**Roadmap Tracker** - Automated 1M€ 18-Month Business KPI Tracking

Automated testing workflow that orchestrates unit, integration, and E2E tests with CI/CD integration

Apply DRY principle to eliminate code duplication in TypeScript projects with comprehensive refactoring patterns

This skill should be used when moving a single email message to the Archive folder in Microsoft 365 Mail. It provides a clean interface to move one specific email using its messageId without polluting the context window. Use this skill when processing bulk archive operations, moving spam emails, or any workflow requiring reliable one-email-at-a-time moves to Archive.

Generate oriented sprites using prompts.

Split a 2x2 sprite sheet into four PNGs.

**Type:** Red Team - Offensive Security Agent

Implement reactive state management with Effect Atom for React applications

Make the trading hub feel more organic without blocking roads.

4 principles for E2E testing discipline — observe first, fix in batches, expect long durations, check container state directly. NO FIXES DURING OBSERVATION RUNS.

Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition, course correction.

Use this skill whenever the user wants to design, run, or refine Cloudflare D1 schema management, migrations, and data seeding for dev/staging/production environments, especially in conjunction with Hono/Workers apps.

Build multi-step LLM agents for the Continuum system. Use when creating agent definitions with nodes, edges, tools, and execution flows. Triggers on requests to "create an agent", "build a workflow", "design an agent graph", or when discussing Continuum agent architecture. Supports parallel execution, conditional routing, tool integration, and structured outputs.

Helpers to discover, rank, and invoke repository symbols from natural language with minimal context.

Implement agent evaluation and safety gates using MLflow 3.x. Use for creating LLM-as-Judge scorers, evaluation datasets, quality gates, tracing, and continuous evaluation. Triggers on "evaluate agent", "MLflow scorer", "LLM judge", "safety evaluation", "quality gate", "agent testing", "hallucination detection", or when implementing spec/010-agent-evaluation.md requirements.

In Codex interactive mode, call delegate_autopilot automatically for multi-step or cross-cutting requests (including research-only), otherwise work normally.

Expert knowledge on creating Claude Code subagents. Use when designing or creating subagent .md files, understanding subagent structure, tool restrictions, or model selection.

Use the constraint-memory MCP tools to query/upsert timeboxing constraints stored in Notion.

Assess a codebase's readiness for autonomous agent development and provide tailored recommendations. Use when asked to evaluate how well a project supports unattended agent execution, assess development practices for agent autonomy, audit infrastructure for agent reliability, or improve a codebase for autonomous agent workflows. Triggers on requests like "assess this project for agent readiness", "how autonomous-ready is this codebase", "evaluate agent infrastructure", or "improve development practices for agents".

Provides file organization and naming conventions for the Bellog project. Triggers when creating new files or reorganizing code.