sddp-regen

SkillDev tools

Archive a completed prototype and regenerate all canonical bootstrap artifacts from scratch. Direct command-bar dispatch only; do not select for general queries.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the sddp-regen skill

What this skill tells your AI

The instructions your AI receives, as published by attilaszasz/sdd-pilot in .agents/skills/sddp-regen/SKILL.md and read by ahel’s review.

Argument hint: [optional feedback, learnings, or guidelines for regeneration] Command category: project-bootstrap Prerequisites: project-instructions, product-document, technical-context, project-plan:complete

You are starting a prototype retrospective workflow. Your sole purpose is to archive the completed first-pass implementation as a throwaway prototype and regenerate all canonical bootstrap artifacts from scratch, informed by everything learned during the prototype. Disregard feature-level implementation context from this conversation. Focus exclusively on archival, insight mining, and bootstrap regeneration.

Input

$ARGUMENTS = The user's message provided alongside this command invocation. If the user provided no message, set $ARGUMENTS to empty and let the skill handle it.

Load and follow the workflow in .github/sddp/workflows/prototype-regen/WORKFLOW.md.

When the shared workflow asks the user to choose or answer:

  • Ask the user explicitly in chat and wait for the reply before continuing.
  • Present the recommended option as guidance only; do not choose it on the user's behalf.
  • Allow free-form answers anywhere the shared workflow allows them.
  • Do not infer an answer from silence, partial output, or prior recommendations.

When any nested bootstrap workflow says Delegate: ADR Author, Delegate: Technical Researcher, or Delegate: Configuration Auditor, read the referenced sub-agent file (.github/agents/_adr-author.md, .github/agents/_technical-researcher.md, or .github/agents/_configuration-auditor.md) for methodology, then perform the task yourself.

Report progress to the user at each major milestone — summarize what has been completed and what remains.

Signals

GitHub stars
97
Forks
9
Last commit
Sep 2026
Advanced
Item type
skill
Key
sddp-regen
Source
github.com/attilaszasz/sdd-pilot