home / skills / dmitriiweb / extract-emails / agents-md-assistant
This skill drafts a comprehensive AGENTS.md from repository context, capturing commands, structure, and workflow rules to accelerate onboarding.
npx playbooks add skill dmitriiweb/extract-emails --skill agents-md-assistantReview the files below or copy the command above to add this skill to your agents.
---
name: agents-md-assistant
description: Inspect a repository and draft an AGENTS.md file using the standard template, capturing commands, structure, and workflow rules.
---
# AGENTS.md Assistant
## Quick start
- Review `README.md`, `CONTRIBUTING.md`, and docs/CI configs to learn the intended workflow.
- Pull exact commands from build scripts (`Makefile`, `package.json`, `pyproject.toml`, `justfile`).
- Map key directories (source, tests, docs, scripts) and mark generated or vendor paths.
- Capture architecture: key entrypoints, components, and configuration locations.
- Fill unknowns with TODOs and confirm them with the user.
## Workflow
1) **Inspect the repository**
- Read `README.md`, `CONTRIBUTING.md`, and `/docs` for goals and workflows.
- Check build/config files: `Makefile`, `package.json`, `pyproject.toml`, `justfile`, `Dockerfile`, CI pipelines.
2) **Extract commands**
- Record install, dev, lint, format, typecheck, test, and build commands exactly as documented.
- If multiple options exist, capture the preferred default and note alternates.
3) **Map structure**
- Identify primary code, tests, docs, scripts, and generated/ignored folders.
- Note where key configs live and any build artifacts to avoid editing.
4) **Summarize architecture & environment**
- Document key components, data flow, and entrypoints.
- Capture required versions, services, env vars, and migration/seed steps.
5) **Author AGENTS.md**
- Use `references/agents_md_template.md` as the base.
- Place `AGENTS.md` at the repo root unless instructed otherwise.
- Flag missing info with TODOs and ask for confirmation.
## Reference
- `references/agents_md_template.md`: base template to fill.
This skill inspects a code repository and drafts a complete AGENTS.md file using the standard template. It captures exact commands, maps project structure, and documents workflow rules, leaving TODOs for any missing details. It is tailored to Python projects that scrape or parse data, like extracting emails and LinkedIn links from URLs.
The assistant reads key docs (README, CONTRIBUTING) and CI/build files (pyproject.toml, Makefile, Dockerfile, CI pipelines) to extract install, dev, lint, test, and build commands. It maps source, tests, docs, scripts, and generated or vendor folders, identifies entrypoints and data flow, and summarizes environment requirements and important env vars. Finally, it fills the agents_md_template with captured details and flags unknowns as TODOs for user confirmation.
What if files referenced in the template are missing?
I insert clear TODO entries in AGENTS.md describing the missing files and the information needed, then prompt you to confirm or supply details.
Will the assistant change repository files?
No. It drafts the AGENTS.md content for review. You can approve or edit before committing it to the repo.