Recently added agent tools.

Verify the bead daemon is alive and responsive

Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.

Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.

A utility to verify that the bead daemon is running and responsive, facilitating development and system monitoring.

>-

Atom.runtime, Atom.make, runtimeAtom.fn, operation atoms, Result handling. Atom-as-State doctrine for integrating Effect services with React.

Stress-test a user's plan or design by interviewing them through the decision tree until shared understanding is reached. Use when the user wants to be grilled, stress-test a plan, sharpen a design, or mentions "grill me".

Diagnose is a disciplined debugging tool that helps reproduce, hypothesise, instrument, and fix hard bugs and performance regressions in software development.

Image and video analysis powered by Isaac vision models. Capabilities include visual Q&A, object detection, OCR, captioning, counting, and grounded spatial reasoning with bounding boxes, points, and polygons. Supports streaming, structured outputs, DSL composition, and in-context learning. NOT for: generating images (analysis only).

Provide a systematic debugging checklist. Use when a junior developer is stuck and needs a structured approach.

|

Autonomous crypto trading on Base via Bankr. Use for trading tokens, monitoring launches, executing strategies, or managing a trading portfolio. Triggers on "trade", "buy", "sell", "launch", "snipe", "profit", "PnL", "portfolio balance", or any crypto trading task on Base.

An AI agent that designs tailored, actionable business strategies for print-on-demand operations, including planning, metrics, and execution steps.

CCXT cryptocurrency exchange library for Python developers. Covers both REST API (standard) and WebSocket API (real-time). Helps install CCXT, connect to exchanges, fetch market data, place orders, stream live tickers/orderbooks, handle authentication, and manage errors in Python. Use when working with crypto exchanges in Python projects, trading bots, data analysis, or portfolio management. Supports both sync and async (asyncio) usage.

Ableton Live Object Model (LOM) API reference for Python Remote Scripts and control surface development.

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this,"...

Predict metagenome functional content from 16S rRNA marker gene data using PICRUSt2. Infer KEGG, MetaCyc, and EC abundances from ASV tables. Use when functional profiling is needed from 16S data without shotgun metagenomics sequencing.

Before product-market fit, your job is to learn as fast as possible. That means doing things that won't scale - manual onboarding, concierge service, recruiting users one by one. Paul Graham's "Do Things That Don't Scale" is the bible here. This skill synthesizes the hustle playbook that creates escape velocity. Use when "keywords, contexts, " mentioned.

Export NIST OSCAL (Open Security Controls Assessment Language) JSON from

現在のブランチでPull Requestを作成し、CIステータスを確認。「/issue-pr」で使用

Azure Event Grid SDK for Python. Use for publishing events, handling CloudEvents, and event-driven architectures.

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

開發新 Agent Skills 的標準化工作流程。當使用者要求建立新技能、轉化工作流程為技能、或詢問 SKILL.md 格式時自動啟用。包含技能結構設計、YAML frontmatter 規範、觸發關鍵字最佳實踐、資源檔案組織。A meta-skill for creating new Agent Skills with standardized workflow, SKILL.md format specification, trigger keyword design, and resource organization best practices.

Update or correct an existing skill file based on judge feedback or improved understanding.

DNAnexus Integration provides a cloud genomics platform with tools and SDKs for developing, managing, and executing bioinformatics pipelines and workflows.

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.

Diagnosticá problemas de performance frontend con evidencia antes de proponer cambios. Usá esta skill solo cuando el usuario pida analizar lentitud de navegación, renders excesivos, fetches duplicados, useEffects redundantes, componentes pesados o cuellos de botella visibles.

CAPA system management for medical device QMS. Covers root cause analysis, corrective action planning, effectiveness verification, and CAPA metrics. Use for CAPA investigations, 5-Why analysis, fishbone diagrams, root cause determination, corrective action tracking, effectiveness verification, or CAPA program optimization.

Overall Equipment Effectiveness calculation skill with loss categorization and improvement analysis.

A tool that automates Sendbird AI Chatbot tasks and operations through Rube MCP workflows.

|-

Format and validate Obsidian wiki links with proper filename, section, and folder conventions. Verify links exist before creation and fix broken links. Use when creating or checking wiki links in markdown files.

|

## Overview This skill enables classification in the domain of computer-graphics (computer-science). It represents research-level-level expertise and is designed for production use in research, industry, and educational contexts. ## Description Use this skill when you need to perform classification operations related to computer-graphics. This includes tasks such as: - analyze complexity - train models - debug programs The skill leverages development environments and follows best practices estab

Knowledge base from \"Contagious: Why Things Catch On\" by Jonah Berger. Use when applying Berger's STEPPS framework for word of mouth, virality, social currency, triggers, emotion, social proof, practical value, and storytelling, studying the book, or referencing its concepts.

Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.

Generate comprehensive C4 architecture documentation for an existing repository/codebase using a bottom-up analysis approach.

Use to understand how a Journal of Personality and Social Psychology (JPSP) manuscript is judged — per-section editors, masked review, the theoretical-innovation gate, central vs. peripheral limitations, and decision categories. Sets expectations; it does not predict any specific editor's or reviewer's verdict.

Generate comprehensive C4 architecture documentation for an existing repository/codebase using a bottom-up analysis approach.

An AI agent that builds and operates compliance evidence mapping to ensure measurable and validated outcomes in lifelong learning plans for operational governance and oversight.

UX designer and UI specialist. Use when the user asks to talk to Sally or requests the UX designer.

Generate comprehensive C4 architecture documentation for an existing repository/codebase using a bottom-up analysis approach.

Configure deployment settings for /land-and-deploy.

Frontend design system utilities with component libraries, theme management, responsive design tools, and accessibility features.

Generate comprehensive C4 architecture documentation for an existing repository/codebase using a bottom-up analysis approach.

>

Use this skill for Pest PHP testing in Laravel projects only. Trigger whenever any test is being written, edited, fixed, or refactored — including fixing tests that broke after a code change, adding assertions, converting PHPUnit to Pest, adding datasets, and TDD workflows. Always activate when the user asks how to write something in Pest, mentions test files or directories (tests/Feature, tests/Unit, tests/Browser), or needs browser testing, smoke testing multiple pages for JS errors, or archit

Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.

Prüft unzitierte Tatsachenbehauptungen über die reale Außenwelt – Produkte, Institutionen, Zahlen, Funktionsansprüche –, die keine Quellenangabe tragen und deshalb für Teil-Check G, Stresstest und Autoref-Check unsichtbar sind. Läuft als kalte, isolierte Sitzung ohne Projektstatus, Prüfbericht und Änderungshistorie, verifiziert jeden Kandidaten einzeln per Websuche und schreibt faktencheck-bericht.md. Nutzen, sobald alle Kapitel FERTIG sind und ein Marktüberblick, eine Wettbewerbsanalyse, eine W

プログラミング演習のアシスタントおよび出題者として振る舞うスキル