AI & ML

iamhenry Skill

Set up and connect to an iOS simulator using argent MCP tools. Use when starting a new session, booting an iOS simulator, getting an iOS UDID, or before any iOS simulator interaction task.

iamhenry Skill

Set up and connect to an Android emulator using argent MCP tools. Use when starting a new session on Android, booting an emulator, getting a device serial, or before any UI interaction task.

rooseveltadvisors-claude-agent-stack Skill

Agent-driven memory via GCC commands. COMMIT progress, BRANCH explorations, MERGE results, CONTEXT to orient.

mae616 Skill

Agent Browser（Headlessブラウザ自動化CLI）を使ったUI検証・E2Eテスト・スクリーンショット取得の判断軸。アクセシビリティツリーベースの要素選択を優先し、壊れにくいテスト設計を目指す。

ryryo Bundle

承認済みのteam-opencode計画（task-list.json）をAgent Teamsで並行実行。 Wave式チーム実行→レビューフィードバック→クリーンアップ。 Trigger: dev:team-opencode-exec, /dev:team-opencode-exec, チーム実行, team exec

rooseveltadvisors-claude-agent-stack Bundle

Dynamic agent composition and management system. USE WHEN user says create custom agents, spin up custom agents, specialized agents, OR asks for agent personalities, available traits, agent voices. Handles custom agent creation, personality assignment, voice mapping, and parallel agent orchestration.

rooseveltadvisors-claude-agent-stack Bundle

Comprehensive research and content extraction — quick/standard/extensive/deep modes with multi-agent parallel research, content retrieval, AI trends analysis, and 242+ Fabric patterns. USE WHEN research, do research, quick research, extensive research, deep investigation, find information, investigate, extract alpha, analyze content, retrieve content, use fabric, AI trends, Claude research, enhance content, extract knowledge, interview research, web scraping, YouTube extraction, standard research.

rooseveltadvisors-claude-agent-stack Skill

Multi-mode analytical and creative thinking — first principles decomposition, iterative depth analysis, creative brainstorming, multi-agent council debates, adversarial red teaming, world threat modeling, and scientific hypothesis testing. USE WHEN first principles, decompose, deconstruct, reconstruct, challenge assumptions, iterative depth, multi-angle, deep exploration, be creative, brainstorm, divergent ideas, tree of thoughts, maximum creativity, technical creativity, idea generation, domain specific, council, debate, perspectives, quick consensus, red team, critique, stress test, adversarial validation, parallel analysis, devil's advocate, threat model, world model, future analysis, test idea, test investment, update models, view models, time horizon, think about, figure out, experiment, iterate, science, hypothesis, define goal, design experiment, quick diagnosis, structured investigation, full cycle.

trilwu Skill

Fact-check LLM-drafted technical content against primary sources — source hierarchy, programmatic existence probes for tool and plugin names, class-before-instance error triage, the truncated-negative trap, adversarial re-checking, and the verified-stamp discipline. Use when auditing a SKILL.md for factual errors, before stamping a skill verified, when a command or artifact claim needs confirming against upstream documentation, or when reviewing any drafted content whose specifics were written from model memory.

trilwu Skill

Audit Model Context Protocol servers for injection surfaces, excessive tool scope, authorization gaps, resource over-exposure, and transport weaknesses across stdio, SSE, and Streamable HTTP deployments. Use when reviewing an MCP server implementation, assessing tool definitions for injection or description manipulation risk, auditing the trust boundary between an AI agent and MCP tools, or reviewing MCP server deployment for authentication and authorization controls.

ryryo Bundle

Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, or defining reference labels for images, videos, and audio.

hidden-history Bundle

Generic and BMAD agent selection, instruction preparation, and activation routing

hidden-history Bundle

Select the appropriate LLM model for each agent based on task complexity and role

hidden-history Bundle

tmux agent lifecycle management for non-Claude providers

hidden-history Bundle

Initialize sanctum directory for an agent. Runs deterministic First Breath scaffolding — creates folder structure and writes template-substituted files.

hidden-history Bundle

Design agent team structure for parallel work execution

ryryo Bundle

画像・動画の生成Promptを新規設計し、失敗したPromptを生成サービス固有の形式へ変換する前に状況から再構築する。カメラ、構図、ポーズ、場所、家具、背景、光、人物数、参照素材の責務、動作、ショット順を作成または変更するときに使う。誤字、台詞の正確な表記、schema、生成内容を変えない時刻だけの修正には使わない。

ryryo Bundle

粗い商品・サービス・店舗情報と人物、商品、店舗などの参照素材から、MiniMax H3向け縦型リール広告の企画、Aロール／Bロール構成、T2VA・I2VA・FL2VA・L2VA・Ref2VAプロンプト、15秒超のedited・AV latent continuous・hybrid長尺方式、編集テロップ、音声設計、結合指示を作成または監査する。ECの商品販売、サロン・飲食・小売・教室などの予約・来店・問い合わせ広告、UGC風広告、商品実演、体験レポート、募集・限定告知に使う。細かな絵コンテではなく、ざっくりした入力から広告構成も考える必要があるときに使う。動画生成の実行や広告配信には使わない。

ryryo Bundle

MiniMax H3向けのモーショングラフィックス動画プロンプトを新規作成または監査する。キネティックタイポグラフィ、フラットイラスト説明広告、商品ヒーローCM、グラフィックコラージュ／タイトルシーケンスについて、T2VA、I2VA、FL2VA、L2VA、Ref2VAの正しい出力形式、秒単位のビート設計、正確な日本語・英語表示文字、参照素材の役割、音同期、可読ホールド、安定したエンドカードが必要なときに使う。動画生成の実行やプロバイダー操作には使わない。

trilwu Skill

Decide whether an agent skill, plugin, or MCP server is safe to install into an AI coding agent, where its content is loaded into a model's context and its config can run on startup. Use when reviewing a skill pack, Claude Code / Cursor / Cline plugin, or MCP server before adoption; when a repo ships a SKILL.md, .mcp.json, or plugin.json you are about to trust; or when judging whether third-party agent content can steer the model or exfiltrate an engagement.

thedaviddias Skill

Helps users discover and install agent skills. Use when they ask "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities with installable skills.

trilwu Skill

Reverse engineer and security-review Chrome/Firefox browser extensions — unpacking the CRX/XPI, reading the manifest for over-broad permissions, and tracing the trust boundary between page, content script, background service worker, and native messaging host. Use when analyzing a suspicious or over-permissioned extension, auditing your own extension's privilege model, or investigating how a content script exposes privileged APIs to a web page.

everyone-needs-a-copilot Skill

Analyze markdown files for token budget compliance. Checks word count, section lengths, and overall file size against documentation guidelines. Use proactively when creating or reviewing documentation files, knowledge-copilot pages, or when a doc might be over-budget for agent context loading.

everyone-needs-a-copilot Bundle

Use when you want to invoke codex-copilot specialist agents natively in Codex, either by selecting the right specialist skill for the main session or by mapping specialists onto real Codex spawned-agent roles for delegated work.

thedaviddias Bundle

Use when designing or improving prompts, commands, hooks, skills, or sub-agent instructions, including output quality, reliability, and token efficiency.

thedaviddias Bundle

Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Use when the user explicitly asks to threat model a codebase or path, enumerate abuse paths, or perform AppSec threat modeling.

everyone-needs-a-copilot Bundle

STRIDE threat identification with coverage checking (prose judgment) plus deterministic STRIDE coverage and DREAD severity scoring via executable script. Covers system architecture security review, trust boundaries across services, auth, payments, and PII feature pre-implementation review, and threat model refresh sessions. Use proactively when designing or reviewing a new system architecture or API, running pre-implementation security review for features touching auth, payments, or PII, conducting threat modeling sessions (initial or refresh), or reviewing another team's threat model for completeness. Run the coverage checker for deterministic STRIDE gap and DREAD scoring.

trilwu Bundle

Audit source code for exploitable vulnerabilities using threat-model-driven review, taint tracing, invariant checking, and variant analysis. Use when reviewing a codebase or diff for security bugs, performing a security audit, hunting for vulnerabilities in a target's source, or validating whether a suspected finding is real.

datamaker-kr Skill

완성된 specs/plans 문서를 Jira 이슈로 push-back 합니다 (Markdown → ADF 자동 변환). Jira MCP가 가용한 환경에서만 동작합니다.

7a336e6e Skill

Enforce safeguards specifically for AI Agents to prevent prompt injection, tool misuse, and excessive autonomy (OWASP Top 10 for Agents).

7a336e6e Bundle

Design and implement production-quality RAG (Retrieval-Augmented Generation) pipelines with hybrid search, reranking, agentic patterns, and continuous learning.

7a336e6e Bundle

Decompose requirements into discrete tasks and delegate them to the most appropriate specialist agents based on their capabilities.

7a336e6e Skill

Manage sequential and parallel execution across specialist agents, maximizing throughput while respecting task dependencies.

7a336e6e Skill

Quality gates and output validation — verify that agent deliverables meet acceptance criteria, maintain cross-agent consistency, and are ready for integration.

boltaai Bundle

Documentation of V2 execution engine - how jobs fire and agents reason through tasks (NOT a callable tool)

flonat Skill

Propose and, after approval, execute content-aware file reorganization or deduplication using a local Mac Mini model with a reversible undo record. Use when sorting a folder by file contents or finding exact and near duplicates. Always dry-runs first.