# Dekc Grade

> Grade reverse-engineering quality with automated rubric scores and adversarial judge protocol. Use after walks, before claiming RE complete.

- Skill: `spillwavesolutions/dekc-grade` (Agent Skill)
- Install (CLI): `npx skillmds@latest add spillwavesolutions/dekc-grade`
- Raw SKILL.md: https://api.skillmd.com/api/skills/spillwavesolutions/dekc-grade/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: spillwavesolutions (https://skillmd.com/u/spillwavesolutions)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/spillwavesolutions/dekc-grade

---


# DEKC grade (adversarial RE quality)

## Automated baseline

```bash
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/dekc_grade.py" --repo . --bundle knowledge
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/dekc_grade.py" --repo . --bundle knowledge --json
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/dekc_grade.py" --repo . --bundle knowledge --write
```

Default scores **DEKC nouns only** (29 types). Mixed SAC+PKC brains (~15k Module/Function nodes) will not dominate.

```bash
# Walk-scoped
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/dekc_grade.py" --repo . --bundle knowledge \
  --prefix semantic,tables/gold-,reports,dashboards,ingestion
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/dekc_grade.py" --repo . --bundle knowledge --tag fabric-walk-2026-08-24
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/dekc_doctor.py" --repo . --bundle knowledge   # DEKC technical
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/dekc_doctor.py" --repo . --bundle knowledge --all  # bundle-wide OKF
```

Dict-valued `description` fields (bad YAML / mixed bundles) are coerced; grade does not traceback.

## Adversarial loop (required for acceptance)

1. Spawn **lineage-skeptic**, **business-skeptic**, **stream-job-skeptic**, **coverage-skeptic**
2. Aggregate with **re-adversary-judge** against `evaluation/reverse-engineering-rubric.md` (threshold 0.75)
3. On fail → orchestrator revises (capture evidence or **retract** claims) → re-grade
4. On pass → `dekc_doctor.py` (search/pack refresh the SQLite index themselves)

Orchestrators: **data-lake-walker**, **reverse-engineering-orchestrator**.

## Rubrics

- `evaluation/reverse-engineering-rubric.md`
- `evaluation/lineage-integrity-rubric.md`
- `evaluation/business-fidelity-rubric.md`
- `evaluation/stream-job-landing-rubric.md`