Analyze ML model architecture from papers and code. Use when understanding model structure for implementation.

Ignore file management for .gitignore, .dockerignore, and .specstory directories. Includes synchronization, alphabetical ordering, organization, best practices, and testing guidelines. Activate when working with .gitignore, .dockerignore, .specstory files, or managing version control and Docker build context.

GLM-4.6v image analysis subagent for game screenshot and sprite quality assessment

Batch image processing: resize, crop, watermark, color correction, format conversion, compression. Quality presets for web, print, and social media.

Generate website images with Gemini 3 Native Image Generation. Covers hero banners, service cards, infographics with legible text, and multi-turn editing. Includes Australian-specific imagery patterns. Use when stock photos don't fit, need text in images, or require consistent style across assets. Prevents 5 documented errors.

ImageAgent - Generate EVOLEA Brand Images with Reinforcement Learning

image-generator

Generate AI images using Gemini image generation API. Use this skill when content needs images - thumbnails, social posts, blog headers, or creative visuals. Follows an iterative workflow - brainstorm concepts, select direction, generate in multiple styles, then produce via API.

Generate and edit images using AI models via OpenRouter. Supports Nano Banana Pro (Gemini 3 Pro Image), FLUX, and other image generation models.

Guide for using ImageMagick command-line tools to perform advanced image processing tasks including format conversion, resizing, cropping, effects, transformations, and batch operations. Use when manipulating images programmatically via shell commands.

Generate blog post thumbnails for Skill Stack using the brand aesthetic. Follows an iterative workflow - brainstorm concepts, get approval, generate with Gemini API.

Write clear, emotionally resonant, and well-structured content that readers remember and act upon. Use when writing or editing any text—Twitter posts, articles, documentation, emails, comments, updates—for maximum clarity, engagement, and impact.

'Execute refactoring tasks from a task file with parallel agent orchestration'

Orchestrate spec-to-PR workflow with session tracking, worktree isolation, and audit trail

Implement features using Test-Driven Development (TDD). Executes red-green-refactor cycle, uses bmad-commands for file operations and testing, verifies acceptance criteria. This skill should be used when implementing new features or functionality from task specifications with test coverage.

>

Executes implementation tasks using Test-Driven Development, prevents code duplication through anti-duplication checks, and maintains quality through continuous testing. Use when implementing features from tasks.md, during the /implement phase, or when the user requests TDD-based implementation. (project)

Create feature implementation plans before development. Captures requirements, acceptance criteria, non-goals, risks, and implementation complexity in structured markdown. Use when starting a new feature to ensure scope clarity and implementation guidance.

Use when you have specifications or requirements for multi-step implementation tasks requiring comprehensive documentation for handoff

Master orchestrator that generates all implementation specs (PRD, Architecture, UX, Implementation, Test, Release) from product plan. Use when generating complete specification package.

Use after implementation complete to verify all tasks done, update roadmap, run full test suite, and create final report - ensures implementation completeness before finishing development branch

Implement features with code, tests, and documentation. Use when building

Complete TDD workflow for implementing business logic (use cases) and API endpoints that make tests pass. Covers Zod safeParse validation, async/await patterns, Next.js API routes, service orchestration, and Clean Architecture compliance.

Write production-quality code following project patterns. Use when implementing features, fixing bugs, or creating new files. Includes Context7 library documentation lookup.

Implements new Agent Skills for the project. Identifies the AI coding tool (Cursor, Claude Code, Gemini CLI), ensures specification compliance, and provides specialized templates. Use when creating, authoring, or adding a new skill, or when the user asks about Agent Skills format or SKILL.md.

Implements CLI user experience with output formatting, progress indicators, and interactive prompts. Uses chalk, ora, and inquirer for consistent terminal interactions. Triggers on: CLI output, progress bar, spinner, ora, chalk, inquirer prompts, error formatting, exit codes, reporter.

Write clean, efficient, maintainable code. Use when implementing features, writing functions, or creating new modules. Covers SOLID principles, error handling, and code organization.

Implements drag-and-drop and sortable interfaces with React/TypeScript including kanban boards, sortable lists, file uploads, and reorderable grids. Use when building interactive UIs requiring direct manipulation, spatial organization, or touch-friendly reordering.

Import brownfield documentation from Notion exports, Confluence, GitHub Wiki, or any markdown folder. Automatically classifies files as specs, modules, team docs, or legacy.

AUTO-EXECUTE import of external work items (GitHub/JIRA/ADO) since last import. NO PROMPTS - immediately runs with defaults. Creates READ-ONLY references in living docs. Options available but NOT required.

Analyzes conversation history to improve CLAUDE.md files. Use when you notice patterns in how Claude misunderstands requests, want to consolidate repeated guidance, or improve instruction clarity based on actual usage.

Improve skill(s) by analyzing the current session.

Systematically work through TBTA features using the 6-stage STAGES.md workflow. Use when user wants to improve TBTA features, work on TBTA, or continue TBTA feature work.

Expert at automatically applying improvements to Claude Code components based on quality analysis. Enhances descriptions, optimizes tool permissions, strengthens security, and improves usability. Works in conjunction with analyzing-component-quality skill.

Improve existing agent skills based on user feedback and best practices. Use when the user wants to fix, enhance, or refactor an existing skill. Gathers user feedback first, then applies technical analysis and implements improvements.

use to query historical data on the IMSA Weathertech seasons

Expert guidance for building and maintaining the Para Obsidian inbox processing system - a security-hardened automation framework for processing PDFs and attachments with AI-powered metadata extraction. Use when building inbox processors, implementing security patterns (TOCTOU, command injection prevention, atomic writes), designing interactive CLIs with suggestion workflows, integrating LLM detection, implementing idempotency with SHA256 registries, or working with the para-obsidian inbox codebase. Covers engine/interface separation, suggestion-based architecture, confidence scoring, error taxonomy, structured logging, and testing patterns. Useful when user mentions inbox automation, PDF processing, document classification, security-hardened file processing, or interactive CLI design.

Comprehensive incident root cause analysis skill for distributed systems. Analyzes logs, metrics, and traces to identify cascading failures, resource contention, and root causes through systematic anomaly detection, timeline correlation, and evidence-based hypothesis testing.

Create actionable runbooks for common incidents.

Use when writing code, documentation, or comments - always use accessible and respectful terminology

Generate culturally diverse names for examples, mock data, and test fixtures. Includes edge-case names that catch bugs.

AI-powered quality assessment using LLM-as-Judge pattern with BMAD risk scoring and formal gate decisions. Use for evaluating increment specs, assessing task completeness, or making quality gate decisions (PASS/CONCERNS/FAIL). Chain-of-thought reasoning ensures transparent evaluation.

Use when implementing features or refactoring with TDD - enforces writing ONE test at a time, implementing minimal code to pass, then repeating, preventing batch test writing that defeats incremental design discovery

Generate hierarchical AGENTS.md knowledge base for a codebase. Creates root + complexity-scored subdirectory documentation.

Deep domain research and expertise synthesis across industries, combining academic research, market intelligence, and practitioner knowledge

Specialized agent configurations for specific industries

Systematic research protocol for discovering novel AI-native software businesses in the synthetic workforce era. Maps capability trajectories, analyzes segment-problem spaces, generates business models, and calculates inevitability scores across 3-24 month time horizons. Use when exploring AI business opportunities, conducting market research, or identifying automation-native ventures.

Эксперт influencer outreach. Используй для шаблонов писем, partnership proposals и collaboration briefs.

infra-adoption