sc-compose

Build a local, self-contained HTML A/B comparison viewer for two or more generated HTML variants (e.g. different template revisions, different data sets, before/after fixes), so a human can pick between panes side-by-side without any external hosting.

Reusable QA orchestration skill for GitHub PRs. Use for multi-pass QA, CI monitoring, and template-driven findings and final quality reports.

Generate a sprint status report for the current phase. Default is --table.

Generate and triage adversarial templates, var-files, and rendering inputs against sc-compose by coordinating bounded background agents, differential and metamorphic checks, minimization, and regression-test promotion. Use when trying to break a rendering subsystem, validating a risky change, hunting parser/validator/rendering edge cases, or turning a confirmed fuzz failure into a unit or CLI test.

Team-lead drives plan hardening after the current plan state already exists in repo docs.

Session initialization for the team-lead identity. Confirms identity and detects whether a full team restore is needed. Only run when ATM_IDENTITY=team-lead.

Repair Claude teammate routing after same-session compaction or resume when sc-compose still exists on disk and the saved leadSessionId still matches the current SESSION_ID, but ATM or teammate reachability is broken.

Orchestrate sc-compose sprint work where team-lead coordinates, comp is the sole developer, and quality-mgr enforces the QA gate.

Review Rust architecture plans, crate boundaries, and code for structural design-pattern compliance. Use when the task involves typestate, sealed traits, error contracts, wrapper/newtype design, object safety, interior mutability, or other type-system-driven Rust correctness patterns that go beyond general style guidance.

Develop, review, and explore Rust code with strict adherence to Pragmatic Rust Guidelines. Use when the user mentions Rust, .rs files, Cargo, clippy, rustdoc, or requests Rust architecture, implementation, or review.

Harden Rust backend services for production readiness. Use when working on Tokio, Axum, Hyper, Tonic, or Reqwest-based services and you need guidance or review for config validation, structured tracing, request IDs, timeouts, retries, graceful shutdown, backpressure, body limits, health checks, metrics, and dependency hygiene. Not for non-service Rust crates, embedded Rust, pure sync CLI tools, or low-level libraries without runtime, network, or server concerns.

Run the repo Rust TODO finder during sprint-end or integration review and turn every discovered TODO into a QA finding rather than deferred work.