The developers behind Claude Code plugins

A cross-platform frontend kit for Codex, Claude Code, Cursor, OpenCode, etc. It helps AI coding agents work predictably and safely with existing frontend projects.

A quality-first harness for autonomous AI coding agents. It turns "the agent said it's done" into *"here's the proof — graded by an independent, default-FAIL checker."* Done is earned, not asserted.

Verified, resumable engineering loops for Claude Code. A ratchet only turns forward. Every unit of work is gated by acceptance criteria and locked in as one atomic commit — the loop never slides back, never wanders off-spec, and never loses its place.

Memory that learns and keeps itself current. A six-layer memory stack for Claude Code plus a nightly learning loop (capture, consolidation, scouts, conductor) that promotes your lessons into rules and surfaces new tools that fit your stack. Free, MIT.

An Agent Skill that generates real .pptx files — not HTML. Built on PptxGenJS with 9 pre-built design themes (5 magazine + 4 Swiss) and 32 layout templates with production-ready coordinates.

Give Claude Code a durable objective and it won't stop until the work is done. Budgets, deadlines, progress notes, idle detection, and a Stop-hook guard that keeps sessions alive across hours or days, all in a single file with no dependencies.

A lightweight journal/memory system for Claude Code with no ML dependencies. Uses simple SQLite for fast, local storage. This is a full-featured Claude Code plugin with slash commands, skills, an agent, and auto-capture hooks.

Claude Code plugin that fits the model, effort, and context to each task — fewer tokens, same quality. Deterministic policy kernel in the hooks; every number it reports is measured, not estimated.

Claude Code plugin that writes grounded, verified context for your coding agent — every claim checked against your code. Lean CLAUDE.md + deep docs, 100% local, MIT.

An AI agent skill that generates IEEE-format technical reports as LaTeX. Point it at your project, and it reads the codebase, maps requirements to sections, and produces a publication-ready .tex + .bib output with zero code artifacts in the report body.

Keeps AI coding agents consistent with the decisions your project already made. Plugin for Claude Code, Cursor, and Codex · MCP server · pre-commit and CI checks

Generate the design first, approve it, then build it. 先生成设计，确认后再实现。

give-me-job is an AI agent toolkit for Korean job applications. It helps you turn scattered career notes, a Korean job post, and company context into a focused application package: JD analysis, evidence-grounded 자기소개서 drafts, HR risk review, interview

治 vibe-coding 的病：交付物在涨，理解没跟上。 你在用 Claude Code 高速交付。但交付物里有一部分是"甩手让 AI 做了、自己没真懂"的——AI 干活时早解释过，你没接住。这个 skill 不是再讲一遍，是就着一段真实的、你在场的改动，逼你从"认得"走到"真懂、能复述、能迁移"。 它是认知健身房，不是问答 bot。先让你猜、逼你想，不直接喂答案——费力是功能，不是 bug。 哲学锚：「知之为知之，不知为不知，是知也」/「绝知此事要躬行」/「少就是多」。

mARC · Multi-Agent Relay Control — an installable AI engineering team for Claude Code. A tech-lead orchestrates specialist subagents (dev · SRE · design · security), enforces a pre-merge security gate, and runs in any repo via one plugin.

Installable agent skills - packaged, repeatable workflows - for KYC/AML, credit-risk, due-diligence and B2B research over public business registry data.

A gated build loop between Claude Code and Codex CLI. Codex writes the plan, Claude approves it, Codex implements that same plan from the same thread, Claude reviews the diff against it.

Cross-platform, dependency-free domain availability checker — runs as a plugin in Claude Code, an extension in Gemini CLI, and a skill in Codex CLI / OpenCode, or as a plain Python CLI. Ask your coding agent "is example.com free?"

An open, evidence-led agent skill for paid-media analysis and strategy across Meta Ads, Google Ads, TikTok Ads, and LinkedIn Ads.

Subtitle Optimizer 是一个 Agent skill，用来在保留 SRT 序号和时间戳的前提下优化字幕文本。它会生成候选修正版和可视化 HTML 审查台，让你逐条接受、拒绝或手动修正。

tunelab moves repetitive LLM calls — tool calling, classification, extraction — onto small local models.

Anti-hallucination plugin for academic research in Claude Code. Create literature reviews and papers guaranteed without fabricated citations.

Maximum Claude output with minimum tokens. 50+ compression patterns, 10 system prompts, benchmarked results. Star to unlock usage.

Instructions for your AI coding agent — not a library you import or an app you run.