Art & Design

Evidence-first scientific manuscript revision and title optimization for Cell, Nature, Science, and leading conferences—natural academic English, verified citations, scientific figures, three-line tables, editable SVG, and clean-submission DOCX QA.

Agent skills for auditing and explaining software repos — committed HTML audit reports, codebase explainers, one shared design system. Claude Code, Cursor, Codex and any Agent Skills harness.

Reusable Claude Code skills for builders: Figma MCP design/build, Fusion 360 CAD, LangGraph agents, LangSmith evals, After Effects ExtendScript.

Build and operate an agent-friendly Notion library for Skills, Prompts, MCPs, Apps, and Workflows.

Curated Agent Skills for webapp audit, GAS webapps, debugging & design — publish-ready SKILL.md (opencode/claude/cursor compatible)

Two verifiable Agent Skills for human UI review and clear input-output value covers.

A two-stage Codex skill for black-and-white line art and five-ink Riso comparison posters.

AI agent skills and a signed Go CLI for BroSettlement onboarding, API integration, and WebSocket events.

Curated, tested AI agent skills for Codex and compatible runtimes

Secure Acceptora verification skill for Codex, Claude Code, and Gemini CLI with MCP, REST, completion gates, and offline recovery.

Make a cheap model perform like an expensive one on your MCP server — by changing the server, not the prompt. An Agent Skill that measures the weak/strong model gap and closes it with additive, evidence-backed tool-surface changes.

从 Git 历史与 AI 编程会话中重建项目故事，发现返工、回滚和时间黑洞，生成项目复盘、作品集与真实简历证据。

Open-source Agent Skill for careful French/EU legal drafting and document review, with anti-invention safeguards, GDPR/RGPD analysis and consistency checks.

A Codex skill and workflow for semi-DIY graduate application PS revision.

Agent toolkit for log-driven runtime tracing and evidence-based debugging.

The Open-Source AI Agent Skill for generating pixel-perfect, high-resolution, branded quote cards.

A teaching skill for AI coding agents — teaches from your level, then verifies real learning by restatement. Adapted from Matt Pocock's teach (MIT).

Obsidian-backed PRDs for unsettled product decisions and Lean execution for settled technical work—across Claude Code, Codex, and OMP.

Skill for standardized browser debug approach for AI models

The CamScanner CLI Skill provides a complete document processing toolkit through the `camscanner-cli` command-line tool and the CamScanner AI Tools API. It supports image enhancement, OCR, format conversion, watermarking, translation, restoration, merging, and related operations. Results can also be saved to the user's CamScanner account.

An AI operating system you own: five layers, Constitution, Memory, Skills, Tools, Focus. Send this to your AI and it builds you one.

Evidence-first agent skill for auditable statistical analysis, diagnostics, publication figures, tables, and teaching reports from real research data.

Helix is ​​a powerful self-learning AI agent with memory, skills, and the ability to recall tools. It learns from successful tasks and creates reusable skills for the future.

ActonOS is a single-purpose appliance operating system engineered as a customizable, self-governing AI agent kernel running 24/7.