Skip to content

onstring/md2automation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

md2automation

A Claude Code skill that turns markdown DevOps notes (runbooks) into tested, parameterized automation scripts — bash, python, or ansible — without ever touching real infrastructure.

  • Solid: scripts are parameterized, fail-fast, idempotent where possible, and proven repeatable by executing them twice in a sandbox.
  • Safe: dry-run by default (--apply to mutate), secrets externalized and scanned for (in the note and the generated artifact), all execution in throwaway Docker containers with --network none, OpenStack calls intercepted by a mock CLI. The human runs the real thing themselves.
  • Feasible: gaps in the note become batched questions with recommendations, not silent guesses; four approval gates (selection, review, plan, results).

Layout

  • SKILL.md — the skill workflow (phases + gates)
  • references/ — extraction criteria, codegen patterns, testing matrix
  • scripts/check_tools.sh — prerequisite gate
  • scripts/scan_secrets.py — plaintext secret scanner (notes + artifacts)
  • scripts/run_checks.sh — layered test harness (L0 secrets, L1 static, L2 dry-run, L3 sandboxed execution)
  • scripts/openstack-mock — fake openstack CLI: canned/fixture reads, logged-never-executed mutations
  • evals/ — eval prompts + sample notes

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors