Engineering

Open Codiff for a narrative code walkthrough, a blocking plan handoff, or a shared walkthrough URL. Use when the user writes "$codiff", "/codiff", "$codiff plan", "$codiff share", "show me codiff", "open Codiff", or asks to review a change or edit a plan in Codiff.

Create structured plans for multi-step tasks once the goal is clear enough to plan. Use after ce-brainstorm or ce-grill, or directly for clear planning requests. If the request has branchy product/scope ambiguity, run ce-grill first.

Execute implementation work with a compact product-contract loop. Use when the user asks to build, fix, implement, polish, or finish a scoped task. Favor reasoning, prior art, smallest correct changes, focused tests, and real-surface proof. Do not run autonomous PR, CI, ticket, or residual-work pipelines.

Find root causes and fix bugs. Use for errors, failing tests, issue repros, stack traces, "debug this", or "why is this failing".

Clarify and stress-test a requirements doc, plan, design, or rough approach through a focused interview. Use when the user wants to be grilled, or before ce-plan when the requirements are too branchy, ambiguous, or strategically important to plan cleanly.

Generate and evaluate grounded ideas. Use for 'what should I improve', 'give me ideas', 'ideate', 'surprise me', or 'what would you change'.

Start the dev server, open the feature in a browser, and iterate on improvements together. Manual invocation only — type /ce-polish to run it.

Use when the user asks for a code review, PR review, pre-commit audit, or review of a branch or local diff after implementation exists. Review-only; use document-review for plans and requirements.

Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Use when the user asks for ce-council, council this, run the council, war room this, pressure-test this, stress-test this, debate this, validate this, get multiple perspectives, or when they are torn between meaningful options. Do not trigger on simple factual questions, trivial yes/no questions, implementation tasks, or casual should-I questions without a real tradeoff.

Apply TypeScript and React code-shape taste for implementation, review, refactor, and quality-gate tasks. Use when TypeScript or React changes involve typed contracts, helper boundaries, domain cores, IO or UI adapters, schemas, reducers, selectors, premature abstractions, speculative guards, maintainability smells, courier objects, JSX business logic, casts, useEffect, effect soup, or over-engineering.

Generate or refresh ONBOARDING.md for a codebase. Use for onboarding docs, new contributor docs, 'vonboard', or 'vonboarding'.

Use RepoPromptCE / rpce-cli for token-efficient codebase exploration, planning, review, refactor context, and prompt exports.

Run metric-driven optimization loops with experiments and hard gates. Use for search, clustering, build, prompt, or measurable quality tuning.

Split or rebuild oversized diffs into reviewable pieces. Use for 'too big to review', 'break this down', 'decompose this', or 'split this up'.

Normalize a consequential or ambiguous request when missing context, boundaries, or proof could materially change the work. Explicit invocation previews the improved prompt.

Explore requirements and approaches through collaborative dialogue, then write a right-sized requirements document. Use when the user says "let's brainstorm", "what should we build", or "help me think through X", presents a vague or ambitious feature request, or seems unsure about scope or direction -- even without explicitly asking to brainstorm.

Shared conventions and references for the ce-* skill family. Shared by Engineering skills as a sibling directory; not invoked directly.

Perform iterative web research and return structured external grounding. Use when planning or ideating needs prior art, competitor patterns, cross-domain analogies, or market signals from outside the repo. Prefer over ad hoc manual web searches for structured external context.

Run the changed-code quality gate after implementation: touched-file lint, format, type-check, tests, and code-shape checks. Use after ce-work writes code, before review or shipping, and when the user asks to make changed files clean.

Research official documentation and version-specific constraints for a framework, library, or API when current external behavior materially shapes a plan or implementation. Returns official-docs findings, version caveats, and community patterns.

Review requirements, PRDs, kickoff docs, and implementation plans with taste. Use after ce-plan for markdown plans, before ce-plan for requirements docs that need a quality pass, or whenever a written project artifact needs sharper scope, coherence, and reader utility.

Use when the user asks to simplify, refactor, clean up, reduce duplication, or remove unnecessary complexity from recently changed code. Also use after a substantial refactor or rewrite to check behavior preservation, reuse, and resulting complexity before completion.

Run a repository's existing cross-provider multi-model review through visible Orca-managed Claude, Codex, and OpenCode terminals. Use when the user asks for orca-multi-review, an Orca-based multi-model review, or wants to watch the repository review agents and progress instead of launching hidden coding CLIs.

Apply Spade-specific Python service design taste when writing, reviewing, refactoring, or fixing Python under spade, especially FastAPI or Termpower services, Pydantic boundaries, router packages, runtime dependencies, expensive endpoints, and service code-shape decisions.

Perform scoped repository reconnaissance — technology, architecture, patterns, conventions, issues, templates — and return a compact evidence-backed markdown summary inline. Use when onboarding to a codebase, grounding a plan, or when a loop skill dispatches scoped repo research.

Use when a code change needs a higher-confidence review in RepoPrompt, especially before merge or after substantial, subtle, or high-risk changes. Produces one evidence-checked CE report from independent model reviews.

Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.