AI & ML

evanoman Bundle

Promote a privately owned skill into Evan's public skills repository, update the canonical agent-config registry, scrub and validate the public payload, and publish managed links to both Claude and Codex. Use when the user asks to graduate, publish, open-source, or move a personal skill into the public skills repo.

evanoman Bundle

Use when designing a new system's structure or reworking an existing one around its business domain — triggers include domain-driven design, DDD, Cosmic Python, Architecture Patterns with Python, bounded contexts, ubiquitous language, aggregates, event storming, anemic domain model, or a codebase that has sprawled and needs architectural refactoring rather than a bug fix.

pollyglot Bundle

Manage the monetization catalog, subscriptions and one-time products, as declarative files with gplay `subscriptions` and `iap`. Use when putting a catalog under version control, editing a product's prices/offers/listings, reviewing catalog drift in CI, promoting a legacy in-app product to the v2 model, or migrating live subscribers to a new price.

dzhokhov Skill

Processes meetings, transcripts, and notes: extracts decisions, tasks, facts, risks, and durable knowledge, then routes them through the vault structure. For recurring meetings with history, use context-compression first so the agent does not read the whole meeting archive.

dzhokhov Bundle

Maintains a compressed meetings/README.md for recurring meetings and long-lived contours. Use when a project has 3+ meeting summaries, when a decision is reversed, when a new meeting should update the rolling context, or when the agent would otherwise need to read the full meetings folder.

initializ Bundle

General-purpose coding agent that reads, writes, and edits code, and searches codebases.

initializ Bundle

Read Linear issues, transition state, and post comments. The entry point for ticket-driven agent workflows.

initializ Bundle

General-purpose coding agent that reads, writes, and edits code, and searches codebases.

initializ Bundle

AI-powered code review for diffs and individual files using LLM analysis

benbrastmckie Skill

Conduct Nix/NixOS/Home Manager research using MCP-NixOS, web docs, and codebase exploration. Invoke for nix research tasks.

shoji9x9 Bundle

仕様を変えないアプリケーションリプレイスで、parity-suite が採取したベースライン・ノイズ基準値・強度ゲートで検証済みの差分器を使い、現行と新側の差分を決定論的ツールで検出して分類する replace-strategy の姉妹スキル。検出は画素・特性照合・aria の 3 経路が担い、LLM には「差分があるか」を聞かず「この差分は重要か」だけを 1 件ずつ crop 対で聞いて要対応／許容／環境ノイズに分類する。新側環境は --target で選び成果物は環境別。要対応は parity-replace へ差し戻し、収束は未説明差分ゼロかつ未修正回帰ゼロ。1 回で 1 機能。replace-strategy setup・golden-dataset・対象 slug の parity-suite・parity-replace の新側 green が前提で、未完了なら捏造せず停止する。「現新の差分を検出して」「差分を分類して」「parity-diff」や --feature / --target を伴う依頼で発動する。

shoji9x9 Bundle

フロントエンド／バックエンドの変更が画面表示・コンソール・API 応答・主要コンポーネントの挙動に悪影響を与えていないかを、実ブラウザ（chrome-devtools MCP）で回帰確認するスキル。実施できる操作は環境ごとの設定（`forbidden_actions`）に従い、未定義の環境は読み取り専用として扱う。副作用を伴う操作は実施前にユーザーの承認を得る。環境とスコープからの影響ページ導出・console クリーンの確認・課題のクロス環境切り分けまで進める。バックエンドの変更もそれを呼ぶ画面を通して確認する。`browser-test setup` は対話的にプロジェクト設定を記録する。「ブラウザで確認」「画面で確認して」「browser-test」「動作確認して」「回帰がないか見て」や、`--env` / `--scope` / `--ignore-forbidden-actions` / `setup` を伴う依頼で発動する。

shoji9x9 Bundle

仕様を変えないアプリケーションリプレイスで、新旧どちらの実装にも当てられる実行可能な合否判定基準（パリティスイート）を現行アプリに対して構築し、故障注入で強度を検証する replace-strategy の姉妹スキル。論理名のロケータマッピング層と手書きの寛容な aria スナップショットで Playwright スイートを書き、API を record/replay で特性化し、視覚ベースライン（スクリーンショット・computed style・参考 aria スナップショット）とノイズ基準値を採取して parity-diff へ引き渡す。1 回で 1 機能（横断 API リソース・バッチも可）。replace-strategy setup と golden-dataset の完了が前提で、未完了・Playwright 不可なら停止する。「パリティスイートを作って」「現行アプリを特性化して」「parity-suite」や --feature <slug> / --target <name>（対象環境）を伴う依頼で発動する。

shoji9x9 Bundle

仕様を変えないアプリケーションリプレイスで、parity-suite が定義した論理名に対し新側を実装する replace-strategy の姉妹スキル。担うのは 3 つ——機能をページ単位のフェーズに分割し、新側ロケータマッピングの例外を充填し、実装役と分離した敵対的レビューを未コミット差分にかける。ブランチ作成・commit・PR は issue-start へ委譲。現行コードを一次情報源に読み、推測せず確信度を申告し、パリティスイートが新に対して green かつ検証コマンドが通れば完了（差分ゼロは parity-diff との往復の終了条件）。対象環境は --target で選び、証跡は環境別に残す。1 回で 1 機能。replace-strategy setup・golden-dataset・対象 slug の parity-suite 完了が前提で、未完了なら停止する。「新側を実装して」「parity-replace」や --feature / --target / --max-iterations を伴う依頼で発動する。

shoji9x9 Bundle

仕様を変えないアプリケーションリプレイスの入口として、現行アプリを実測して戦略を決め、機能に分解して姉妹スキル（golden-dataset / parity-suite / parity-replace / parity-diff）へ振り分けるスキル。自分では実装しない。setup（依存確認・現行環境の由来確認・対話セットアップ・測定・戦略決定・レジストリ・機能インベントリ・パッケージ選定。受領資産からの再構築は current-environment-bootstrap へ委譲）／issues（対象機能を選択して GitHub Issue を起票。issue-create へ委譲）／status（Issue とリポジトリ内成果物から現況と未検証領域を導出）の 3 モードを持つ。測定できない場合は戦略へ進まず停止する。「リプレイス戦略を立てて」「リプレイスを始めたい」「現行アプリを測定して」「replace-strategy」や、setup / issues / status・--feature を伴う依頼で発動する。

rysweet Skill

Conversational interface for managing MCP (Model Context Protocol) server configurations in Claude Code

rysweet Bundle

Expert delegation specialist that creates comprehensive context packages for coding agents, analyzes requirements, identifies relevant files, and generates clear instructions. Activates when delegating work, assigning tasks, creating delegation packages, or preparing agent instructions.

nowork-studio Skill

Discover, connect, and verify NotFair paid-ad integrations and their actual capabilities. Use when asked to connect an ad account, configure an ads MCP, check available tools, troubleshoot access, or determine whether NotFair can read or change a platform.

royalmilkteamaster Skill

供臨時開發 Agent 依已核准 Ticket 與測試接縫按需載入。以最小垂直切片執行 Red、Green 與必要時 Refactor，測試公開行為、先重現 Bug，內部迭代不逐次回報，只在 Ready for Review 提交精簡可重現證據。Implement Coordinator 不親自執行 TDD。

royalmilkteamaster Skill

供執行開發任務的 Claude 或 Codex 子 Agent 按需載入。遇到非預期錯誤、錯誤行為、不穩定測試或效能退化時，讀取既有 Spec、planning 文件、CONTEXT.md 與 ADR，重現問題、驗證根因、在正確接縫建立回歸測試或記錄替代驗證、完成最小修正，再繼續原任務。不處理 TDD 刻意產生的 Red 或尚未完成造成的預期失敗。

royalmilkteamaster Skill

為已確認需要保存、交接或重用的研究問題，依第一手來源建立一份附引用的 Markdown。當使用者明確要求研究文件，或規劃、實作與 Review 需要共同引用同一份外部證據時使用。一般不確定事實由目前 Agent 直接查證，不使用本 Skill。不替其他角色做產品、需求、架構或實作決策。

royalmilkteamaster Bundle

供臨時 Reviewer 依 Coordinator 指定的 Spec 或 Standards 軸，獨立審查固定 Snapshot，提出有證據且分級的 Findings，並定向複驗 Developer 的修正或反證。Ticket 實作完成、需要獨立 Review 時使用；不修改程式、不派 Agent、不管理共識。

royalmilkteamaster Bundle

快速設定目前專案共用的執行環境，以及 Developer、Reviewer A、Reviewer B 的 Agent、CLI、模型與推理強度。設定固定寫入專案的 `.milktea/agent-settings.yaml`，供之後所有 Implement 與 Brownfield Implement Task 直接使用；也可檢查或安裝 Reviewer B 使用的 Open Code Review。不派工、不實作。

royalmilkteamaster Skill

供執行 Git 整合的臨時開發 Agent 按需載入。當 merge、rebase 或 cherry-pick 回報 CONFLICT 或 unmerged paths 時，依 Spec、Ticket、Commit、ADR 與測試理解雙方意圖，完成合併與驗證；平時不預載。

aspi6246 Skill

Per-project glossary of key definitions, abbreviations, and command-phrases, stored in `GLOSSARY.md` at the project root. Use this skill when the user defines or asks about a project-specific term — variable names, dataset or database names, acronyms — or sets up a command-phrase (a phrase that maps to an action, e.g. "push" = commit and push the paper to GitHub). Triggers include "add to glossary", "glossary: X means Y", "define X for this project", "what does X mean here", "what does X stand for", "from now on X means Y", "show the glossary", "what's in our glossary", and "remove X from glossary". Also use proactively: offer to capture a term when the user defines one in passing, or when you hit an undefined abbreviation or variable name in their code or data. Loaded at session start by `/spin-up` so command-phrases stay active.

aspi6246 Bundle

Systematic dataset profiling protocol for empirical research. Use this skill when the user has a new dataset and wants to understand it before analysis — including unit of observation, variable definitions, panel structure, data quality, and descriptive statistics. Trigger on phrases like "explore this data", "profile this dataset", "what's in this data", "understand this dataset", "describe this data", "what are the variables", "check the panel structure", or any request to examine a dataset before running regressions.

delzarsolutionsllc Skill

Turn a vague ask into a spec an agent can build against: scope, invariants, and done-when. Use when the user asks to write a spec.

delzarsolutionsllc Skill

Model the data so the queries you will actually run stay honest as the product grows. Use when the user asks to schema.

fusedio Skill

Reference for the fused CLI — environment management, file storage, secrets, code execution, and infrastructure commands. Use when writing or explaining shell commands that invoke `fused`, or when helping users set up, switch between, or provision environments. If the commands are part of building or running a project, load `fused-projects` first for the end-to-end model.

fusedio Skill

Comprehensive guide for writing Fused User Defined Functions (UDFs). Use when helping users create, optimize, or debug UDFs, including function structure, parameter handling, performance optimization, agent-friendly design, and security best practices.

fusedio Skill

Entry-point router for the Fused skills in this repo. Use when a user asks how to get started with, set up, or install Fused, how to build a project or UDF, how to get a widget UI / dashboard out of Fused, or is unsure which Fused skill to load. Maps a goal to the specific skill(s) to read next.

fusedio Skill

Security scanning, testing, and correctness validation for code running in openfused. Use when writing or reviewing verify_code, test_code, get_audit_log calls, or when advising on security policy, spec checks, data expectations, or code quality in the fused context. If you're validating code that belongs to a project, load `fused-projects` first for the end-to-end flow.

fusedio Skill

Best practices for running code through fused's execute_code tool. Use when writing or reviewing any mcp__openfused__execute_code call — covers how to structure user code, choose a data library, handle results, and write outputs to the file store. For security scanning, spec checks, and testing see fused-verify. If this is part of building or running a project, load `fused-projects` first for the end-to-end model (and `fused-widgets` if the result is a rendered UI).

fusedio Skill

Authoring and previewing JSON-UI widgets as the response of running a project — the py-UDF-computes → json-widget-visualizes pattern, the {{ref}}/$param data grammar, how resolution runs through the compute backend, and the CLI surfaces (widget open, parley, deployed URL) that put a rendered widget in front of a human. Use whenever the desired output of a UDF/project is a widget, not raw data.

fusedio Skill

Reference for using Fused's built-in integration connections inside UDFs. Covers data sources (Snowflake, BigQuery, GCS, S3, Airtable, Notion, Google Drive), compute/inference providers (Modal, Hugging Face, Baseten, Daytona, ComfyOrg, Slack), and LLM providers (Anthropic, OpenAI) — the fused.api connect helpers, secrets access, and common operations (query, write, list, invoke, infer). Use when the user is writing a UDF that reads from, writes to, or calls out to a connected service.

heypinchy Skill

Use before opening a PR that changes docs/ or a user-visible surface (an API route, the tool registry, an agent template, the audit event catalogue, the settings navigation, plugin tools), and when the user asks to "review the docs", "check the docs", or "are the docs still right". Reads the changed prose against the code it describes. Runs locally — the deterministic guards run in CI, this is the layer they cannot reach.