venikman

Issues a proxy audit verdict for a session.

Verifies Definition of Done checks and generates a DoD report.

FPF Pattern F.18: Local‑First Unification Naming Protocol

Initializes a bounded context skeleton under runtime/contexts/<context>.

Mints a new F.18 Name Card with strict Twin-Label and Sense-Seed validation.

Records a formal Design-Rationale Record (DRR) for architectural decisions.

Scaffolds a new Skill (SkillSpec + SKILL.md + code stub + fixtures + test harness), regenerates inventory + index, and logs U.Work.

Checks session compliance against a Rule of Constraints policy.

Verifies that an execution trace complies with the FPF Behavioral Specification.

Generated skill for design/audit-name.

Generated skill for design/deprecate-name.

Generated skill for design/mint-name.

Minimal reference skill used to validate parsing and loading.

Evaluates a value against an FPF CSLC (Characteristic/Scale/Level/Coordinate) definition (A.18).

Calculates the SkillUsabilityScore (U.Metric) for Zero-Shot Enactment.

Creates an initial SlotFillingsPlanItem (A.15.3) baseline.

Portable builder skill for pi. Use when a bounded task card is approved and a builder must execute one artifact-first loop at a time against plans/<feature>/ artifacts under orchestrator and reviewer oversight.

Local Effect doctrine for the pi healthcare harness. Use when a task touches files importing effect and needs consistent rules for services, schemas, errors, layers, config, and structured effectful composition.

Practical FPF usage guide for the vfpf harness. Use when a task needs a fit check, an FPF entry route, starter artifacts, mixed-team handoff rules, or an FPF-shaped review rubric without loading the full specification into the prompt.

Portable evaluation skill for pi. Use when comparing runs, agent mixes, or orchestration changes for Claude and Codex. Only compare results inside an explicit comparability frame and tie outputs back to plans/<feature>/.

Portable orchestration skill for pi. Use when Claude and Codex should work as peer agents with bounded scopes, stable task cards, and evidence-backed handoffs. Use it to drive the orchestrator -> builder -> reviewer loop and keep all delegated work tied to plans/<feature>/ artifacts.

Portable planning skill for pi. Use when a feature needs bounded context, explicit alternatives, and one approved execution plan before implementation. Keep the output artifact-first so Claude and Codex can work against the same plan surface. Write plans under plans/<feature>/.

Portable review skill for pi. Use when work needs a findings-first review that checks behavior, regression risk, evidence quality, and plan adherence across Claude and Codex outputs. Review against plans/<feature>/ artifacts and act as the blocking reviewer in the orchestrator loop.

Use when Claude Code is changing OntoTwin dense semantic atlas visuals, lenses, point styling, labels, rails, responsive behavior, or analyst workflow UI.

Use when Claude Code is mapping a real ontology corpus into the OntoTwin atlas manifest, adapters, groups, labels, lenses, counts, search, or tile APIs.

Use when Claude Code is extracting, packaging, installing, or adopting the OntoTwin atlas as a reusable React library.

Add repeatable local and CI benchmark commands for a Catlas adopter and run the right tier to produce a maturity-backed gate result. Runs Tier A ui-graph-evaluator first against any canvas/SVG host, and Tier B clickable audit only for semantic-atlas-compatible chrome. Validates against the existing M2 mapping (examples/atlas-data-prep + npm run conformance). Use after catlas-adoption-scout, when a team needs evidence that their integration is bounded and rendering correctly.

Read-only scout for adopting @catlas/atlas-react. Inspects an adopter repo and reports its framework, data access, graph surface, styling system, and data source, then recommends the first realistic maturity target (M1, M1.5, or M2) and the next skill to run. Use this first, before any edits, when a team wants to evaluate whether their product can render as a Catlas semantic atlas.

Install, connect, validate, or self-host the FPF Reference MCP server. Use for hosted remote setup, local stdio or HTTP runtime setup, and local bridge/proxy setup for clients that need a localhost MCP URL while using the hosted remote endpoint.

Bootstrap or refresh an FPF-aligned Codex workspace in the current repository. Use when the user wants the FPF multi-agent team, AGENTS.md orchestration rules, or project .codex agent files created or updated. Also use to add repo-local validation and operating defaults for code-bearing repos. Do not use for normal coding tasks.

Use when the user wants to run the ATR smoke flow, trigger a production bulk smoke test, run metadata/group-only stages, or execute the same workflow locally.

Use at end of a run or when blocked. Creates ONE new work/checkpoints/<YYYYMMDD-HHMM>.md and updates work/STATE.md (last checkpoint + delta + next actions).