engineering

Plugin engineering from marketplace agent-kit in SiTaggart/agent-kit. Commands read from the repo's manifest — today.

Skills (35)

• ask-chatgpt-pro

  Build a focused repository context package with RepoPrompt CE, send it to a Pro model in the ChatGPT website, and return an Oracle-style second opinion. Use when the user explicitly asks to consult ChatGPT Pro, use ChatGPT's website, or use a named Pro model there; do not use for a generic request t

• ays

  Use when the user asks 'are you sure?', requests a second pass, challenges a prior answer, or asks you to reconsider the conversation before proceeding.

• bro

  Restate the assistant's last message in plain human language with no jargon. Use only when the user explicitly invokes bro.

• ce-brainstorm

  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 directio

• ce-conventions

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

• ce-council

  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 t

• ce-debug

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

• ce-decompose

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

• ce-grill

  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.

• ce-ideate

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

• ce-optimize

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

• ce-plan

  Create grounded technical plans at the depth the work needs. Use after ce-brainstorm or ce-grill, or directly for planning requests. Capture intent, useful context, constraints, and direction while leaving implementation judgment with the engineer.

• ce-polish

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

• ce-quality-gate

  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.

• ce-review

  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.

• ce-simplify-code

  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.

• ce-technical-review

  Run a rigorous multi-pass technical code review of recent changes. Use when the user asks for ce-technical-review, a technical review, a deep code review, or a strict pre-commit audit.

• ce-thermo-nuclear-code-quality-review

  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.

• ce-work

  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 pipe

• code-taste

  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, mainta

• codex-agent-team-setup

  Install or update Agent Kit's portable Codex scout, builder, and reviewer profiles and register them in Codex. Use when setting up task-lead or project-control on a machine or checking that its Codex configuration is healthy.

• codiff

  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.

• docs-researcher

  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.

• document-review

  Review requirements, PRDs, kickoff docs, and technical plans for clarity, grounding, and reader usefulness. Use when a written project artifact needs sharper scope, coherent direction, or a focused check before handoff.

• onboarding

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

• project-control

  Coordinate a software project from a persistent control task. Use when the user wants one lead agent to create and progress tickets, launch isolated Codex worktree tasks, govern scout-builder-reviewer execution, and follow pull requests through CI and review without implementing product code itself.

• prompt-check

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

• repo-research-analyst

  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.

• repoprompt-multi-review

  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.

• repoprompt

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

• scannable-ui-text

  Scannable UI text. Use when writing or reviewing neighboring session titles, feed items, dashboard summaries, or notifications. For collections compared in an interface, not narrative prose.

• spade-python-taste

  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.

• task-lead

  Lead one scoped software task through scout, builder, reviewer, verification, and a draft pull request. Use when the user requests a task lead or this full workflow, or when project-control delegates a worktree task.

• typescript-advanced-types

  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 proje

• web-researcher

  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.

Similar plugins