Skill UI

A specialized tool designed to manage and deploy cloud infrastructure using Terraform commands. It activates only when explicit Terraform CLI operations (such as plan, apply, or destroy) are detected. Users must specify the target workspace path and the desired action to ensure accurate and controlled infrastructure management.

This advanced methodology builds an evidence-linked causal chain from a localized fault to an actionable systemic root. It moves beyond simple proximate causes by requiring counterfactual testing, verifying multiple independent pathways, and prescribing countermeasures that eliminate enabling conditions, ensuring true recurrence prevention.

A rigorous method for authorized adversarial security review. It models the attacker, maps the entire attack surface (APIs, auth flows, data handling), and generates reports containing only findings with a concrete, reproducible exploit path and verified mitigation steps. Essential for pre-launch hardening and critical system reviews.

Coordinates authorized multi-stage security assessments including full penetration testing, external-to-domain compromise, and attack path planning. The skill acts as a central orchestrator, routing reconnaissance, initial access, privilege escalation, lateral movement, and reporting tasks to specialized sub-skills. Intended for authorized engagements only.

Discover, name, and label every LLM workflow in a repository for Caveman Cloud. Helps break LLM spend down by workflow instead of one bucket. Inventory code paths, propose a labeling table, wire gateway labels, and verify changes through the user's normal review.

A read-only repository explorer for cold-start code orientation and cross-file localization. It locates where relevant code lives using broad parallel search and returns only compact path:line citations. Use when the exact file or symbol is not yet known; skip when direct search already works.

Monitors a running mobile app's Metro terminal output to autonomously detect and fix runtime, bundle, and silent errors (empty lists, blank screens, swallowed network failures) by injecting temporary console.log traces at data-path boundaries and editing source files.

Comprehensive skill for FedRAMP certification and compliance under CR26. Covers authorization paths, Certification Classes A-D, SSP/SAP/SAR/POA&M documentation, NIST SP 800-53 control mapping, FedRAMP 20x, OSCAL mandate, 3PAO assessments, continuous monitoring, and gap assessments. Ideal for cloud service providers and security teams navigating federal cloud authorization.

Design NPC and enemy decision-making with finite state machines, behavior trees, steering behaviors, and A* pathfinding. Use for enemy AI, FSM, behavior trees, flocking, or pathfinding in games.

A comprehensive, stack-agnostic tool for deeply evaluating agent harnesses. It checks for broken code paths, redundant instructions, and the overall usefulness of agent logic using a structured, multi-stage dual-judge protocol. The process involves high-priority questionnaires (Q1, Q2) before running three defined tracks: A (Correctness), B (Redundancy), and C (Usefulness). Ideal for auditing complex agent systems before deployment or major refactoring.

This methodology guides the development of new features, product slices, or integrations while mitigating the risk of overbuilding. It mandates an architecture-first approach, requiring the definition of clear acceptance criteria and explicit non-goals. The process focuses on delivering a coherent end-to-end path across responsible system layers, omitting unnecessary configuration, polish, or complexity, and halting immediately upon successful acceptance testing.

A guided tool to manage and progress through a structured, multi-module technical learning curriculum. It tracks prerequisites, requires recording concrete evidence artifacts for completion, and implements spaced repetition reviews to ensure long-term knowledge retention in coding practices.