refacil-sdd-ai

Guided complete flow to investigate and fix bugs — delegates investigation and fix to the refacil-debugger sub-agent in two passes separated by user confirmation

Internal reference — SDD-AI prerequisites shared by all other refacil skills (do not invoke manually)

Validate that the implementation meets the specs — builds a briefing with testCommand and CA/CR criteria, delegates to the refacil-validator sub-agent for the report, and handles corrections with user approval

Implement the tasks of a proposed change — verifies artifacts and working branch, builds a structured briefing, and delegates to the refacil-implementer sub-agent to execute the implementation in isolated context

Archive a completed change — move artifacts to archive and sync specs

Run the SDD implementation cycle autonomously after /refacil:propose was approved by the human — chains apply → test → verify → review → archive → up-code in a single invocation, and notifies the user via WhatsApp through Kapso when finished (success or failure). Use when the user says "autopilot", "ejecuta el resto del flujo", "termina solo", "modo autónomo", or indicates they will step away from the computer.

Interactive guide for the SDD-AI methodology — explains which command to use based on what you need to do

Create a complete change proposal — delegates codebase exploration and artifact generation to the refacil-proposer sub-agent, and handles mandatory human review of the artifacts

Code review with the team quality checklist — builds a briefing with changed files and project type, delegates to the refacil-auditor sub-agent, and processes the verdict

Show statistics for a change — token savings, review history, compact and CodeGraph telemetry; optional narrative interpretation

Show which phase of the SDD-AI cycle a change is in and the exact command to resume it — use for "where am I?", "how is it going?", "status of the change", "resume", "where did I leave off". Distinct from /refacil:stats (which shows telemetry, token savings, and review metrics). Use /refacil:status to navigate the flow; use /refacil:stats for observability data.

Generate unit tests based on SDD artifacts or for specific files — builds a briefing with CA/CR and file scope, and delegates to the refacil-tester sub-agent for generation and execution in isolated context

Ask something directed to another session on the bus. Optionally blocks waiting for the response (--wait N seconds) for automatic LLM-to-LLM flow.

Explore and investigate the codebase before making changes — delegates to the refacil-investigator sub-agent to analyze architecture, flows, and dependencies without modifying anything

View new messages from the room since the last time you read them. Useful when a question with --wait expired without a response.

Join (or create) an agent bus room to communicate with Claude Code, Cursor, OpenCode, or Codex sessions in other repos. Session name = repo folder name.

Listen to SDD spec Markdown files in the browser with on-device TTS (Supertonic). Use after propose or on-demand for active changes and archived specs.

Reply to the last question directed to this session on the bus. The broker autocompletes the correlationId.

Send a message to the entire bus room (broadcast). For general announcements, not directed questions.

Configure the repository for SDD-AI — refacil-sdd layout, AGENTS.md / .agents/, IDE indexes, and methodology hooks

Push code and create PR for integration — git add, commit, push, and PR to the target branch

Detect and apply pending migrations of the SDD-AI methodology to the current project

Active bus listening mode. Waits for questions directed to this session, processes them and responds; then continues listening. Enables automatic LLM-to-LLM conversation between repos.