# .claude/

## Subdirectories

| Directory | What | When to read |
| --------- | ---- | ------------ |
| `skills/` | 16 `mvp-*` reusable knowledge skills, one directory each (see Skills table below) | Loading project-specific knowledge before a task |
| `output-styles/` | Output formatting templates (`direct.md`) | Customizing response style |
| `tdd-guard/` | TDD-guard tool state (test/modification tracking data) | Debugging TDD-guard behavior |

## Skills (`skills/`)

Each skill is `skills/{name}/SKILL.md`; its frontmatter `description` states exactly when to load it — this table is a condensed pointer, not a substitute for reading it.

| Skill | What | When to read |
| ----- | ---- | ------------- |
| `mvp-architecture-contract/` | Load-bearing architecture decisions, invariants, and known weak points | Designing, extending, or reviewing a feature or refactor |
| `mvp-build-and-env/` | Fresh-checkout setup and build/test/install failure triage | Any local build, install, or test command fails |
| `mvp-change-control/` | Issue/branch/PR workflow, RULE 0/1/2 quality-review taxonomy, label discipline | Making any repo change, reviewing code, asking "is this safe to merge" |
| `mvp-config-and-secrets/` | Env vars, config fields, Docker secrets, feature flags, tier gates | Adding/changing config or secrets; startup config errors |
| `mvp-debugging-playbook/` | Symptom-to-root-cause triage index | Diagnosing a live bug from its symptom |
| `mvp-deploy-safety-campaign/` | CI/CD safety gaps (no tests/lint/security gate, `:latest` tag hazard) and the plan to close them | Working on CI/CD pipeline safety |
| `mvp-diagnostics-and-logging/` | Grafana/Loki/LogQL, health checks, redis-cli, shipped diagnostic scripts | Observing or measuring the running system instead of guessing |
| `mvp-docs-and-writing/` | Doc trust map, house style, doc-sync discipline, temporal-contamination rule | Reading or writing any documentation, including CLAUDE.md files |
| `mvp-failure-archaeology/` | Chronicle of past incidents, dead ends, and reverts with root cause and evidence | Before re-investigating a familiar-smelling bug or deleting old-looking code |
| `mvp-launch-readiness/` | Pre-launch blockers and guardrails for external/user-facing claims | Assessing launch readiness or writing a public claim about the product |
| `mvp-ocr-gemini-pipeline/` | OCR engine stack, Gemini semantic extraction, VIN decode, WIF auth chain | Working on OCR, VIN decode, or email-ingestion features |
| `mvp-proof-and-analysis-toolkit/` | Prove-it methods for high-stakes decisions and stuck bugs | Before committing to an architectural/design decision, or after a failed fix attempt |
| `mvp-research-frontier/` | Open problems and methodology for proposing/validating new work | Seeding the next piece of work; the issue tracker is empty |
| `mvp-run-and-operate/` | Deploy, rollback, blue/green switch, backup/restore procedures | Operating staging or production environments |
| `mvp-validation-and-qa/` | Evidence bar and definition of done; real test-suite map | Before claiming a change is done, tested, or ready to merge |
| `mvp-vehicle-domain-reference/` | Vehicle domain theory: VIN validation/decode, MPG/unit conversion, tiers | Working on VIN, fuel-efficiency, unit-conversion, or tier-limit logic |