Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.

Resolve on-screen 5chan DOM elements to React source files, line numbers, component names, and ownership stacks using the app's dev-only element-source helpers and playwright-cli. Use when Codex needs to inspect a page element, map a snapshot ref to source code, confirm which component rendered a node, or follow up after $profile-browsing finds a rerender hotspot and needs file-level attribution.

Start a research project with intelligent agent orchestration

Short, explicit alias for vc-router. Use only when the user explicitly invokes `use vcg:` and wants the shortest reliable router command.

Generate a structured deep research prompt. USE WHEN the user needs to research a complex topic, market, or bug deeply. Capabilities include objective clarification, tech stack validation, and prompt generation.

iOS Simulator automation and interaction using the AXe CLI tool. Use when working with iOS simulators for UI automation, testing, accessibility verification, or screen recording. Specific use cases include simulating touches and gestures (tap, swipe), entering text, pressing hardware buttons (home, lock, Siri), recording or streaming simulator video, extracting UI accessibility information, or automating iOS simulator interactions. Assumes axe CLI is already installed.

Capture atomic learning insights into .workflow/learning/lessons.jsonl. Lightweight CRUD over the shared learning store — supports capture, list, search, and show modes. No LLM or CLI calls; all operations are pure file reads and writes.

Deploy Tempo Zones, start zone nodes, validate router swap-and-deposit flows, and debug zone sync, portal ingestion, withdrawal, sequencer key, and generated zone artifact issues in this repository. Use when working with just deploy-zone, zone-up, deploy-router, demo-swap-and-deposit, or generated/<name>/zone.json.

Implement or adjust the core color pipeline (parse, normalize, scale, resolve) guided by src/planning/spec-v0.3.md and src/planning/roadmap-v0.3.md.

Migrated from the legacy agent profile. Use this as an on-demand specialist workflow.

Write, critique, and iterate prompts for OpenAI GPT-5 series models. Use for tasks like: (1) turning vague requirements into high-signal instructions, (2) selecting between quick vs deep reasoning behaviors, (3) creating robust structured-output prompts (JSON schemas, tool calls), (4) designing evaluation prompts and rubrics, and (5) debugging prompt failures (hallucinations, format drift, tool misuse). Trigger when the user mentions GPT-5, prompt engineering, system/developer messages, structured outputs, agent prompts, or wants best-practice templates.

Structured workflow for discovering, reproducing, and fixing bugs in Searchlite by inspecting real code paths (CLI/HTTP/core), validating durability invariants, and producing regression tests; use when investigating incorrect results, crashes, data loss risks, or “it sometimes fails” reports.

Use when building Shopify themes, apps, custom storefronts, or e-commerce solutions. Invoke for Liquid templating, Storefront API, app development, checkout customization, Shopify Plus features.

Use after scope-need and relevant specialist skills approve work. Takes the scoped-need document and produces a flat, ordered list of discrete changes required. Each change is scoped to be a single commit.

Format high-quality Git commit messages from staged or unstaged changes with stable conventions. Use when Codex is asked to create, polish, or validate commit messages, especially for Conventional Commits, commitlint-compatible repositories, squash/fixup flows, or teams that require consistent subject/body/footer structure.

'Assess non-functional requirements (performance, security, reliability, maintainability) before release with evidence-based validation'

Conecta e realiza operações (CRUD e Aggregations) em bancos de dados MongoDB utilizando configurações de conexão salvas. Suporta queries JSON e auxílio na sua construção.

Expert C4 Container-level documentation specialist. Synthesizes Component-level documentation into Container-level architecture, mapping components to deployment units, documenting container interfaces as APIs, and creating container diagrams. Use when synthesizing components into deployment containers and documenting system deployment architecture.

Build, query, and inspect the project knowledge graph in .planning/graphs/

Use when working on ScenePilotix across multiple threads or when a task may change product flow, workspace boundaries, naming, save/export behavior, prompt-engine routing, or platform execution strategy. Ensures the shared development strategy doc is treated as the single source of truth and updated at the end.

Master Flutter development with Dart 3, advanced widgets, and multi-platform deployment. Handles state management, animations, testing, and performance optimization for mobile, web, desktop, and embedded platforms. Use PROACTIVELY for Flutter architecture, UI implementation, or cross-platform features.

This is an example `workflow-<slug>/SKILL.md` generated from a workflow spec.

Use when starting any active phase/group in ntn-sim-core platform refactor, or before promoting a downstream MODQN/UI prompt into active work, to verify authority docs, phase status, prompt freshness, and go/no-go conditions.

Applies the project's commit message convention. Use when writing commit messages, making git commits, or summarizing changes.

Use when validating beamHO-bench changes, deciding which project gates to run, preparing SDD closure, or checking whether lifecycle docs and manual acceptance evidence are sufficient before marking work complete.

Generates high-quality, predictable, and efficient .agent/skills/ directories based on user requirements. Reference this at any time you are creating any other skill for Antigravity.

Use when mapping literature or standards evidence into ntn-sim-core parameter registry, parameter spec, or provenance surfaces without letting synthesized simulator docs override the paper-catalog source chain.

Guidelines and instructions for developing the Z8 runtime. Includes coding standards, build processes, and testing workflows.

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

Use when needing to programmatically invoke a CLI coding agent (Claude Code, OpenCode) from Python, delegate work to a sub-agent, or orchestrate multiple agents. Covers AgentShell instantiation, prompt execution, response streaming, session resumption, tool scoping, and cost tracking.

'Use this when: (1) Creating a new project-specific skill to document project patterns, (2) Improving or updating an existing project skill, (3) Writing skill descriptions that will trigger other agents, (4) Organizing skill content for progressive disclosure, or (5) Learning what project-specific skills exist in .claude/skills/. Ensures skills follow project conventions and provide effective progressive disclosure.'

Use when you need high-quality stock-style images from Aura Assets (aura.build/assets) similar to Unsplash for design mockups and marketing: backgrounds, abstract wallpapers, architecture, portraits, and headshots. Includes a workflow for searching by tag on aura.build/assets and returns 5 real image URLs per category plus practical guidance for using different resolutions and aspect ratios.

Create clear, concise technical documentation for a specified file, module, or folder.

Use when implementing globe.gl (Globe.GL) for 3D globe data visualization with WebGL/ThreeJS, including setup, data layers (points, arcs, polygons, labels), and integration patterns in plain HTML or React.

Improve skills and workflows by analyzing run artifacts and execution logs (events.jsonl/state.json) under runs/ (or OpenSpec changes/). Use when you want to iterate on skills based on real runs: find failure modes, bottlenecks, unclear prompts, missing I/O contracts, and propose concrete edits.

Introspection & Querying: describe/list commands, config filtering, workspace introspection, dependency graphs, YQ integration

Monitor RPC endpoint health and provide automatic failover for reliable blockchain access.

Connect your local machine to a Kubernetes cluster for local development with Signadot — local connect, proxy, traffic override, and traffic recording/inspection. Use when a developer wants to run services locally that participate in cluster traffic, or record/inspect sandbox traffic.

Comprehensive guide for creating high-quality specialized agents following v2 architecture patterns. Use this skill when users need to design and implement new agents, understand agent architecture, or learn best practices for agent creation.

Use after any meaningful ntn-sim-core phase/group completion or contract change to determine which SDD, status, validation, README, and todo documents must be updated in the same change set.

Craft high-precision prompts and edit instructions for Nano Banana image workflows, especially when using the local nanobanana MCP tools for generation, editing, character consistency, or multi-image fusion. Use when the task needs structured prompts, reference-role assignment, layout-heavy image specs, typography-heavy images, iterative edit-first refinement, or reliable model/aspect/output-path choices.

Write commit messages to a temporary file and commit with `git commit -F`. Never use `git commit -m`.

Automate browser interactions via the Playwright CLI. Use for web testing, form filling, screenshots, UI verification, and data extraction.

Use when editing beamHO-bench paper profiles, source maps, assumption-backed research parameters, or paper-source registries so schema, profile JSON, sources JSON, and validation coverage stay traceable and synchronized.

Rewrite user requests into clear, precise, and complete AI prompts. Use when a user asks to create, convert, or refine a prompt, or to restate a request as a specification for an AI model.

**🛡️ Test your AI agent's security posture against adversarial attacks**

Packer orchestration: init/build/validate/inspect/output, machine image building, template management, source management

Create workflow-* skills by composing existing skills into end-to-end chains. Turns a user idea into a workflow_spec.md SSOT (via workflow-brainstorm), discovers available skills locally + from skills.sh, and generates a new workflow-<slug>/ skill package. Use when you want to design a new workflow, chain multiple skills into a flow, or turn scattered atomic skills into a resumable plan-then-confirm workflow.

Use when you need to turn a vague idea into a confirmed design spec before implementation (new feature/component/behavior change). First check project context, then ask one question at a time, provide 2-3 options with trade-offs, finally output design in segments (~200-300 words each) with confirmation after each. Triggers: brainstorm, clarify idea, design spec, refine concept, requirement clarification.

Use when deciding whether a future ntn-sim-core follow-on, especially OMNeT++ / INET / estnet or other external-consumer/backend realism work, should be bootstrapped with OpenSpec instead of the repo's normal SDD/todo flow. Also use when a user explicitly mentions OpenSpec, opsx workflows, or wants a separate change/spec workflow for a new track without replacing existing ntn-sim-core authority.