AI & ML

treasure-data Skill

Use when the user wants to review, validate, or check a scheduled task before enabling it. Runs two parallel sub-agent checks — structural validation and quality assessment. Triggers on "review this task", "check my scheduled task", "validate task", "is this task ready", etc.

treasure-data Skill

Run automated tests for Treasure AI Foundry agents using `tdx agent test`. Covers test.yml format with user_input/criteria, single and multi-round tests, evaluation by judge agent, and criteria development workflow.

treasure-data Skill

Write effective system prompts for Treasure AI Foundry agents. Covers role definition, constraint specification, output formatting, tool usage instructions, and prompt structure patterns.

treasure-data Skill

Use when the user wants to create, configure, schedule, or run an agent in Treasure Work. Covers AGENTS.md authoring, the `agent_*` MCP tools, on-demand vs scheduled agents, lifecycle (draft → active → paused), and chat-based result inspection. Triggers on "create an agent", "set up an agent", "schedule a task", "set up a recurring job", "automate daily report", "cron job", "run X every weekday", etc.

meaningfy-ws Bundle

The shared, representation-agnostic modelling craft reused across the modelling skills — naming discipline, modelling anti-patterns, and the guardrails a modeller follows while working, plus the two load-bearing principles (decouple attributes into reusable first-class properties; identify everything by a stable URI, implicit by default). Use when authoring or reviewing ANY model regardless of representation (conceptual, UML, LinkML, ontology). Trigger on "modelling conventions", "naming conventions for a model", "modelling anti-patterns", "reusable properties/slots", "should this attribute be shared", "URI/identity discipline", "review this model for smells". This is the cosmic-python-style reuse layer for modelling — cited by conceptual-modelling and linkml-engineering, never restated by them.

forgivesam168 Skill

Context structuring and conflict detection for AI-assisted development. Use this skill when: making technical decisions that require understanding full project context, detecting vocabulary or terminology conflicts before implementing, generating or updating CONTEXT.md for persistent project memory, or when architect-agent needs to ground decisions in project-wide context. Triggers on: "context engineering", "context conflict", "vocabulary mismatch", "update context", "project context", "CONTEXT.md", "context bootstrap". Do NOT trigger when doing routine code implementation (use tdd-workflow), simple Q&A, or single-file edits with no cross-cutting concerns.

mmcmedia Bundle

Analyze task complexity and recommend the optimal agent (haiku, sonnet, codex, opus) for spawning sub-agents. Use before sessions_spawn to optimize cost and performance.

treasure-data Skill

Use when the user wants to review, validate, or check an agent before activating it. Runs two parallel sub-agent checks — structural validation of `AGENTS.md` against the schema, and a quality assessment against the user's intent. Triggers on "review this agent", "check my agent", "validate agent", "is this agent ready", "review the agent before activating", etc.

aki2022 Bundle

Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB model context protocol (MCP) tools for automated database operations.

zoom Bundle

Zoom Meeting SDK for Windows - Native C++ SDK for embedding Zoom meetings into Windows desktop applications. Supports custom UI architecture with raw video/audio data, headless bots, and deep integration with meeting features. Includes SDK architecture patterns and Windows message loop handling.

victory-hugo Skill

MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具，让 AI 助手连接外部能力

victory-hugo Skill

Make websites accessible for AI agents. Navigate, click, type, extract, wait — using Chrome with existing login sessions. No LLM API key needed.

victory-hugo Skill

在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。

aki2022 Bundle

複数のコーディングエージェント（Claude Code / Codex CLI / Antigravity・Gemini CLI 等）の 設定ファイル、スキル、commands、非秘密のMCP設定を symlink で単一ソースに統一する規約と手順。正典は `.agents/` （グローバルは `~/.agents/`、リポジトリ単位はリポジトリルートの `.agents/`）。 必ずこのスキルを使うこと: CLAUDE.md / AGENTS.md / GEMINI.md / skills.md などのエージェント 設定ファイルや `.claude/skills` `.agents/skills` `.codex/skills`、複数account間で共有する commands / MCP設定を**新規作成・編集・移動・削除** しようとする時、「設定を共通化／統一」「symlink で揃える」「新しいリポジトリにエージェント設定を入れる」 と言われた時、あるいは既存の symlink 構成を壊しかねない操作（symlink を実体ファイルに置換、別の場所へ コピー作成、正典ディレクトリの削除）をしようとする時。グローバルでもリポジトリ単位でも適用される。 スキルの静的チェック（lint）もこのスキルが所有する。「スキルを改善したい」「スキルの品質を チェックして」と言われた時もこのスキルを使う。トラブル・摩擦の**記録**は所有しない （`origin-trouble-log` が所有する）。

aki2022 Bundle

Send and receive transactional emails with Cloudflare Email Service (Email Sending + Email Routing). Use when building email sending (Workers binding or REST API), email routing, Agents SDK email handling, or integrating email into any app — Workers, Node.js, Python, Go, etc. Also use for email deliverability, SPF/DKIM/DMARC, wrangler email setup, MCP email tools, or when a coding agent needs to send emails. Even for simple requests like "add email to my Worker" — this skill has critical config details.

aki2022 Skill

Set up or update vibe-guard security guardrails for an AI-assisted coding repository (git pre-commit/pre-push hooks, gitleaks secret scanning, local-info detection, agent bypass rules). Use when bootstrapping a repo's guardrails, running `vibe-guard doctor`/`repo-bootstrap`, or when a security check blocks a commit/push and the user asks how to remediate without bypassing it.

iamhenry Bundle

Run Argent skills to drive, test, debug, profile, and prove iOS, Android, TV, and Chromium apps on simulators, emulators, and physical devices using the `argent` CLI without an LLM in the loop. Use whenever a task mentions Argent, a flow YAML, argent MCP tools, device interaction, UI testing, profiling, Metro debugging, screen recording, screenshot diffs, or on-device user-flow proof, or when an iOS repro or verification task needs a replayable device flow. Builds and mechanical proof stay with xcodebuildmcp-cli; use that skill instead for compile/build/test commands.

ryryo Bundle

docs/PLAN 配下の計画書ファイル（tasks.json v2）のフォーマット不整合を検出・修正し、 ダッシュボードでの表示問題を解決するスキル。 スクリプトによる自動チェック（構造・整合性・パースシミュレーション）を第一手段とし、 解決しない場合は LLM エージェントが原因を調査する。 Trigger: 計画書が壊れた, プランの修正, 計画書のフォーマット直す, /dev:fix-plan, plan fix, plan broken, ダッシュボードに表示されない

firef1ie Skill

Use AgentPMT external API to run the Document OCR Agent tool with wallet signatures, credits purchase, or credits earned from jobs.

iamhenry Bundle

Design a closed autonomous loop for a measurable goal. Use when the user wants to create an agentic loop, digital worker, autonomous operator, long-running agent, or SKILL.md that can observe act verify record and continue with minimal human intervention.

iamhenry Skill

Shape a messy workflow or system into one simple reliable flow. Use when the user wants to design a process, reduce brittleness, define owners, choose one source of truth, or turn an idea into a minimal operating model.

iamhenry Skill

Obtain independent read-only critiques through `opencode run`. Use when the user asks for a second opinion, asks Grok/Luna/GLM/Kimi/Sol/DeepSeek/Opus/Fable, wants multiple models to review something, compare model opinions, or use OpenCode run for critique.

zircote Bundle

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

ryryo Bundle

承認済みの team-plan 計画（task-list.json）を Agent Teams + Subagent ハイブリッドで並行実行。 Git Worktree でファイル分離。Delegate mode / Plan Approval / hooks にフル準拠。 Trigger: dev:team-run, /dev:team-run, チーム実行, team run

ryryo Bundle

Codex Plan Mode 専用。docs/PLAN/{YYMMDD}_{slug}/ に schema v3 仕様書を作成する。 Gate 契約 (Goal / Constraints / Acceptance Criteria)、Mermaid 図、Cursor Agent 委任ヒントを含む。 Trigger: spec-codex

iamhenry Bundle

Reusable verification gate for completed work before commit or merge. Use when implementation is done and Claude must prove the task works, verify the main user flow, route verification by platform, and return a PASS/FAIL/BLOCKED verdict with evidence. Web and mobile-web verification uses agent-browser. iOS and macOS verification uses xcodebuildmcp-cli, with argent flow replay for iOS user-flow proof.

iamhenry Bundle

Shape a rough product or engineering idea into an implementation-ready behavior contract using project evidence, current external sources when needed, and the multi-model Council. Use only when the user explicitly asks for shape-with-council, /shape-with-council, or says to shape something with Council. Stops for human approval before updating the canonical project ISA and never implements code.

firef1ie Skill

Use AgentPMT external API to run the Create 3D Model From Image tool with wallet signatures, credits purchase, or credits earned from jobs.

firef1ie Skill

Use AgentPMT external API to run the Text to 3D Model Generation tool with wallet signatures, credits purchase, or credits earned from jobs.

ryryo Bundle

事前設計が必要な中〜大規模作業についてrepositoryを調査し、依存関係・設計境界・複雑さ・判断の確定度・実装の独立性・副作用・検証oracle・実行主体・UI/UX契約・統合順・完了条件を持つsingle-md計画を `docs/PLAN/{YYMMDD}_{slug}.md` に作成して実行する。fixedまたはboundedな判断、独立した実装、排他的write scope、再現可能なoracle、可逆な副作用を備えた実装をheadless Cursor CLIへ委任する。Codex subagentは独立した調査・比較・監査・障害分析・レビューに限定する。Trigger: cursor-agent-delegate、Cursorで計画、worker委任計画、依存関係やUI受け入れを設計して実装

ryryo Skill

日本語の技術文書・書籍原稿の文章規範。整形（一文一行、引用ブロック、脚注、コラム記法）、段落と論証の構成（パラグラフライティング）、論証の厳密さ（ツッコミどころの除去）、読み手の負荷の管理、視点と語り、演出の抑制、LLM っぽい空句の禁止、冗長の排除を定める。日本語で技術書の章、草稿、記事、解説文を書くとき、または推敲・リライトするときに使用する。

ryryo Bundle

main Codex を既定の実行主体とし、fixedまたはboundedな判断、independentまたはstagedな実装、排他的write scope、再現可能なoracle、可逆な副作用を備えたtaskを `cursor agent --print --yolo --trust --model composer-2.5-fast` に委任する。`.codex/tmp/YYMMDD_slug/` 配下で短い実行状態を管理し、docs/PLAN は作らない。Trigger: cursor-agent-sprint-cli、Cursor CLI sprint、headless Cursor Agent 並列実装、CLI worker sprint、Cursor を使って計画を実装

ryryo Bundle

Image Genツールを使う画像生成スキルの共通実行規約。生成前のtaskとmodel決定、output配下への採用画像保存、候補画像、prompt/request/reviewメタデータ、目視確認、採用画像の扱いを統一する。generate-t2i系スキルやその他Image Gen前提のスキルが共通出力契約を必要とするときに使用する。

ryryo Bundle

Claude Agent SDK（Python / TypeScript）を使った機能実装の設計をサポートするスキル。 ヒアリング型ワークフローでユーザーの要件を明確化し、 公式ドキュメントに基づいた最適なアーキテクチャと実装パターンを提案する。 Trigger: Agent SDK, claude_agent_sdk, claude-agent-sdk, ClaudeAgentOptions, ClaudeSDKClient, Agent SDKで, エージェントSDK, エージェントを作りたい, agent-sdkを使って, query(), createSdkMcpServer, サブエージェント構成, agent architecture

iamhenry Skill

Autonomously test an app UI (iOS or Android) by running interact-screenshot-verify loops using argent MCP tools. Use when testing UI flows, verifying login works, testing navigation, running end-to-end UI test scenarios, manual QA steps, visible UI changes, or visual behavior.

iamhenry Bundle

Interact with an iOS simulator, Android emulator, or Chromium (CDP) app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, waiting for an element to appear or disappear, or checking visible app state after interactions.