ue-claude-scaffold

Use for any container agent that posts progress to the coordination server's message board. Defines the curl format, channels, message types, payload conventions, posting responsibilities, and verbosity levels.

Use when a review agent must produce structured output. Defines the BLOCKING/NOTE/Summary/Verdict template, the two-tier confidence rubric, and the JSON shadow block consumed by POST /tasks/:id/reviews. Compose with review-process and a domain skill.

Use when an agent evaluates the output of other agents or decides whether work meets the bar. Enforces rigorous quality standards — reject shortcuts, demand evidence, no rubber-stamping.

Use when an agent is the FSM arbitrator on a durable task. Defines the two triggers, the three ruling types, the POST contract, the addendum-file rules for contradiction rulings, and the 409 handling. Project-agnostic.

Tells container agents where the Unreal Engine source tree is mounted inside the container, so they can grep and read engine headers to verify API signatures and class hierarchies.

Use when an agent must review code changes. Defines the universal review sequence — identify files, read context, check against domain criteria, score, filter. Compose with a domain skill and review-output-schema.

Use when an agent must write code via test-driven development. Defines the types-stubs-red-green-refactor cycle with build verification. The last action before finishing must be a successful build with all tests passing.

Use when reviewing Unreal Engine C++ code for UE-specific correctness concerns — Mass ECS query/fragment alignment, UE invariant preservation, and UE-specific semantic traps. Compose with general-correctness for universal logic checks.

Use when writing or reviewing Unreal Engine C++ code. Authoritative style guide covering naming, formatting, const, ownership, pointers, lambdas, UE vs std choices, reflection macros, and modern C++ usage. Domain knowledge independent of review process.

Use when an agent must enforce strict role boundaries — what actions are valid, what is out of scope. Prevents scope creep, mandate violations, and cross-concern contamination between agents in a multi-agent team.

Use for the UE container orchestrator. Defines the UE agent resolution table, review agent mandates, and the terminal style sweep. Compose with orchestrator-message-discipline for posting rules and verbosity levels.

Use when reviewing any codebase for logic errors, spec compliance, boundary conditions, and test coverage gaps. Universal correctness truths independent of language or framework.

Use when an agent must write code and verify it compiles. Defines the read-modify-build-iterate cycle and the completion rule that the last action before finishing must be a successful build.

Use for the container orchestrator. Defines the full phase execution protocol — implement, parallel review, consolidate fixes, commit gate, cycle budget, decomposition review, and the optional terminal style sweep.

Agent resolution table, review mandates, and terminal style sweep for the scaffold-server orchestrator running inside a Docker container against the server/ subtree of ue-claude-scaffold.

Agent resolution table, review mandates, and terminal style sweep for the scaffold development orchestrator running inside a Docker container against the ue-claude-scaffold project.

Use when running a terminal style sweep as the last stage of a plan. Defines the edit-in-place loop — read diff, apply style fixes, build, test, commit, post. Compose with a domain style skill (ue-cpp-style, scaffold-server-patterns, react-component-discipline, etc.) plus container-git-write.

Use when reviewing Unreal Engine C++ code for decomposition opportunities. UE-specific concerns — UPROPERTY chain visibility, GC rooting, unity build inlining, and UE responsibility group types. Compose with general-decomposition for universal structural checks.

Use when reviewing Unreal Engine C++ code for memory safety, pointer lifecycles, GC interactions, thread safety, and MoveTemp correctness. Domain knowledge for safety-focused review.

Agent resolution table, working-scope declaration, and review mandates for the content-catalogue-dashboard orchestrator running inside a Docker container against the content-catalogue-dashboard project.

React, Mantine UI, TanStack Router, and TanStack Query conventions for any dashboard SPA on this stack.

Agent resolution table, working-scope declaration, and review mandates for the scaffold-dashboard orchestrator running inside a Docker container against the dashboard/ subtree of ue-claude-scaffold.

Use for any agent working on the ue-claude-scaffold codebase. Defines where things live, how to build/test/typecheck, and what tools are available. Non-container interactive execution.

React-agnostic web safety checklist for any code that renders in a browser. Covers XSS, untrusted URL handling, external links, browser storage, CSRF on mutating requests, postMessage, clickjacking, open redirects, and error-message leakage. Applies equally to React, Vue, Svelte, or plain HTML apps.

Fastify plugin conventions, ESM patterns, Drizzle ORM + PGlite usage, route structure, and typed handler patterns for the ue-claude-scaffold coordination server.

Use when writing, reviewing, or refactoring React components — especially those with hooks, callbacks, modals, or store interactions. Enforces separation of data logic from UI, keeps dependency arrays small enough to reason about, and prevents the emergent complexity bugs (infinite render loops, stale closures) that arise when components accumulate too many concerns. Use this skill whenever you see a useCallback or useMemo with more than five dependencies, a component file over 150 lines, or any mix of store orchestration and JSX in the same function.

Use when an agent must audit a codebase area and produce documentation. Defines the audit workflow — scope the area, read code and existing docs, trace composition, write new markdown deliverables. Never edit existing code files.

Use when an audit deliverable must cross-reference two project axes as a bipartite graph. Defines the conceptual structure — two axes, edges, and gap flagging. Presentation format is left to the agent.

Domain knowledge for UE Slate — the C++ UI DSL, style registration system, widget ownership model, and common footguns. Use when an agent reads, reviews, or documents Slate code.

Use when reviewing any codebase for file bloat, excessive nesting, DRY violations, hand-rolled algorithms, and decomposition opportunities. Universal structural truths independent of language or framework.

Complete message board protocol for the container orchestrator. Defines how to post, channels, message types, mandatory posts, and verbosity levels.

Git environment for write-access container agents. Covers the bare repo clone model, branch assignment, auto-push after commit, and branch restrictions.

Git environment for UE build-intercept container agents. Covers the bare repo clone model, automatic commit-and-push via the build hook, and branch restrictions.

Use for any agent running inside a Docker container that interacts with the project's git repository. Explains the bare repo clone model, branch naming, and how work is persisted.

Use for the cleanup session leader. Defines the issue surfacing, fix cycle, review round, clean-check voting, and cleanup report phases unique to cleanup sessions.

Git environment for read-only container agents (reviewers, planners). Covers the bare repo clone model and read-only workspace constraints.

Use when an agent implements code via TDD and must report results. Defines the input shape (plan or fix instructions) and the output template (Changes Made, Build Status, Test Status, Notes).

Use for any agent that writes code and must produce a work audit before building. Defines the debrief file format, naming convention, timing, and required sections.

Use for any agent that communicates with other agents or the user via a chat channel. Defines the reply/check_messages tool mechanics, @-addressing, and the conversational posture — engaged, concise, patient, and grounded.

Use for any agent that leads a multi-agent design or cleanup session. Defines the complete arc from handshake through convergence voting to deliverable, including voting cadence and tallying rules.