ai-eng-system

Build a personalized learning roadmap with milestones and practice checkpoints

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

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 reference page, or wants to render structured documentation as an interactive canvas.

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 direct invocation from other skills.

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

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".

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.

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

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

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

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

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 where a single-prompt answer is too shallow.

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 skills", "fix disable-model-invocation", or "skill token audit".

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

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.

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.

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 over memory—the SDK surface evolves and references here are the source of truth.

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

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

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

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.

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

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.

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

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

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.

Design CI/CD pipelines, quality gates, and iterate on failing PR checks until green. Use when setting up pipelines or fixing CI on a branch.

Find failing PR checks, inspect logs or external check links, and apply focused fixes

Manage git worktrees for isolated parallel development. Use when running multiple sessions concurrently or working on parallel features.

Review changes, open PRs, run pre-launch checks, staged rollouts, and rollback. Use when preparing to ship to production or closing out a branch.

Recursively initialize AGENTS.md in monorepo subdirectories with smart detection. Creates hierarchical agent context files with proper linking to root CLAUDE.md and parent AGENTS.md. Use for setting up multi-package projects, microservices, or any project with important subdirectories that need AI agent guidance.

This skill should be used when creating extensions for Claude Code or OpenCode, including plugins, commands, agents, skills, and custom tools. Covers both platforms with format specifications, best practices, and the ai-eng-system build system.

Chrome DevTools for live runtime data: DOM inspection, console logs, network traces, performance profiling. Use when building or debugging anything in a browser.

Multi-axis code review with optional strict maintainability mode. Use before merging any change—human, agent, or automation output.

Build a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for UI verification, screenshots, perf profiles, or reproducing UI bugs.

Guides systematic root-cause debugging. Use when tests fail, builds break, behavior does not match expectations, or any unexpected error appears.

OWASP Top 10 prevention, auth patterns, secrets management, dependency auditing, boundary validation. Use when handling user input, auth, or external integrations.

Red-Green-Refactor workflow: write tests before implementation, maintain coverage. Use when implementing logic, fixing bugs, or changing behavior.

Run an extremely strict architecture and system design review for coupling, boundary violations, dependency direction, layering, and structural decay. Use for a thermo-nuclear architecture review, thermonuclear system design audit, or especially harsh architecture review.

Run an extremely strict performance review for runtime efficiency, memory usage, bundle size, database query patterns, and scalability limits. Use for a thermo-nuclear performance review, thermonuclear performance audit, or especially harsh performance review.