> Write integration tests that exercise real dependencies using test databases and containers

Apply the Design Thinking process (Empathize, Define, Ideate, Prototype, Test) to solve complex user problems.

Design system architecture from approved requirements. Technology-agnostic process covering quality attribute analysis, architectural style selection, multi-view documentation (arc42/4+1), and ADR creation. For new systems or major architectural changes.

|-

DeePMD-kit training, finetuning, testing, and model inspection skill. Use this skill whenever training or finetuning a Deep Potential (DP / DPA-1 / DPA-2) model, running model tests, or inspecting model parameters. Training is split into a preparation phase (data conversion + input.json generation, always local) and an execution phase (dp CLI commands, local or via dpdisp skill on hpc or Bohrium).

Comprehensive unit testing with xUnit, mocking, test patterns, and best practices for .NET applications

Create and clean up isolated git worktrees for parallel agent tasks, compatible with spec-kit.

>

Interact with Supabase through the official CLI: install/check the CLI, initialize or link projects, run the local stack, manage migrations and schema diffs, push or pull database changes, generate types, manage Edge Functions and secrets, and troubleshoot CLI auth or linking issues. Use when the user mentions Supabase CLI commands, a `supabase/` directory, project refs, migrations, `db push`/`db pull`, `functions deploy`, or local Supabase services.

fizzy

Add a newly dropped `.webp` swag image to this portfolio's existing swag collection by gathering the required metadata, renaming the asset to the next numeric filename, and updating `src/assets/swag/swag.ts`. Use when the user wants to add a new swag item, mentions a dropped swag image, or asks to update the swag collection in this repository.

Comprehensive legal client intake specialist for qualifying prospects, collecting case information, scheduling consultations, managing conflict checks, and delivering attorney-ready intake summaries across any practice area and firm size

Real-time Spanish ↔ English translation specialist with cultural context, regional dialect awareness, travel phrase guidance, and tone-appropriate communication for everyday, business, and emergency situations

Convert implementation-ready specs to executable JSON format for autonomous task completion.

Analyze and edit connected Google Sheets with range precision. Use when the user wants to find a spreadsheet, inspect tabs or ranges, search rows, plan formulas, clean or restructure tables, write concise summaries, or make explicit cell-range updates.

Inspect, create, import, summarize, and update Google Slides presentations through connected Google Slides data. Use when the user wants to find a deck, read slide structure, summarize a presentation or specific slide, understand charts, graphs, or other slide visuals by combining slide text with thumbnail-based image understanding, create a new presentation, import a `.ppt`, `.pptx`, or `.odp`, or make general content edits in Google Slides. For visual polish on an existing deck, such as formatting cleanup, alignment fixes, overflow cleanup, or slide-by-slide deck cleanup, prefer `google-slides-visual-iteration`.

Use when the user wants to capture, organize, or retrieve project knowledge as a git-committable memory system at project-memory/ at the project root. Trigger proactively on phrases: 'lesson learned', 'save lesson', 'wrap up session', 'postmortem', 'retro', 'capture this', 'what did we learn', 'why did this fail', 'have we seen this before', 'add to lesson', 'end of session', 'project memory', 'team memory'. Also trigger when a mission is ending and no lesson has been captured yet, or when the user asks a question whose answer likely lives in prior work. Backed by qmd for hybrid BM25 + vector search over every subsystem under project-memory/.

Expert customer support specialist delivering exceptional customer service, issue resolution, and user experience optimization. Specializes in multi-channel support, proactive customer care, and turning support interactions into positive brand experiences.

Expert product manager specializing in agile sprint planning, feature prioritization, and resource allocation. Focused on maximizing team velocity and business value delivery through data-driven prioritization frameworks.

> CONSUMER-DRIVEN CONTRACT TESTING INVERTS THE TRADITIONAL INTEGRATION TEST — EACH CONSUMER PUBLISHES THE EXACT SHAPE IT EXPECTS, THE PROVIDER VERIFIES AGAINST EVERY CONSUMER'S CONTRACT IN CI, AND A B

> Structuring information — card sorting, tree testing, mental models, labeling systems, organization schemes, findability

> Mock modules, functions, and timers in Vitest and Jest to isolate units under test

Generates optimized descriptions for video platforms from transcripts and supplementary material. Use when the user asks for a video description or provides a transcript for video preparation.

Visual-reference-to-app implementation loop for building or restyling a web app screen to match a provided reference image. Use when Codex is asked to take a screenshot/reference/mockup/image and build an app or route that looks like it, especially when the task requires hosting the app, capturing Playwright screenshots, comparing against the reference, and repeatedly editing until the result is close.

Specialized planning agent for creating detailed implementation plans

Multi-LLM parallel planning with context-safe auto-save.

Screenshot-obsessed, fantasy-allergic QA specialist - Default to finding 3-5 issues, requires visual proof for everything

Manage build system, testing infrastructure, CI pipelines, and release automation. Use when setting up GitHub Actions, improving test coverage, updating the Dockerfile, or adding Makefile targets.

Create new Agent Skills (SKILL.md files). Use when asked to create, write, or add a new skill for Claude Code, OpenCode, or other skills-compatible agents.

Use jj (Jujutsu) for local version control instead of git. Activate when: the repo has a .jj/ directory, the user or project config mentions jj, the user says 'use jj', or any version control operation is needed in a jj-managed repo. Also use this skill when the user asks to commit, branch, stash, rebase, or perform any git-like operation in a repo that uses jj. If unsure whether the repo uses jj, check for a .jj/ directory.

Map MD-DDL data product declarations to Open Data Product Specification (ODPS) v4.0 YAML manifests for external cataloguing, marketplace publication, and cross-platform interoperability. Use when the user wants to publish data products, generate ODPS YAML, or align with external data product standards.

Use when a feature or implementation-ready slice needs to become a human-sized story packet, acceptance tests, enabler work, spec handoff, implementation-plan input, and execution context without overwhelming the user.

Transform vague agent instructions into formal "Contracts" that specify deliverables, scope, and validation criteria, mirroring real-world service agreements to ensure reliability.

Decide when raster tiling is needed and how to structure GDAL-based pipelines.

Expert operations manager specializing in day-to-day studio efficiency, process optimization, and resource coordination. Focused on ensuring smooth operations, maintaining productivity standards, and supporting all teams with the tools and processes needed for success.

End-to-end audit workflow for evaluating the safety of open-source

INVOKE THIS SKILL as the primary orchestrator. Routes tasks to specialized agents and coordinates complex workflows.

Analyze a codebase for improvements across multiple dimensions — test coverage gaps, documentation quality, performance, API ergonomics, correctness. Use when the user wants to find what's missing or could be better in their project.

Ralph-orchestrator is an autonomous coding loop that coordinates specialized AI agents ("hats") to implement features from specifications.

Elixir troubleshooting, debugging, and problem investigation

> Confirmation dialogs — destructive action writing, consequence clarity, and specific button labels that make irreversibility unmistakable

> Separate data-fetching containers from stateless presentational components

> HTTP STATUS CODES ARE THE RESPONSE CONTRACT BETWEEN SERVER AND CLIENT — CORRECT CODE SELECTION ENABLES ERROR HANDLING, RETRY LOGIC, AND MONITORING WITHOUT PARSING RESPONSE BODIES. MISUSING STATUS CO

Verifies game logic through unit tests and automated gameplay simulations.

Workflow for evaluating and refining agent debugging capabilities using designated test cases and Swarm principles. Use when evaluating subagent performance or creating benchmarks. Do not use for regular bug fixing.

Define RPO/RTO, implement PITR/Snapshots, and test restores.

Reference for every RVST CLI mode and test-harness command. Use whenever you need to validate layout, drive a user interaction, or investigate a render bug without a visible window.

Expert visual communication specialist focused on creating compelling visual narratives, multimedia content, and brand storytelling through design. Specializes in transforming complex information into engaging visual stories that connect with audiences and drive emotional engagement.

> Manage Drizzle schema evolution with drizzle-kit generate/push/migrate and introspect

INVOKE THIS SKILL when: (1) Writing new code, (2) Refactoring, (3) Debugging, (4) Writing tests. Triggers: 'write code', 'implement', 'fix bug', 'refactor', 'add tests'.