Skill Claude CodeCodex
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test…
Skill Claude CodeCodex
An AI product-management coaching tool that reviews assignments, product direction, competitor analysis, PRDs, and AI-agent harnesses. A PRD is a document describing what a product should do and why.
Skill Claude CodeCodex
A toolkit for planning and managing AI products from early research to evaluation. It covers activities such as user research, product design, competitor analysis, technical choices, product requirement documents, and handling bad cases where the AI gives poor results.
Skill Claude CodeCodex
A guided method for analysing bad cases in AI products, meaning examples where an AI system gives an incorrect or unwanted result.
Skill Claude CodeCodex
A method for deeply examining competing AI products, including their capabilities, workflows, and data practices. The AI Product Iceberg Model looks beneath visible features to study how a product works and where its limits are.
Skill Claude CodeCodex
A guide to processing data for AI products, from loading and cleaning it to splitting it into parts and creating embeddings. Embeddings are numerical representations used to find related content in an AI knowledge system.
Skill Claude CodeCodex
A guide for evaluating AI products and models. It covers test sets, business, product, and model metrics, and methods such as RAGAS, scoring by a language model, human review, and A/B tests.
Skill Claude CodeCodex
A guide for writing AI product requirement documents, or PRDs: documents that describe what a product should do and how it should be evaluated. It covers different AI product types, boundaries, uncertainty, and testing.
Skill Claude CodeCodex
A Chinese-language skill for planning and designing AI products, including how they use data and user feedback over time.
Skill Claude CodeCodex
A guide to discovering and managing requirements for AI products. It covers ways to collect possible needs, compare their value, and judge whether AI fits a use case.
Skill Claude CodeCodex
A method for choosing AI product technology, including whether to use AI, which architecture or model to choose, and whether to build or buy.
Skill Claude CodeCodex
A guide to researching users of AI products, including planning studies, writing surveys and interview guides, analysing research data, and checking whether a product need is real.
Skill Claude CodeCodex
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for…
Skill Claude CodeCodex
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this,"…
Skill Claude Code
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…
Skill Claude CodeCodex
Use when the user wants GPT Image 2 prompt ideas, image-generation prompt references, visual style examples, category-based image prompt inspiration, or help adapting a prompt from the YouMind-OpenLab awesome-gpt-image-2 prompt catalog. This skill is a lightweight wrapper around the local prompt library; do not load…
Skill Claude CodeCodex
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Skill Claude CodeCodex
A publishing tool for WeChat Official Accounts, the public pages used by organisations on WeChat. It can send articles or image-and-text posts through an API or a Chrome browser connection.
Skill Claude Code
OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex…
Skill Claude CodeCodex
An adversarial review method for finished plans, articles, or product decisions. It questions the main idea, removes unnecessary parts, checks for reasoning errors and biases, and can ask guiding questions when the thinking is incomplete.
Skill Claude CodeCodex
A skill for Comet's custom five-stage workflow and for creating or upgrading workflow skills managed by Comet Creator.
Skill Claude CodeCodex
A skill for the archive stage of the Comet workflow.
Skill Claude CodeCodex
A build-stage workflow for Comet, used only when explicitly requested or routed by Comet’s main runtime.
Skill Claude CodeCodex
A skill for starting or continuing Comet Classic work when the user explicitly requests it or an unfinished change can be clearly resumed. It uses project configuration to choose the right stage.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: