my-skills

Analyze agent session transcripts to find looping behavior, missing capabilities, or token waste, and leverage framework-native concepts and skill-creator patterns to propose optimizations.

Build multi-agent systems using Google ADK with A2A protocol, deployed on Agent Engine. Use when creating agents that communicate via A2A, building multi-tier agent hierarchies, connecting ADK agents with RemoteA2aAgent, exposing agents with to_a2a(), or deploying agent stacks to Vertex AI Agent Engine. Covers leaf agents with tools, functional agents that delegate, orchestrators that route, local testing with uvicorn, and phased cloud deployment.

Build AI agents using Google's Agent Development Kit (ADK). Use when creating LLM agents with tools, building workflow agents (Sequential, Parallel, Loop), composing multi-agent systems, or developing custom agents. Covers agent creation patterns, function tools, agent configuration, session management, and running agents locally with CLI or web interface.

Deploy and manage AI agents on Vertex AI Agent Engine. Use when deploying ADK agents to production, configuring Agent Engine runtime, managing deployed agents, setting up sessions and memory, or integrating with A2A protocol. Covers deployment from agent objects and source files, environment configuration, scaling, sessions, memory bank, and agent management operations.

Sprint-based agile development with parallel agent execution. Use when the user wants to run an agile sprint, plan sprint work, conduct standups, run retrospectives, manage a backlog, estimate story points, track velocity, or coordinate parallel development across multiple agents acting as Scrum team roles (Scrum Master, Product Owner, Tech Lead, Frontend Dev, Backend Dev, QA Engineer). Also use when the user mentions sprints, user stories, acceptance criteria, definition of done, kanban, or SAFe. Triggers on: 'run a sprint', 'sprint planning', 'standup', 'retrospective', 'backlog grooming', 'agile workflow', 'scrum team'.

Clarify requirements before implementing. Use when serious doubts araise.

Autonomous research loop inspired by karpathy/autoresearch. Iteratively modify a target file (config, prompt, code), run an experiment with a fixed evaluation metric, keep improvements, discard regressions, and log everything to a TSV. Use when optimizing prompts, tuning hyperparameters, evolving agent configurations, or running overnight autonomous improvement loops.

Expert BigQuery data analysis using MCP tools. Perform schema discovery, data profiling, distribution analysis, anomaly detection, time series exploration, data quality assessment, and ad-hoc analytical queries against any BigQuery dataset. Use when the user asks to analyze, explore, profile, investigate, or query data in BigQuery, or asks questions that can be answered by querying a BigQuery dataset (e.g., 'how many users signed up last week?', 'show me the distribution of order values', 'find anomalies in the revenue data', 'what does the customers table look like?').

AI-powered browser automation using the browser-use Python library. Use when the user requests web automation tasks including web scraping and data extraction, form filling and submission, automated testing and validation, web navigation and interaction, or any task requiring programmatic browser control. Supports natural language task descriptions that are executed by AI agents.

Verifies that git commits address security audit findings without introducing bugs. This skill should be used when the user asks to "verify these commits fix the audit findings", "check if TOB-XXX was addressed", "review the fix branch", "validate remediation commits", "did these changes address the security report", "post-audit remediation review", "compare fix commits to audit report", or when reviewing commits against security audit reports.

Keep two directories synchronized by automatically copying new and modified files between them. Use this skill when you need to (1) Sync skills or code between different locations, (2) Bulk sync all skills from a source directory to target, (3) Maintain backup copies of directories, (4) Keep development and deployment folders in sync, (5) Mirror directory contents with symlink support, or (6) Set up continuous folder synchronization with watch mode.

Generate professional GCP-branded architecture diagrams using Gemini image generation models. Use when the user asks to create architecture diagrams, system diagrams, data flow diagrams, deployment diagrams, database schema diagrams, or any technical diagram styled like official Google Cloud Platform documentation. Also use when asked to visualize GCP architectures, agent systems, microservices, or service topologies. Supports gemini-3-pro-image-preview and gemini-2.5-flash-image models via Vertex AI.

Work with Google's Gemini Enterprise (Discovery Engine API) for enterprise search and conversational AI. Use when provisioning Discovery Engine apps, creating/managing data stores, ingesting documents from GCS, querying via StreamAssist or SearchService, configuring Model Armor content safety, registering external agents (A2A/Cloud Run), or integrating Discovery Engine search into ADK agents with DiscoveryEngineSearchTool. Covers the full v1alpha REST API.

Guide and recipes for managing Buganizer issues for the NovaStorm project (Component ID 2059327).

Generate high-resolution architectural and methodology diagrams from text descriptions using the paperbanana CLI. Provides an automated, iterative visual feedback loop to refine diagrams using Gemini 3 and Google Imagen. Use this skill when the user asks to "generate a diagram", "visualize the architecture", "draw an agent swarm", or "create a paperbanana diagram". Don't use for generic markdown generation or when simple Mermaid is sufficient.

Iterative development loop for solving complex tasks through trial-and-error. Use when you need to "fix until passing", "optimize until metric reached", or "iterate until done".

React + Vite frontend development with TypeScript, Tailwind CSS v4, Zustand, React Router, and Lucide icons. Use when building, modifying, or debugging React components, pages, hooks, stores, or services in a Vite-based frontend. Covers component patterns, state management, routing, API integration, testing with Vitest/Playwright, and hot module replacement workflows.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when the Gemini CLI reports errors loading agent definitions in ~/.gemini/agents/, such as unsupported 'color' keys or incorrect 'tools' formats. Provides a script to automatically fix these frontmatter issues.

Contains documentation, role definitions, and workflow guidelines for various specialized sub-agents. Use this skill when you need information on how specific agents (e.g., adk-agent-engine, frontend-dev, qa-engineer) should operate or be utilized.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Guide and best practices for creating data visualizations using Altair in Python. Always use this over matplotlib or seaborn.

Use to build deep architectural context through granular code analysis before vulnerability hunting or security auditing.

Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.

Building Secure Contracts

Burp Suite Project Parser

-- name: canvas-design description: Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the...

-- name: Collision-Zone Thinking description: Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?" when_...

-- name: Condition-Based Waiting description: Replace arbitrary timeouts with condition polling for reliable async tests when_to_use: when tests have ...

Constant-Time Analyzer (ct-analyzer)

Detects timing side-channel vulnerabilities in cryptographic code. Use when implementing or reviewing crypto code, encountering division on secrets, secret-dependent branches, or constant-time programming questions in C, C++, Go, Rust, Swift, Java, Kotlin, C#, PHP, JavaScript, TypeScript, Python, or Ruby.

Culture Index

-- name: Defense-in-Depth Validation description: Validate at every layer data passes through to make bugs impossible when_to_use: when invalid data c...

-- name: demo-enhancement-advisor description: Identify high-impact, low-effort improvements for grocery retail demos, brainstorm ways to showcase Goo...

-- name: demo-qa-coordinator description: QA test demo applications, verify documentation clarity, identify broken user flows or system issues, or coo...

Differential Review

-- name: dssib-vertex-pipelines description: Guide for deploying Dynamic Swarm (DSSIB) Fan-Out agents on Vertex AI Pipelines with ML Metadata integrat...

Analyzes DWARF debug files and understands the DWARF format. Use when interacting with DWARF files, answering DWARF-related questions, or parsing DWARF data using dwarfdump or readelf.

Analyzes smart contract codebases to identify state-changing entry points for security auditing. Detects externally callable functions, categorizes them by access level, and generates audit reports. Use when auditing smart contracts.

Scans Android APKs for Firebase security misconfigurations. Use when analyzing APK files for Firebase vulnerabilities, performing mobile app security audits, or testing Firebase endpoint security.