Claude Code: AI Agent Workflow Collection

A teach-while-building working mode for leveling up engineering judgment with AI. When ON, after writing any non-trivial code Claude gives a short plain-English explanation plus the one design choice it made, surfaces design decisions as options-with-tradeoffs for you to pick (never silently chooses), explains fundamentals in context (2-minute, plain English), one-tap logs anything unclear to a running learning log, and runs a 2-3 question gut-check at the end of a build session. Push-not-pull, no streaks, no guilt, no cutoffs. Applies to ANY build, not one project. Trigger on "/build-mode", "build mode on", "build mode off", "learn mode", "teach mode", or when you start a coding/build session and ask for it.

Generates a standalone, interactive HTML map of your Claude Code automation setup: a radial SVG mind-map of your skills grouped into departments, a schedule view of every scheduled task, and a feedback panel that turns flagged issues into copy-ready fix prompts. Best if you run several skills and/or scheduled agents. Trigger on "/generate-system-map", "map my skills", "generate a system map", "visualize my automations", or "build a map of my setup".

Forces the model to think twice before making any factual claim. Use to prevent false claims, fabrications, and overconfident guesses from slipping into output. Trigger on phrases like "no bullshit", "don't make stuff up", "be rigorous", "verify before claiming", "don't overpromise", "high stakes", "are you sure", or explicit /no-bullshit. Applies to anything where being wrong costs something: code, advice, research, plans, decisions, drafts, factual answers. Requires evidence or an explicit uncertainty label for every nontrivial claim. Blocks "it works" without execution proof. Requires pushback on wrong premises. Bans overpromising what the current session can actually do.

Creates viral social media hooks using proven psychological patterns and trigger words. Use when user needs attention-grabbing openings for posts, threads, videos, or content.

Anthropic's official best practices for collaborating with Claude well, distilled from the Anthropic Academy courses. Covers the 4D framework (Delegation, Description, Discernment, Diligence), Claude's real capabilities and limitations, the prompting techniques that actually move quality, and the operating discipline for Claude Code. Use when starting a build / code / design / strategy task, when deciding what to hand to AI vs keep human, when a prompt is not landing, when evaluating whether Claude's output is trustworthy, or whenever you want to work with Claude the way Anthropic teaches. Complements build-mode (teach-while-building), frontend-design (UI aesthetics), and claude-api (API/model reference); this skill is the high-level "how to collaborate with Claude" layer.