michaelshimeles/skills: Agent Skills and AGENTS.md Workflow for Coding Assistants

LinkmichaelshimelesTool

A GitHub repository providing modular agent skills and an AGENTS.md workflow template designed for Claude Code, Cursor, and Codex across development cycles.

Key points

  1. Four-beat workflow: AGENTS.md structures tasks into Isolate (new-feature), Build (code-structure), Prove (evidence-driven-testing), and Ship (before-and-after plus greploop).
  2. Isolated tasks: The 'new-feature' skill creates separate Git worktrees from origin/main so multiple agents can work in parallel without repository conflicts.
  3. Architectural guidelines: 'code-structure' enforces a two-layer separation between orchestration actions and a shared operational service layer.
  4. Visual test evidence: 'evidence-driven-testing' records app behavior using an FFmpeg-based recorder or Playwright, attaching videos and manifest summaries to PRs.
  5. Review loops and text cleanup: 'greploop' iterates PRs through Greptile reviews until reaching zero comments, while 'unslop' eliminates 31 AI prose patterns.

Why it matters

Working with autonomous coding agents can lead to messy work trees, architectural erosion, and unsubstantiated claims in PRs. This system provides explicit guardrails for isolation, structure, visual proof, and automated review cycles.

Analysis

The project unifies upstream utilities (such as Greptile review loops and Vercel's comparison CLI) alongside custom Python recorder scripts. Using SKILL.md frontmatter triggers allows Claude Code to load relevant skills on demand, reducing context bloat while enforcing concrete empirical proof before merging.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

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:MengTo/Skills

    Agent Skills: Reusable Playbooks for AI Coding Agents

    The GitHub repository MengTo/Skills provides a curated collection of Markdown-based 'agent skills'. It enables designers and builders to guide AI coding agents like Codex, Claude, and Cursor through complex web design, interaction, and 3D rendering tasks.

    6.2kstarsHTML

    AI & LLMs· Resource

  • Repository:23jmo/jmo-skills

    jmo-skills: Workflow Agent Skills for Claude Code and Coding Agents

    A repository packaging a collection of hackathon workflow skills for Claude Code and other coding agents. It provides commands for spec generation, clear technical explanations, UI refinement, animations, and Codex CLI handoffs.

    21stars

    AI & LLMs· Tool

  • Repository:humanlayer/skills

    HumanLayer Skills: Modular Extensions for Claude Code

    HumanLayer's 'skills' repository delivers a curated set of modular extensions for Claude Code, focusing on configuration tuning, React type refinements, and automated agent loops.

    1.4kstarsTypeScript

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

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.