Jira toolkit for terminals, coding assistants, and bots.

The operations layer for agentic engineering — portable skills and contracts connecting intent, agents, software factories, and independent judgment.

claude-carbon: track the carbon footprint of your Claude Code sessions

Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md file.

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Research-first design skill for AI agents. 150K+ real app screens and flows via Refero MCP.

Switch between multiple Claude Code providers (Kimi, GLM, MiniMax, etc.) with a single command.

A thinking process, not a template. 4-stage planning framework with 21 anti-pattern checks, adversarial hardening, and 8-domain detection for Claude Code.

AI plugin to enhance and accelerate Flutter & Dart development, built by Very Good Ventures

Official plugin distribution for the hosted Zapier MCP server. Install it in your AI client and connect to thousands of apps.

🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace

27 Skills that diagnose, build, and optimize every architectural layer of your Claude environment

A reusable agent workflow kit with personas, skills, rules, and memory files.

Hand off tasks to Devin — a plugin/skill for Claude Code, Codex, Cursor, and any coding agent

Stop agents from designing sloppy UI. Inspired by Impeccable, but without the plugin machinery. Just one SKILL.md file.

AI agent skills for the personal operator's craft — decisions, research, second-brain, content rotation, scenario modeling, and meta-skills to author more. Works with Claude Code, Codex, Cursor.

Multi-agent codebase review for PRs, CI, and downstream fork syncs.

flow + prompt = flompt - Visual AI Prompt Builder. Decompose, edit as flowchart, recompile into optimized machine-readable prompts

When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deeds; fakes blocked, not warned. Each check ships at measured zero false positives. 誠

Project continuity for Claude Code and Codex: a roadmap beside your code, grounded handoffs, and clear task status.

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

A curated list of resources for Japanese natural language processing (NLP): Python libraries, LLMs, dictionaries, corpora, and datasets. Includes Claude Code skills to search resources.

AI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.

Governance standard and reference toolset for LLM-maintained knowledge corpora