Sac reverse engineer
Skill SpillwaveSolutions/system-architecture-capture/skills/sac-reverse-engineer
End-to-end reverse-engineer one or more git repositories into a SAC architecture knowledge graph (packages, services, IaC, CI/CD, IAM, identity, topology). Primary entry skill for SAC.From its SKILL.md
npx -y skills add SpillwaveSolutions/system-architecture-capture --skill sac-reverse-engineerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.5 KB, as published. Nobody here has run it
SAC Reverse Engineer
Populate the second brain for system architecture information on the given monorepo or multi-repo set: walk code/IaC, materialize concepts using the standard OKF schema pack (schemas/types.json), wire relationships, validate with --schema, and leave a queryable knowledge bundle.
Connectivity
Provider login/API details come from host skills and MCPs — not from SAC. Fetch wiki/tickets/live cloud inventory via those tools first; SAC normalizes paths you pass in. In-repo scanners need only filesystem access to git roots.
Process
- Confirm repo roots (local paths or clones of URLs) and system name.
- Optional: wiki export dir, tickets JSON.
- Run orchestrator:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sac_orchestrate.py" \
--repo . \
--system "$SYSTEM_NAME" \
--scan-root "$REPO_ROOT" \
--json
- Delegate enrichment to sub-agents for purpose/SLA/ownership and API contracts.
- Run blast radius on critical services.
- Validate:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sac_validate.py" --repo . --schema
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sac_doctor.py" --repo .
- Report topology summary + knowledge paths.
Default scan domains include diagrams (Mermaid/PlantUML) and code (Module/Class/Method/Function).