Search

SoulPolicy Python SDK — LLM behavior trust primitives (drift / guardrail / snapshot / style)

Railway-Oriented Programming for Python — Option[T] and Either[T, E] sum types with sync + async combinators, sealed pattern matching, and 100% branch coverage.

Python SDK clone for Claude Code CLI

Bootstrap a production-grade .claude/ setup into any project, instantly.

Persistent hybrid memory for AI coding assistants

A fake shell powered by raw LLM completion. The model hallucinates command output until it emits the next prompt.

Desktop-first Enterprise Capability Model studio with Git-managed JSONL storage.

Planning mode for Claude Code and Cowork. Claude pauses execution, clarifies intent, and compiles a reviewable plan before acting on complex tasks.

Real-world data science methodology as a Claude Code skill — process, not algorithms, is the work. By Data Science With Dennis.

Logic-first code review using semi-formal execution tracing. Finds behavioral bugs, type contract breaches, and interprocedural semantic mismatches that linters miss. Six skills including a full-repo autonomous audit-and-fix pipeline. Works with Claude Code, Codex CLI, and Gemini CLI.

Agent skill: read & search IMAP mailboxes from the CLI via myl. For OpenClaw, Claude Code, AgentSkills. Gmail / Yandex / Mail.ru / autodiscovery.

Clean Code principles applied to Java by Claude Code — 20 rules, 12 references, 10 before/after pairs (Spring Boot · plain Java · domain). Installable Claude Code skill.

🎭 Talk to Claude in 100% emoji. A stylized communication mode for Claude Code.

Security scanner for AI agent skills and plugins

Multi-agent decision-partner system in Claude Code for founders & PMs building new products. 9 named specialists (research, ICP, product, brand, positioning, GTM, launch, growth, strategy) with named decision moments, file-based engagement workspaces, runbooks for common scenarios. Self-contained, no paid APIs.

A standalone, zero-cost RAG hallucination evaluator.

Professional Claude Skills for AI image and video prompting. Supports Nano Banana (Gemini 3 Pro/Flash), GPT Image 2, Seedance 2.0, Kling 3.0 (multi-shot + native dialogue), Veo. Works with Claude Code, Cursor, Windsurf, OpenCode, Hermes-agent.

Claude Code plugin that reviews every edit in plain English so you approve or undo with full context.

AI Agent Skill for NSAuditor AI — gives any AI coding agent built-in knowledge of NSAuditor's MCP tools, schemas, plugins, and security audit workflows. Works with Claude Code, Cursor, Windsurf, and any MCP-aware agent.

The System Prompt Architecture that upgrades LLMs into Senior B2B Systems Architects. Enforces Zero-Defect coding via Toyota Jidoka and Inversion Thinking.