Agent
Independent, cold verifier of a grounding ledger before implementation or commit. Assumes every claim is wrong until the live code proves it right. Row-checks cited evidence, gap-scans for omitted load-bearing claims, and certifies that a plain-English summary matches the diff. Read-only — cannot mutate the repo. Use…
Skill Claude CodeCodex
Engineering rules and reusable patterns for building polished web UI, React artifacts, slide decks, animations, and device mockups — distilled from Anthropic's leaked Claude Design agent system prompt. Use ALONGSIDE the frontend-design skill whenever building or iterating on visual web output: single-file React/HTML…
Skill Claude CodeCodex
Profile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table or file, checking null rates and column distributions, spotting data quality issues like duplicates or suspicious values, or deciding which dimensions and metrics to analyze.
Skill Claude CodeCodex
Activate Fable mode - adopt the Fable execution playbook and the Claude Code behavior layer as standing discipline for this session. Use when the user types /fable, says "fable mode", "use fable", "work like fable", or asks for maximum-discipline execution - and PROACTIVELY at the start of any non-trivial engineering…
Skill Claude CodeCodex
Self-terminating grounding loop for a development step. Turns assertions, assumptions, and inferences into verified knowledge via an evidence-backed ledger; self-resolves code-determinable forks and logs them; escalates only genuine preference forks; spawns an independent verifier; and emits a plain-English review…
Skill Claude CodeCodex
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Skill Claude CodeCodex
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.