ai-eng-core

Plugin ai-eng-core from marketplace ai-eng-system in v1truv1us/ai-eng-system. Commands read from the repo's manifest — 1 month ago.

Skills (38)

• simplify

  Review recently changed files for reuse, quality, and efficiency issues, then fix them. Use after completing a change, before declaring done.

• architect

  Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.

• code-simplification

  Simplifies code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be.

• comprehensive-research

  Multi-phase research orchestration for thorough codebase, documentation, and external knowledge investigation. Invoked by /ai-eng/research command. Use when conducting deep analysis, exploring codebases, investigating patterns, or synthesizing findings from multiple sources.

• create-goal

  Transform a vague idea, request, or prompt into a concrete, actionable goal with clear success criteria, scope boundaries, and measurable outcomes. Use when the user has an intention but needs help defining what \"done\" looks like.

• create-learning-path

  Build a personalized learning roadmap with milestones and practice checkpoints

• cursor-sdk

  Guide building apps, scripts, CI pipelines, and automations with the Cursor TypeScript SDK (`@cursor/sdk`). Use when integrating `Agent.create`, `Agent.prompt`, `Agent.resume`, streaming, MCP servers, local vs cloud runtime, errors, or porting REST `/v1/agents` calls to the SDK. Prefer this skill ov

• doc-review

  Structured document review for structure, clarity, and technical accuracy. Use for \"review this doc\", feedback, critique, or /doc-review.

• docs-canvas

  Render a documentation-style Cursor Canvas that organizes architecture notes, API references, walkthroughs, and how-tos into a navigable layout with sections, tables of contents, and cross-references. Use when the user asks for a docs canvas, documentation overview, architecture walkthrough, API ref

• dynamic-router

  Conductor/subagent routing for tasks across multiple harnesses. Assesses task complexity and intent, then dispatches to the appropriate subagent model via a harness-specific adapter. Supports Anthropic (Claude), Cursor, OpenCode, Codex (OpenAI), and Pi adapters. Use via /dynamic-task command or dire

• eval-harness

  Agent evaluation framework. Measure agent performance, identify weaknesses, and track improvement over time. Use when assessing agent quality, comparing approaches, or validating changes.

• grill-me

  Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or mentions \"grill me\".

• grill-with-docs

  Extend grill-me by producing or updating a CONTEXT.md or ADR-style decision record while stress-testing a plan. Use when the user wants to be grilled and wants the shared understanding persisted as a living document.

• incremental-implementation

  Deliver changes in thin vertical slices. Use when implementing a feature or refactor that touches more than one file.

• morning-brief

  Daily briefing synthesizing calendar, tasks, and priorities. Use for \"morning brief\", \"daily briefing\", \"start my day\", or /morning-brief.

• orchestrate

  Use only when the user explicitly types `/ai-eng/orchestrate <goal>` to decompose a large task, spawn a tree of parallel cloud-agent workers/subplanners/verifiers via the Cursor SDK, and collect structured handoffs; do not invoke autonomously.

• planning-and-task-breakdown

  Decompose specs into small, verifiable tasks with acceptance criteria and dependency ordering. Use when you have a spec and need implementable units.

• prompt-refinement

  Convert vague requests into compact TCRO prompts with phase-specific constraints. Used by research, specify, plan, and work workflows.

• arena

  Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

• automate-me

  Use for \"automate me\", \"create/update/refresh my -mode skill\", \"turn/capture my preferences or working style into a skill\", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling fresh evidence from recent transcri

• how

  Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique archi

• poteto-mode

  poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

• reflect

  Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

• typescript-best-practices

  TypeScript best practices. Use when reading or editing any .ts or .tsx file.

• why

  Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, prod

• repurpose

  Adapt existing content into new formats for different channels. Use for \"repurpose this\", \"turn this into\", \"adapt for\", or /repurpose.

• research-deep

  Multi-source deep research with confidence-rated synthesis. Use for \"research deeply\", \"deep dive on\", \"comprehensive research\", or /research-deep.

• run-learning-retrospective

  Evaluate learning progress, identify blockers, and adjust the learning plan

• source-driven-development

  Ground every framework decision in official documentation. Use when you want authoritative, source-cited code for any framework or library.

• spec-driven-development

  Write a structured specification before code: objectives, structure, code style, testing strategy, boundaries. Use when starting a new project or feature.

• storm-research

  Stanford STORM multi-perspective research method. Runs four sequential phases (multi-perspective scan, contradiction map, synthesis, peer review) in one thread to produce a PhD-level briefing on any topic. Use for \"storm research X\", \"multi-perspective research\", \"STORM method\", or any topic w

• sync-skill-taxonomy

  Classify every skill in skills/ as user-invoked or model-invoked, ensure disable-model-invocation is set on user-invoked skills, and inject metadata.category on all. Run after adding or changing skills, or when token-cost/routing quality is being reviewed. Use for \"sync skill taxonomy\", \"classify

• text-cleanup

  Remove AI-generated filler, repetition, inflated language, and redundant comments while preserving meaning.

• unslop

  Cut AI tells from any writing. Must always apply.

• using-agent-skills

  Discovery and invocation of all skills, commands, and agents. Decision tree for task-to-skill mapping. Core operating behaviors for agents. Use when unsure which skill or agent to use.

• weekly-review

  Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work

• workflow-from-chats

  Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.

• ralph-wiggum

  Continuous iteration loop pattern for well-defined tasks with clear completion criteria. Use when getting tests to pass, implementing features with automatic verification, bug fixing with clear success conditions, or running automated development overnight. Provides prompt templates, safety guidelin

Slash commands (13)

• /ai-eng-core:context

  Manage session state, memories, and context engineering

• /ai-eng-core:cook-status

  List active cooking-routines loops by reading marker files. Prunes stale markers (dead PIDs or mismatched start_epoch).

• /ai-eng-core:dynamic-task

  Route a task to the right Anthropic-powered subagent. The conductor assesses complexity and intent, then dispatches to LookupAgent (Haiku), WorkAgent (Sonnet), PlannerAgent (Opus), DebuggerAgent (Sonnet), or RefactorAgent (Opus). - name: task description: The task to route and execute. required: tru

• /ai-eng-core:init

  Initialize ai-eng-system configuration and project setup

• /ai-eng-core:orchestrate

  Orchestrate multiple agents for complex development tasks

• /ai-eng-core:plan

  Create detailed implementation plans from specifications

• /ai-eng-core:research

  Conduct comprehensive multi-phase research across codebase, documentation, and external sources

• /ai-eng-core:review

  Run comprehensive code review with multiple perspectives

• /ai-eng-core:simplify

  Review recently changed files for code reuse, quality, and efficiency issues, then fix them

• /ai-eng-core:skill-learning-approve

  Approve a pending skill_edit proposal so it becomes eligible for shadow evaluation

• /ai-eng-core:skill-learning-dismiss

  Reject a pending skill_edit proposal so it is excluded from shadow evaluation

• /ai-eng-core:spec

  Create a feature specification using structured requirements gathering

• /ai-eng-core:work

  Execute a plan or task with systematic tracking, quality gates, and comprehensive validation.

Subagents (13)

• architect-advisor

  Architectural guidance and technical decisions

• backend-architect

  Design RESTful APIs, microservice boundaries, and database schemas.

• claude-conductor

  Conductor agent that receives tasks, assesses complexity and intent, and routes to the appropriate Anthropic-powered subagent. Supports single-step dispatch and multi-step chaining. - Read - Grep - Glob

• claude-debugger-agent

  Agent for systematic debugging, error tracing, and root-cause analysis. Uses claude-sonnet-4-6. - Read - Grep - Glob - Bash

• claude-lookup-agent

  Fast, low-cost agent for file scanning, quick lookups, listing, and simple factual questions. Uses claude-haiku-4-5-20251001. - Read - Grep - Glob

• claude-planner-agent

  High-reasoning agent for architecture, planning, system design, and complex multi-step problems. Uses claude-opus-4-8. - Read - Grep - Glob

• claude-refactor-agent

  Agent for code restructuring, design pattern application, and architecture improvement. Uses claude-opus-4-8. - Read - Write - Edit - Grep - Glob - Bash

• claude-work-agent

  Balanced agent for coding, implementation, bug fixes, and standard development tasks. Uses claude-sonnet-4-6. - Read - Write - Edit - Grep - Glob - Bash

• frontend-reviewer

  Reviews frontend code for best practices

• full-stack-developer

  Generalist implementation developer focused on end-to-end feature

• java-pro

  Expert Java development with modern Java 21+ features

• skill-improver

  Convert evidence-backed skill failure clusters into small SKILL.md

• subagent-orchestration

  Ensures proper delegation to ai-eng-system specialized agents.

Similar plugins