LLM & Agents

Unit testing framework for Python using pytest. Use when writing test cases, validating code behavior, checking test coverage, or debugging test failures.

Perform vector similarity search using embeddings. Use when implementing semantic search, finding similar documents, or building recommendation systems. NOT needed for basic content aggregation or API integration.

Implement routing strategies for warehouse order picking. Use this skill when determining optimal pick sequences, applying heuristic routing methods, calculating travel distances, or optimizing picker movements through storage areas.

Developer for Claude Orchestrator. Implements tasks according to Tech Lead instructions, applies design tokens, and reports completion. Use when asked to implement code or execute development tasks for the orchestrator.

Graph algorithms for network analysis including shortest paths, cycle detection, and connectivity analysis. Create directed/undirected graphs with weighted edges. Use when modeling currency exchange networks, detecting arbitrage opportunities via negative cycles, finding optimal trading routes, calculating path lengths, analyzing network topology, or working with any connected data structures. Supports Bellman-Ford, Dijkstra, and other graph algorithms.

Comprehensive testing guidelines for Vitest and React Testing Library. Covers quality standards, AAA pattern, naming conventions, branch coverage, and best practices. Reference this skill when creating or updating test code during Phase 2 (Testing & Stories).

Work with sparse matrix formats (CSR, CSC, COO) and algorithms. Use when implementing efficient sparse operations like matrix-vector/matrix-matrix multiplication with many zero elements.

Allocate customer orders to optimal inventory sources and fulfillment locations. Use this skill when deciding which warehouse should fulfill orders, managing split shipments, optimizing order-to-inventory assignment, or implementing allocation rules.

Balance inventory across warehouse locations for optimal fulfillment. Use this skill when redistributing stock between locations, optimizing inventory positioning, managing regional inventory levels, or planning inventory transfers.

Work with JSON data. Use for parsing API responses, config files, or structured data storage.

Manage warehouse operations including inventory control, location management, and process optimization. Use this skill when working with WMS systems, managing storage locations, tracking inventory movements, or optimizing warehouse workflows.

Optimize warehouse and storage space utilization. Use this skill when maximizing storage density, planning storage layouts, calculating volume efficiency, or minimizing empty space in warehouses and containers.

Create well-defined task specifications from plans or user prompts. Use when user wants to define a task, create a work item, break down a plan into actionable work, or write a spec for implementation. Triggers on "create task", "define task", "write spec", "break this down", "make this actionable", or when moving from planning to execution.

Guide for managing tasks within a session using bd (beads) for subtasks and local todo lists. Use this skill when breaking down plans into issues, tracking progress, managing dependencies, or coordinating work across sessions and agents. Triggers include requests to "manage tasks", "track progress", "break down this work", or questions about bd workflow.

Comprehensive mobile testing for iOS and Android platforms including gestures, sensors, permissions, device fragmentation, and performance. Use when testing native apps, hybrid apps, or mobile web, ensuring quality across 1000+ device variants.

Focus testing effort on highest-risk areas using risk assessment and prioritization. Use when planning test strategy, allocating testing resources, or making coverage decisions.

AI agents as force multipliers for quality work. Core skill for all 19 QE agents using PACT principles.

Apply the Holistic Testing Model evolved with PACT (Proactive, Autonomous, Collaborative, Targeted) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality practices.

Shared foundation for Oracle & Corrector agents. Establishes the source hierarchy for resolving conflicts between documentation, code, and specs. Load this skill first when investigating how the system works.

First-draft writing assistant for Crucible-planned novels. Use when author has completed planning (crucible-planner) and outlining (crucible-outliner) and wants to write the actual prose. Handles scene-by-scene drafting, style matching, continuity tracking, and hallucination prevention. Triggers on "write my novel," "draft chapter X," "start writing from my outline," "help me write my book," or when user has Crucible outline and wants prose output. Works with any Crucible-planned story.