Coding & Dev Tools

shoji9x9 Bundle

GitHub Issue の作成を `gh` で標準化するスキル。バグ・機能要望・タスクなどの短い説明を受け取り、対象リポジトリ確認・重複チェック・`.github/ISSUE_TEMPLATE/` のテンプレ検出・本文ドラフトのユーザー承認・`gh issue create` での起票までを進める。「Issue を作って」「課題として登録して」「バグを起票して」「issue-create」や、新しい機能要望・不具合・タスクを GitHub Issue にしたい依頼で必ず発動する。作業着手は姉妹スキル issue-start が担う。

shoji9x9 Bundle

Dependabot が作成した PR のレビューとマージを `gh` で標準化するスキル。PR URL / PR 番号で 1 件、`--all` または無指定で open な全 Dependabot PR を対象にする。CI 成功の確認 → 更新内容（changelog/release notes）からマージ影響の確認 → 判断を PR コメントに記録 → 問題なければマージ、までを進める。特に 0.x（<1.0）依存はマイナー更新でも破壊的変更があり得るため影響を確認してから扱う。「Dependabot の PR をマージして」「依存更新 PR を確認してマージ」「dependabot-merge」「dependabot の PR を全部見て」や、`--all` を伴う依頼で必ず発動する。依存更新 PR を 1 件ずつ影響判断してからマージする。

shoji9x9 Bundle

マルチエージェント環境（Claude Code / Codex / GitHub Copilot）向けのスキル・ルール・Hooks・ドキュメントのセットアップに必ず使用すること。スキルの作成・更新・削除、ルールの追加・管理、Hooksの設定、CLAUDE.md・AGENTS.md・.github/copilot-instructions.mdなどのドキュメントの整備・整理・分割・集約、プロジェクトのマルチエージェント初期化で参照する。加えて、知識・規約・処理を新たに追加する、またはドキュメントを整理・再配置するときに、それを skill / rule / hook / ドキュメントのどれに落とすか（rule なら paths を最小スコープに、ドキュメントなら基底ドキュメントか個別かを選ぶ）を判断する場面でも必ず参照する。

shoji9x9 Bundle

作成済み GitHub PR の CI エラー解消とレビュー指摘対応を、CI が成功しレビュー指摘が尽きるまで自律ループで回すスキル。PR URL を受け取り、CI 失敗の修正・レビュースレッドの返信/解決・commit/push・設定したレビューツール（Copilot/Claude Code/Codex/none）への再レビュー依頼を反復する。ループ中はユーザー確認を挟まず自律動作するが、人間判断を要する指摘だけは確認し、反映後にループへ戻る。`--max-iterations`（既定 5）で無限ループを防ぐ。レビュー対応単体は姉妹スキル pr-review-handle が担う。「PR を最後まで解決して」「CI とレビュー指摘がなくなるまで回して」「PR の CI とレビューを収束させて」「pr-finalize-loop」で必ず発動する。

shoji9x9 Bundle

GitHub PR のレビューコメント対応を `gh` で標準化するスキル。PR URL / PR 番号 / レビュー URL を受け取り、未解決レビュースレッドの確認・指摘の妥当性判断・必要な場合のみ修正・返信・解決（resolve）までを段階的に進める。全レビュアー（Copilot を含む）が対象。「レビューに対応して」「Copilot のレビューを処理して」「レビューコメントを解決して」「pr-review-handle」や、`--push` を伴う依頼で必ず発動する。ブランチ作成や Issue 着手は姉妹スキル issue-start が担う。

shoji9x9 Bundle

仕様を変えないアプリケーションリプレイスで、先方から受領した現行アプリの資産だけを起点に、比較基準として測定可能な現行テスト環境（current target）を再構築する replace-strategy の姉妹スキル。受領資産の棚卸しと「受領済み／導出可能／不足」の分類、DB スキーマ・設定の復元、データ意味論の根拠収集、先方・SME 向け質問票の生成、根拠のある範囲での最小の暫定起動データ構築、起動・認証・主要画面到達の実測、空環境からの再実行検証、current target の引き渡しを担う。型やカラム名からの推測でドメイン値を確定せず、来歴・利用許可が不明なデータは投入しない。replace-strategy setup が current.origin＝received-assets のときに委譲する。「受領資産から現行環境を再構築して」「現行テスト環境を建てて」「current-environment-bootstrap」で発動する。

rysweet Skill

Run Microsoft's eval-recipes benchmarks to validate amplihack improvements against baseline agents. Activates when testing with eval-recipes, running evals, or benchmarking changes.

rysweet Bundle

Expert workstream coordinator managing multiple concurrent tasks, tracking progress, detecting conflicts and stalls, analyzing dependencies, and ensuring smooth parallel execution. Activates when coordinating workstreams, tracking progress, checking status, or managing concurrent work.

nowork-studio Skill

Explain NotFair's paid-ads skills, installation, platform boundaries, account connections, and current product capabilities. Use for questions about how NotFair works, what it supports, how to install or connect it, plans or limits, or paid-media troubleshooting that is not an account-performance request.

nowork-studio Skill

Plan and review Amazon Ads with margin-aware ACoS, product, and search-term guardrails. Use for Amazon advertising, Sponsored Products, Sponsored Brands, Sponsored Display, ASIN targeting, Amazon ACoS, or Amazon Ads performance exports.

nowork-studio Skill

Produce a read-only, evidence-based paid-media performance review across connected platforms or supplied exports. Use for weekly or monthly reports, scorecards, performance, CPA, ROAS, CTR, spend trends, pacing, or conversion-tracking health.

nowork-studio Skill

Create evidence-based Meta ad creative briefs, copy angles, and testable asset concepts for Facebook and Instagram. Use when asked for Meta ad creative, Facebook ads copy, Instagram ad assets, UGC concepts, creative briefs, new ad concepts, or creative refreshes.

nowork-studio Skill

Create grounded paid-media creative concepts, copy angles, refresh hypotheses, and measurable test briefs across advertising platforms. Use for ad copy, creative briefs, UGC concepts, headlines, creative fatigue, asset ideas, or a creative refresh.

nowork-studio Skill

Diagnose wasted paid-ad spend, pacing, and allocation, then propose safe evidence-backed optimizations. Use for waste, negatives, budgets, bid changes, poor CPA or ROAS, underpacing, overspend, or scaling decisions.

stacksjs Skill

Use when building CLI commands or tools with Stacks — the @stacksjs/cli package for creating commands with argument parsing, option handling, colored output, tables, progress indicators, prompts, or integrating with the buddy command system. Covers @stacksjs/cli and app/Commands/.

ysyecust Skill

DjangoおよびCeleryを使用した非同期タスク処理。タスクキューイング、ワーカー管理、エラー処理、スケジューリング。Redis/RabbitMQ ブローカー統合。

ysyecust Skill

自動フック実装、イベントドリブン実行、およびルール駆動ワークフロー。

pollyglot Bundle

Ship Android releases through Google Play with `gplay releases`. Use when uploading an AAB or APK to a track, promoting a build up the internal → alpha → beta → production ladder, steering a staged rollout (halt / resume / complete), inspecting or downloading what sits on a track, attaching ProGuard/R8 mappings for vitals symbolication, sharing a private Internal App Sharing build, or managing legacy OBB expansion files.

pollyglot Skill

Sync a Google Play store listing, per-locale text and images, between an on-disk tree and Play with `gplay metadata`. Use when editing store listings or screenshots, migrating listing text into version control, localizing a listing, or gating a listing change in CI before it goes live.

royalmilkteamaster Bundle

執行已核准的 Spec 與 Tickets，協調 Developer 與兩位獨立 Reviewer，以可重現證據完成實作與審查，三方達成共識後交付成果。使用者提供專案根目錄、Spec 與 Tickets，或要求執行已核准工作時使用。

royalmilkteamaster Bundle

由使用者明確呼叫，以繁體中文獨立評估一項構想、方案或已核准設計的技術可行性、依賴、成本、時間、風險、驗證方式與成功機率區間。適合使用者詢問能否實現、是否值得做或想先取得可行性報告時使用；不屬於 grill-me 流水線，不阻擋規格或 Tickets，不修改程式。

royalmilkteamaster Skill

以繁體中文逐一確認需求、範圍、使用流程、限制、專案術語與可驗收結果。由 milktea-skills-grill-me 在需求階段調用，或在使用者要求深入釐清需求時使用；不設計架構、不判斷可行性、不寫規格。

royalmilkteamaster Skill

由 Implement Coordinator 在本次工作啟用使用情境 QA 時委派，實際操作本次成果及直接受影響流程，找出情境缺漏、不合理結果、恢復困難與使用者動向設計缺陷。只回報附證據與燈號的發現，不修改產品。

royalmilkteamaster Bundle

根據已核准需求、現有程式庫與 Milktea 專案結構偏好，以繁體中文逐一確認 Code／Data／Runtime 根目錄、資料流、模組責任、介面、Schema、整合、相容性與測試接縫。由 milktea-skills-grill-me 在架構階段調用，或在使用者要求深入釐清技術設計時使用；不改需求、不寫規格、不實作。

aspi6246 Skill

Re-explain the previous response in plain language when the user did not follow it. Use this skill when the user types "wtf", "wtf?", "huh?", "in English?", "say that simpler", "I don't follow", "you lost me", "explain that again but simpler", "eli5 that", or any short reaction signalling the last answer was too long, too dense, or too jargon-heavy. Rephrases what was already said in ASD-STE100 Simplified Technical English — it does not answer a new question or redo the work.

aspi6246 Skill

Start-of-session orientation routine that briefs Claude on the current state of a project before work begins. Use this skill when the user says "spin up", "spin it up", "let's go", "start up", "spin up the project", "punch it chewy", or any variant signalling they want a session kickoff briefing. Performs: git status check (unpushed commits, remote divergence), CLAUDE.md and README read, most-recent session log read (focusing on "Where we left off"), PINBOARD.md open items, GLOSSARY.md load, the active output style, and a short synthesis of project state. Ends by asking what to work on today.

aspi6246 Skill

End-of-session cleanup routine that captures all session work before context is lost. Use this skill when the user says "wrap up", "wrap-up", "let's wrap it up", "let's wrap up", "wind down", "end session", "that's it for today", "save and close", "let's call it", "close out", "done for today", or any indication they are finishing a work session and want everything documented before starting fresh.

aspi6246 Skill

Digital pinboard for quick project notes, reminders, and ideas. Use this skill when the user wants to jot down a note, reminder, to-do, paper to read, idea, or data issue — including phrases like "pin this", "note to self", "remind me to", "add to pinboard", "I need to remember to", "check out this paper", "look into this later", "jot this down", "don't let me forget", or any quick note the user wants saved for later. Also use when the user says "show my pinboard", "what's on my pinboard", "mark X as done", or "clear my pinboard."

aspi6246 Bundle

Diagnose and raise the general-interest ceiling of an academic economics or finance paper so it reads like a top-5 (or top-3 finance) submission. Use this skill whenever the user asks to review, reframe, or strengthen a paper draft, abstract, introduction, or pitch for a top journal — including requests like "make this more general interest", "why would the JF/QJE care", "punch up my intro", "is this framing ambitious enough", or when evaluating which of several papers or framings has the higher ceiling. Also use when advising on how to position a result relative to competing papers on the same question — even if the user doesn't mention framing or top-5 journals explicitly.

aspi6246 Skill

Use when creating a new `.Rmd` script in `Code/`, editing the `registry:` YAML block of an existing script in `Code/`, moving a `Code/*.Rmd` into `_Archive/`, or when the user says "update registry", "show registry", or "which script makes X". Before writing any new `Code/*.Rmd` script, read `Code/REGISTRY.md` first and surface existing matches before starting fresh. After any YAML change, run `Code/_Claude Scripts/build_registry.R` to refresh `Code/REGISTRY.md`.

aspi6246 Bundle

Conventions for writing empirical finance R code with data.table, fixest, arrow, and ggplot2. Use this skill whenever writing, reviewing, refactoring, or debugging R scripts for panel data, event studies, DiD, IV/2SLS, regressions, or data pipelines — even if the user just says "write some R code" or "clean this data."

delzarsolutionsllc Skill

Red, green, refactor. Write the failing test that pins the contract, then the smallest pass. Use when the user asks to TDD.

delzarsolutionsllc Skill

Reproduce first, then isolate. Turn a failing run into a root cause and a minimal fix. Use when the user asks to debug this.

delzarsolutionsllc Skill

Measure before you change. Find the real hot path, then cut latency or allocations there. Use when the user asks to this is slow.

delzarsolutionsllc Skill

Change structure without changing behavior. Keep the diff small and the tests green. Use when the user asks to refactor.

delzarsolutionsllc Skill

Write the PR a reviewer wants: intent, risk, test plan, and what you deliberately did not do. Use when the user asks to write the PR.