explaingit

crisxuan/agent-workflow-kit

19RubyAudience · developerComplexity · 2/5ActiveLicenseSetup · easy

TLDR

A bilingual, tool-neutral guide and template kit for scoring a repo's risk (0-16) and picking the right AGENTS.md workflow level for AI coding agents.

Mindmap

mindmap
  root((agent-workflow-kit))
    Inputs
      Risk score 0 to 16
      Repo context
    Outputs
      AGENTS.md templates
      Skill packages
      Workflow rules
    Use Cases
      Score a repo for AI risk
      Add agent rules
      Validate docs locally
    Tech Stack
      Markdown
      YAML
      Ruby
      GitHub Actions

Things people build with this

USE CASE 1

Score your repo with the 0-16 table and copy the matching AGENTS.md block

USE CASE 2

Add a Skill package so coding agents follow consistent workflow rules

USE CASE 3

Run the Ruby docs check in CI to validate Markdown and YAML

USE CASE 4

Adopt review gates for security-sensitive or production code

Tech stack

MarkdownYAMLRubyGitHub Actions

Getting it running

Difficulty · easy Time to first run · 30min

You score the repo and copy templates by hand; the Ruby docs-check script needs a local Ruby install if you want to run it.

Guide prose under CC BY 4.0 requires attribution; the reusable AGENTS.md template blocks are CC0 so you can paste them into any repo without credit.

In plain English

Agent Workflow Kit is a documentation-first project for teams that are bringing AI coding agents into real software repositories. Its main output is not code that runs, but a set of guides, templates, and reusable rule files that help a maintainer decide whether their project even needs rules for AI agents, and if so, how strict those rules should be. It is written to be tool-neutral, so it can be used with any large language model or coding agent, not only with one specific product. The central idea in the README is to evaluate before you change. The project gives you a 0 to 16 risk score table. You score the repository, look up the matching workflow level, and copy a corresponding AGENTS.md template into the repo. There are four levels: Level 0 means no formal AI workflow, suitable when AI is not editing the code or the project is disposable. Levels 1, 2, and 3 add progressively more rules: basic agent rules, then spec guidance and external-action safety, and finally review gates for production or security-sensitive work. The README frames the kit around five questions a maintainer should answer: does the project need an AI workflow at all, how heavy should it be, when should a spec layer be added, what should the agent verify before claiming work is done, and which external actions need explicit approval. A small table maps common problems, such as agents jumping into code too quickly or work being claimed done without evidence, to the parts of the kit that address them. The repository is bilingual, with the same guide in English and Chinese. Inside a skills folder are two agent-facing packages, one in each language. Each contains a SKILL.md file with the workflow, a yaml metadata file, and reference files with copy-ready AGENTS.md blocks and an optional catalog of engineering rules. The README shows example prompts you can paste into an agent to invoke them. A small Ruby script in scripts/check-docs.rb runs locally and in GitHub Actions to validate Markdown formatting, YAML syntax, skill folder structure, and links. Licensing is split: the prose uses CC BY 4.0, while the template blocks are released under CC0 so you can paste them into your own repository without attribution.

Copy-paste prompts

Prompt 1
Use agent-workflow-kit to score this repo and recommend an AI workflow level
Prompt 2
Generate an AGENTS.md from the Level 2 template and fill it with my install, test, and lint commands
Prompt 3
Run scripts/check-docs.rb on my repo and fix any Markdown or YAML errors it reports
Prompt 4
Translate the AGENTS.md rules into Chinese using the zh-CN skill package
Prompt 5
Set up a GitHub Action that runs the docs-check workflow on every PR
Open on GitHub → Explain another repo

Generated 2026-05-22 · Model: sonnet-4-6 · Verify against the repo before relying on details.