ai-product skills

65 tagged ai-product, measured the same way as everything else here.

Browse within: ai-native 60methodology 60product-management 58公众号 27book-skill 19p0, 需求发现, 编排器 12orchestrator 5

gmaxxxie/ai-native-product-agent-skills

Skill Claude CodeCodex

A practical method for auditing an AI product or system before release. It examines design evidence, evaluation evidence, and shadow evidence, then defines release limits and a go/no-go decision.

45 3mo ago A 83 tokens

gmaxxxie/ai-native-product-agent-skills

Skill Claude CodeCodex

A method for operating an AI product after launch or during preparation for launch. It covers monitoring, metrics, failure handling, human corrections, feedback, and business or customer feedback loops.

45 3mo ago A 138 tokens

ai-product-teardown

04

w93139/ai-product-teardown

Skill Claude CodeCodex

Reverse-engineer an AI product from authenticated UI evidence, including autonomous screenshot collection when safe browser or desktop controls are available, producing traceable user journeys, Agent I/O contracts, functional-equivalent prompts, or layered product architecture. Use for read-only product teardowns…

5 8d ago A 88 tokens original MIT

prd-for-ai-products

05

WYY-gogogo/prd-for-ai-products

Skill Claude CodeCodex

A guided workflow for turning ideas for AI products into product requirements documents (PRDs), which describe what to build and why. It asks structured questions, adds AI-specific sections, checks the result four ways, and rates its quality.

1 1mo ago A 100 tokens

to-real/cognition-workbench

Skill Claude CodeCodex

Proactively retrieve and apply the user's personal cognition when doing AI or product strategy, model evaluation, competitor analysis, product planning, implementation assessment, business judgment, or related writing. Use even when the user does not mention the knowledge base. Do not use for unrelated coding…

0 28d ago A 66 tokens original MIT

discuss-cognition

07

to-real/cognition-workbench

Skill Claude CodeCodex

Guide an incremental, evidence-aware discussion that turns an AI, product, model-strategy, competition, or implementation topic into durable personal cognition. Use when the user wants to discuss, learn, explore, compare, challenge, or deeply understand such a topic, including a recommended daily topic. Ask one…

0 28d ago A 80 tokens original MIT

to-real/cognition-workbench

Skill Claude CodeCodex

Select and propose exactly one high-value daily topic at the intersection of AI and product, using current developments, durable learning value, and gaps or conflicts in the user's cognition. Use for daily recommendations, today's topic, scheduled topic discovery, or when the user asks what is worth discussing now. Do…

0 28d ago A 70 tokens original MIT

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: