#claude-code

Introspect

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

Dev Pack

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

Manbun

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

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...

Wincreator

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

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...

Postmodernist

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

Superpipelines

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

Tellonce

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

Kroki Diagrams

Agent skill for generating clean Kroki diagrams, interactive SVG viewers, and auto-built diagram indexes.

LLM Wiki Pm

PM knowledge base skill for Claude Code. Karpathy's LLM Wiki pattern with supersession, privacy, crystallize, and qmd hybrid search.