AbdelStark

Use for WorldForge local state: run workspaces and artifacts under `.worldforge/` (run manifests, evidence bundles, retention/prune), the `WorldForge(state_dir=...)` directory, and JSON-native artifact validation. The symbolic `World` JSON store and the `worldforge world` CLI were removed; there is no world persistence. Protects local state from silent corruption.

Use for WorldForge evaluation suites, benchmark harness changes, benchmark input fixtures, budget gates, report rendering, metrics semantics, and any claims based on benchmark or evaluation output. Keeps benchmark/eval artifacts deterministic, coherent, and claim-bounded.

Use for WorldForge provider work: adding adapters, changing capability declarations, promoting scaffolds, debugging provider failures, updating provider catalog docs, or touching LeWorldModel, GR00T, LeRobot, Cosmos-Policy, JEPA, Genie, or JEPA-WMS. Ensures capabilities remain truthful and optional runtimes stay host-owned.

Use for the robotics showcase Textual UI: report panes, launch helpers, screenshots, visual tests, and changes under `src/worldforge/harness/tui.py` or robotics view/rendering modules. Preserves the optional Textual boundary while keeping robotics flow logic testable without the TUI.

Use for LeWorldModel, GR00T, LeRobot, PushT robotics showcase, real-checkpoint smoke scripts, checkpoint building, and host-owned optional runtime dependencies. Keeps real-runtime validation explicit without adding heavy ML/robotics packages or artifacts to the base project.

Use for WorldForge README, docs, changelog, generated provider docs, MkDocs navigation, version/release metadata, public positioning, and release or publish readiness checks. Keeps public surfaces synchronized without hype or generated-doc drift.

Use when selecting, running, or fixing WorldForge validation: pytest, coverage, ruff, generated provider docs, MkDocs strict build, package contract, CI failures, and release gates. Produces the smallest credible command set first, then escalates to full validation when public behavior changes.

Git protocol implementation patterns using gitoxide for Guts repository operations

Infrastructure as Code patterns for deploying Guts nodes using Terraform, Docker, and Kubernetes

Peer-to-peer networking patterns using commonware for building decentralized Guts network

Rust development best practices for the Guts project - idiomatic code, error handling, async patterns, and commonware integration

Comprehensive testing strategies for Guts including unit tests, integration tests, property-based testing, and fuzzing

Author executable BDD specifications using Gherkin features and scenarios with clear Given/When/Then clauses. Use when converting requirements into testable behavior contracts, generating acceptance scenarios, or validating scenario coverage.

Derive and enforce DDD boundaries for work units, including bounded contexts, ubiquitous language, aggregates, and invariants. Use when decomposing RFCs/PRDs, planning implementation slices, or reviewing architecture drift in agentic workflows.

Apply strict non-slop release gates for agentic changes. Use when reviewing merge readiness, validating scenario coverage, checking invariant safety, and deciding land vs evict in orchestration flows.

Enforce strict TDD loops (RED->GREEN->REFACTOR) for behavior-changing work. Use when implementing features, bug fixes, or refactors that alter observable behavior and require non-sloppy verification.

Use when the user asks about EU AI Act risk classification, wants to know what risk tier their AI system falls under, or needs to understand which EU AI Act obligations apply to them. Triggers on questions about AI regulation, compliance classification, prohibited AI practices, GPAI obligations, or high-risk AI systems.

Use when the user needs to track EU AI Act compliance obligations, wants to see what requirements apply to their risk tier, needs to check compliance progress, or asks about specific Article requirements. Triggers on questions about compliance tracking, obligation checklists, Article 9-15 requirements, GPAI obligations, or compliance status.

Use when the user needs to generate EU AI Act compliance documentation, wants templates for technical documentation, risk management systems, data governance plans, human oversight plans, or declarations of conformity. Triggers on requests for compliance documents, Annex IV documentation, Article 9 risk management, Article 10 data governance, or Article 14 human oversight plans.