Solve one assignment problem file using a single endpoint with two logical tracks: (A) Math/Physics PDF problem solving (lecture slides/lecture notes as ground truth) and (B) code artifact generation. Save a final answer with detailed explanation next to the problem file.

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.

Autonomously diagnose Magento 2 message queue problems — backlog growth, stuck consumers, broker connectivity, DLQ overflow — and scaffold new queues (communication, topology, consumer, publisher) from a specification. Produces an AMQP Report with root cause and fix.

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.'

Autonomously generate a complete Magento 2 REST or GraphQL API from a plain-language spec — service contracts, repository, webapi.xml, and GraphQL schema with resolvers.

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.

Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go wrong.

Autonomously diagnose Magento 2 indexer issues, fix invalid or stuck indexers, and scaffold custom indexers from a spec — reads indexer state, mview changelog, and DB schema to produce a concrete fix or implementation plan.

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

Autonomously diagnose Magento 2 cache issues — FPC bypass, Redis pressure, stale blocks, and invalidation failures — and scaffold custom cache types. Produces a Cache Report with root cause and fix.

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

<!--

go-test-coverage

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.

Use when deciding the next sparse-ir-rs release version or checking whether a change set should be patch, minor, or major under Semantic Versioning

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.

Evaluate cross-framework parity for generated components and accessibility metadata. Use when emitter behavior changes or parity regressions are suspected.

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.

Component architecture: Terraform root modules, abstract components, component inheritance, versioning, mixins, catalog patterns

**🛡️ 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.

Execute framework-specific implementation jobs from job bundles (`prompt.md`, `ir.json`, `artifact.json`) and validate outputs package-by-package.

Build or modify a Pi extension. Use this whenever the user wants a custom slash command, extension tool, lifecycle hook, context filtering, session persistence, UI prompt, model/provider integration, or anything placed in ~/.pi/agent/extensions/. This skill is especially relevant when the user says “create a pi extension”, mentions /reload, wants custom command behavior, or needs extension code that uses Pi APIs rather than app code.

>

Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.

Use when working with scaleinvariance package for multifractal field simulation and analysis - Hurst exponent estimation, fractional Brownian motion (fBm), fractionally integrated flux (multiplicative cascades) (FIF), intermittency analysis, and Generalized Scale Invariance (GSI). Also use for scaling analysis of time series, turbulence data, atmospheric fields, or any task involving self-similar, cascade, or multifractal processes or fields.

Manage Signadot sandboxes, route groups, clusters, resource plugins, jobs, and smart tests using the signadot CLI. Use when a developer or platform engineer needs to create, update, inspect, or delete Signadot resources.

>

Use when you need to pick high-quality Unsplash images for product/design assets (avatars, headshots, portraits, large website backgrounds, and abstract wallpapers) and output real Unsplash URLs plus practical instructions for producing the right resolutions and aspect ratios (1:1, 4:5, 3:4, 16:9, 9:16).

Research a topic thoroughly in this repo and return a structured summary with file references. Use when you need to understand how something works, find patterns across modules, or audit implementations.

Run the repository's standard validation flow quickly and safely. Use when changes are made and you need confidence before commit or push.

Simplify and clarify existing code without changing behavior.

Seed a new runnable template under templates/NNN-slug/ from a short spec by chaining existing skills (intake → ship-faster stages) while keeping it clean and shareable (no secrets, minimal scope). Use when creating a new template quickly.

Use when you need to define or converge a project's visual direction. Scan project documentation to identify intent, then produce a design-system.md (either preserve existing style or pick from 30 presets). Triggers: design system, design spec, UI style, visual style, design tokens, color palette, typography, layout. Flow: scan → intent → (gate) preserve vs preset → deploy design-system.md after confirmation → (default) implement UI/UX per design-system.md (plan first, then execute).