SOTA-skills: Structured Engineering Best Practices for AI Coding Agents

Repositorymartinholovsky/SOTA-skillsTool

SOTA-skills is a collection of 42 modular engineering skills for AI coding agents such as Claude Code. It introduces build and audit rules via a dynamic loop rather than relying on bloated prompt dumps.

Key points

  1. Provides 42 skills across 336 files covering software architecture, secure coding, cloud, and compliance.
  2. Supports two distinct operating modes: BUILD and AUDIT.
  3. Employs a targeted routing loop: instruction files stay under 500 lines, restate active rules per turn, and verify compliance before finishing.
  4. Reports an increase in best-practice coverage from roughly 59% to 98% compared to unguided models.
  5. Natively supports Claude Code, Antigravity CLI, Codex, and agents supporting AGENTS.md.

Why it matters

AI coding assistants frequently drop critical requirements like rate limiting, tests, and structured logging as context windows grow. Modular skill routing preserves engineering standards throughout long-running tasks.

Analysis

Martin Holovsky's repository addresses context degradation in AI coding agents. By restricting individual instruction files to under 500 lines and loading rules conditionally, the system keeps essential standards active without polluting context memory. Installation is handled through Claude Code plugins or a shell-based symlink script. With 22 stars and two forks as of October 2026, the project is still at an early adoption stage, but its documented evaluation results and dual BUILD/AUDIT modes make it a practical tool for teams standardising agent workflows.

Found in

Summary generated by AI (Gemini 3.8 Flash, 7 October 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Repository:coleam00/skills

    Cole's AI Skills: Modular Skill Files for Coding Agents

    The GitHub repository 'coleam00/skills' provides a collection of 33 practical skills designed for AI coding agents such as Claude Code. Instead of maintaining a monolithic 2,000-line CLAUDE.md instruction file, each skill resides in a standalone folder with a SKILL.md file and is loaded on demand. The set revolves around a standard development cycle: prime, plan, implement, validate, review, commit, and PR.

    482starsPython

    AI & LLMs· Tool

  • Repository:EveryInc/compound-engineering-plugin

    Compound Engineering: 33-Skill Plugin for AI Coding Agents

    Compound Engineering is an open-source plugin for AI coding agents designed to structure development workflows and systematically preserve learned context. It runs on 14 platforms, including Claude Code, Cursor, and Codex.

    24.9kstarsTypeScript

    AI & LLMs· Tool

  • Repository:vercel-labs/agent-skills

    Vercel Labs Agent Skills: Structured Rules and Audits for AI Coding Agents

    Vercel Labs provides a curated collection of instructions and scripts designed for AI coding agents. Following the Agent Skills specification, the repository covers Vercel cloud optimization, React and Next.js performance, UI best practices, and technical writing.

    31.3kstarsJavaScript

    AI & LLMs· Resource

  • Repository:mattpocock/skills

    mattpocock/skills: Modular Agent Skills for Real Software Engineering

    Matt Pocock shares a curated collection of agent skills taken directly from his own development setup. The project positions itself against rigid frameworks like GSD, BMAD, and Spec-Kit, as well as uncontrolled 'vibe coding'. Instead, it provides small, composable, and adaptable skills compatible with Claude Code, Codex, and other coding agents.

    247.2kstarsShell

    AI & LLMs· Tool

  • Repository:anthropics/skills

    Anthropic Skills: Reference Repository and Specification for Claude Agent Skills

    Anthropic provides a public repository containing example skills, templates, and specifications for Claude's Agent Skills standard. Skills package instructions, scripts, and resources inside folders with a central SKILL.md file to enable repeatable workflows ranging from document generation to technical testing.

    174.3kstarsPython

    AI & LLMs· Resource

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.