#claude-code

Startup Ideation Skills

Open source agent skills for evidence-first startup ideation: capture pains, grill assumptions, design validation tests, synthesize intervie...

Lora Dataset Prep

Prepare image datasets for LoRA training (Ostris AI Toolkit / Z-Image Turbo): quality checks, captioning (templates / Claude Vision / Floren...

Agent Engineering Toolkit

Evidence-first engineering guardrails for coding agents: audit instructions, review change scope, record execution proof, and explain reposi...

Skill Lineage

Trace a skill's family tree before installing — stars reflect ancestry, not which family member is best. 装 skill 前先修谱：Star 只代表血统...

Dev Pack

Guardrails, skills, loops, hooks & review agents for database + website builders on Claude Code (Next.js + Supabase).

Wincreator

Stop your AI agent from lying about tests. Hierarchical engineering loops with machine-checkable proof gates.

Introspect

Agent-agnostic self-improvement skill: reads your Claude Code, Codex & Cursor threads and turns recurring corrections into rules in CLAUDE.m...

Manbun

What happens when a ponytail goes the other way? The manbun takes over.

Tellonce

In-session compliance enforcement skill for Claude Code (paper Sec 6 dogfood). Per-user adaptive threshold + chaos-tested install/doctor/uni...

Agenticat

Some of my skills and agents compatible with many AI coding tools

Superpipelines

Loop Engineering for AI coding agents, with real review boundaries. Your AI reviewer cannot edit code. Structurally.

Postmodernist

Postmodernist critique skill for Claude and Codex. Pressure-test AI-generated strategy and marketing slop. Debug reality.