896 Flaky tests: - checkout.spec.ts:88 applies discount code: 3 flakes in 7 days (runs #2190, #2197, #2205). Quarantine candidate Old unlabeled issues: - web#861 Export button misaligned in Safari (13 days) Approval needed: close web#842, and create a WEB Linear issue to quarantine checkout.spec.ts:88? Reply approve, approve 2, or edit. 9:15 Dot DECISIONS NEEDED 1. Decision: Merge the security bump web#879 today? Options: A) Review and merge today. B) Batch it with next week's dependencies. Recommendation: A. It fixes an advisory, CI is green, and it has waited 15 days. By when: end of day Links: web#879 2. Decision: Who takes over platform#1890 (bulk invoice export)? Options: A) Marco, who reviewed it. B) Close it and return the Linear issue to the backlog. Recommendation: A if bulk export is still on this cycle's plan [confirm], otherwise B. By when: Wednesday Links: platform#1890 3. Decision: Owner for the checkout.spec.ts:88 quarantine fix? Options: A) Jonas, checkout code owner. B) This week's outer loop owner. Recommendation: A, due in 2 weeks, so it never reaches the 30-day quarantine limit. By when: today Links: runs #2190, #2197, #2205

収録内容

  • Skill開発アウターループ Skill差分、赤い CI ログ、マージ済み PR を、リスクを明記した、すぐレビューに出せる文書に変えます。7 ファイル · 933 行
  • Bot開発アウターループ Bot9:00 にリポジトリをトリアージし、リリースノートを下書きする Grok のチームメイト。マージは決してしません。1 ファイル · 241 行
  • Dot開発アウターループ Dotあなたの ChatGPT dot が PR、CI、Linear を整え、あなたには決定事項だけを届けます。1 ファイル · 175 行

さらに、Bundle だけに付くプレイブックがあります。 ファイルは英語です。

engineering-outer-loop-kit-playbook.md1 ファイル · 131 行
  • Engineering Outer Loop Kit playbook

    How to run the Skill, the Bot and the Dot as one system for a team: who owns what, the order to set them up, how work moves between them, the weekly rhythm, the four numbers to…

    • What this system does
    • Setup order
    • How the pieces hand off
    • Weekly rhythm
    • Metrics that matter
    • First 30 days
    • FAQ

この Kit について

Run your team's outer loop as one system: every PR arrives with a description reviewers can act on and a ranked list of what to check, red main gets a verdict and a named owner within minutes, issues land in Linear with a team and priority, every release ships with notes, and every incident ends in follow-ups with owners. The Skill works in each engineer's editor, the Bot keeps the team's daily rhythm in Grok, and the Dot brings the lead the decisions. A playbook ties them together. Set up the whole system in about 50 minutes over two days.

What you get

  • Engineering Outer Loop Skill for Claude, ChatGPT, Codex and Cursor: PR descriptions with risk and rollback, risk-ranked review prep, CI triage, release notes and blameless incident summaries, with review checklists for five change types, a 22-type CI failure taxonomy, a postmortem template and a worked example.
  • Engineering Outer Loop Bot for Grok: five skills and three routines covering weekday 9:00 repo triage, CI triage when main fails, a weekly release notes draft, issue triage into Linear and a Monday hygiene sweep. It posts only what you approve and never merges.
  • Engineering Outer Loop Dot for ChatGPT: a responsibility pack that has your dot watch the repos and Linear, investigate bugs and prepare fixes for review, and bring merge, release and priority decisions to you, under eleven custom rules.
  • The playbook, only in the bundle: how to roll the system out across a team, including:
    • human roles, with a weekly outer loop owner rotation
    • seven production guardrails to set before the Bot posts anything
    • setup order and staggered schedules so the Bot and Dot never duplicate work
    • a handoff table for red main, new PRs, bug reports, release day, incidents and flaky tests
    • the daily, weekly and monthly rhythm
    • four metrics with targets plus three guardrail numbers
    • a week-by-week first 30 days with a team announcement
    • an FAQ

All three draw from one shared set of ten output blocks with fixed field names, so a CI TRIAGE from the Bot or a PR DESCRIPTION from the Skill can be pasted anywhere else unchanged.

Who it is for

  • Tech leads and engineering managers of teams of 3 to 30 engineers on GitHub, Linear and Slack.
  • Teams where reviews wait days, main stays red for an hour before anyone notices, and release notes are an afterthought.
  • Leads who want automation around the code with clear guardrails, not a bot with merge rights.

What it will not do

  • Merge, approve, push, revert or deploy. Every one of those stays with a human.
  • Post, comment, create issues or open PRs without approval of the exact draft.
  • Write your product code. The Dot can prepare a bug fix, but it goes through your normal review.
  • Connect to Jira, GitLab or other trackers. The Bot and Dot use GitHub, Linear and Slack; the Skill takes pasted input from anywhere.
  • Invent facts. Unknown owners, numbers and test results come back as [confirm].

Bought separately

The Skill, the Bot and the Dot cost $19 each, $57 together. The bundle is $49, saves you $8, and adds the playbook, which only the bundle includes: the team rollout plan, roles, production guardrails, handoffs, weekly rhythm, metrics and first 30 days that turn three tools into one system your team runs every week.

レビュー

まだレビューはありません。

$49個別購入 $57$57

ログインして購入
  • 買い切り。ずっと使えます。
  • 説明どおりに動かない場合は、14 日以内にご連絡ください。返金または修正で対応します。
Pro で利用可
セットアップ時間
約50分
対応 AI
ClaudeChatGPTCodexCursorGrok
連携ツール
GitHubLinearSlack
審査済み

GetKits 公式 Kit

GetKits チームが開発・テスト・メンテナンスしています。

  • GetKits が開発・テスト
  • インストールガイドとアップデート付き
  • GetKits の返金ポリシーの対象

ほかの Bundle

Bundle公式
$45

AEO Kit

購入者が「どれを選ぶべき?」と聞いたとき、ChatGPT、Perplexity、Google が名前を挙げるブランドになる。

Google DriveSlackGmailClaudeChatGPT
約45分
Bundle公式
$39

イメージディレクター Kit

フォーマット優先のプロンプト、採点されたレンダー、ぶれないシリーズで、AI 画像を「完成品」に。

NotionGoogle DriveClaudeChatGPT
約30分
Bundle公式
$39

Bot ジェネレーター Kit

手作業でこなしている仕事を、1時間以内に、安全でテスト済みの AI チームメイトに変えます。

GmailSlackNotionClaudeChatGPT
約42分
GetKits

ChatGPT、Grok、Claude などですぐに使える Skills、Bots、Dots、ワークフローが見つかります。1つの Kit に1つの業務。その日から成果が出ます。

ニュースレターに登録

マーケットプレイス

  • Kit を見る
  • Skills
  • Bots
  • Dots
  • Bundles
  • GetKits Pro

業務から探す

  • 営業
  • 会議
  • コンテンツ
  • 開発
  • デザイン
  • 画像
  • SEO / GEO
  • リサーチ
  • Bot ビルダー
  • 暮らし

会社情報

  • GetKits について
  • ブログ
  • ドキュメント
  • お問い合わせ
  • GetKits で販売

規約・ポリシー

  • プライバシーポリシー
  • 利用規約
  • 返金ポリシー

© 2026 GetKits. All rights reserved.