Pair Codex with Pluto.jl notebooks using MCP tools. Use for discovering visible Pluto servers, attaching to running notebooks, opening notebooks headlessly, inspecting @bind controls, setting bond values, reading compact state, or exporting HTML.

Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.

Audit SSOT-to-submission drift and create journal submission manifests from canonical manuscript artifacts.

You are an expert at building modern command-line tools following current best practices. Use this guide when creating CLI applications.

Use this skill to generate images locally using the FLUX.2 Klein 4B model.

Use NoCFO CLI for bookkeeping, invoicing, reporting, and schema introspection. Use when the user wants to query or update NoCFO data from an agent through terminal commands.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work. In this repository, package or lane branches must close through package-first evidence and integration handoff rather than the generic local merge or PR menu.

Gaggiuino skill for machine control, espresso shot analysis through profile intent, dial-in guidance, shot graph rendering, and synchronized overlay videos. Use when checking machine status, analyzing latest or historical shots, switching profiles, reading settings, or generating shot graphs and overlay videos.

Adversarial evolutionary QA using Digital Red Queen. Code and tests coevolve via deterministic state machine execution.

Check skill documentation by applying corrections discovered during execution with

A convenient wrapper over Flutter golden tests. Automates multi-platform and multi-device golden testing: manages device configurations, themes, localization, fonts, and CI environments.

Use this skill when:

Generate TDD task breakdown for SDD workflow. Use when breaking down design into implementable tasks with test-first approach. Invoked via /sdd-tasks <feature-name>.

Superteam Academy — decentralized learning platform on Solana with soulbound XP tokens (Token-2022), Metaplex Core credentials, course registry, achievements, and creator incentives. Covers Anchor program development, testing with LiteSVM/Mollusk/Trident.

Manage Python dependencies, lock files, and project environments using the uv package manager.

Analyze the current repo structure, build system, test setup, and conventions to provide a practical onboarding guide. Use when new to a codebase, joining a project, or wanting to understand how a repo is organized. Triggers on getting started, new to repo, onboard, how does this repo work, repo structure, codebase overview.

Create and improve Claude Code skills. Use when drafting new skills, writing SKILL.md files, improving skill descriptions, or structuring skill directories. Triggers on requests to create skills, write skills, draft skills, improve skill triggering, or fix skills that aren't activating.

Scan Apple Mail inbox for unread, actionable, and priority messages. Use this when the user asks to check their email, see unread messages, find urgent emails, or triage their inbox. Returns categorized email counts and details from the last 24-48 hours.

This skill guides you through writing tests for this Bun + Hono project.

Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization, compound ID, for metabolomics and MS data processing.

Keeps Which Key Lazy documentation in sync with code changes. Use this skill when you need to verify documentation accuracy after code changes, or when checking if documentation (README.md, CLAUDE.md) matches the current codebase. The skill can work bidirectionally - from docs to code verification, or from code changes to documentation updates.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. Includes 149 tests e2e pour Construction Gauthier / Ma Place RH.

Provision instant temporary Postgres databases via Claimable Postgres by Neon (pg.new). No login or credit card required. Use for quick Postgres environments and throwaway DATABASE_URL for prototyping.

Add a new REST API endpoint to the Petal Pro API layer. The argument should describe the resource and actions.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. Activate even when the user says 'create a skill for X', 'the skill is not triggering', 'improve this skill description', 'the agent is not using the skill', 'add a skill to teach the agent how to do X', 'this skill is wrong', or 'update the skill' without explicitly mentioning evals or benchmark.

Contribute skills back to upstream via branch and PR

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.

Generate FOSMVVM Fields protocols with validation rules, FormField definitions, and localized messages. Define form contracts once, validate everywhere.

The CLI uses Chrome/Chromium via CDP directly. Install via `npm i -g agent-browser`, `brew install agent-browser`, or `cargo install agent-browser`. Run `agent-browser install` to download Chrome. Run

Prisma ORM expert for schema design, migrations, query optimization, relations modeling, and database operations. Use PROACTIVELY for Prisma schema issues, migration problems, query performance, re...

Generate destination code from analysis documents (OpenAPI or web-based) and user-selected actions

Measure quality effectively with actionable metrics. Use when establishing quality dashboards, defining KPIs, or evaluating test effectiveness.

Master orchestrator for generating Ralph Wiggum-compatible prompts. Analyzes task requirements and routes to appropriate generator (single-task, multi-task, project, or research). Use when you need to create any Ralph loop prompt and want automatic selection of the right generator.

>

Cut a release of hubble-satnet-decoder — bumps version, generates release notes from commits, commits, tags, and pushes to trigger the PyPI release workflow. Use this skill when the user wants to release, publish, cut a release, bump version, or push a new version to PyPI. Invoke via /release.

Add new feature with full validation: $ARGUMENTS (feature name)

Implements a task locally (without worktree) following TDD with IPC status reporting. Use when working on a task in an existing branch.

Creates, extends, and implements OpenAPI 3.x specifications.

Overseer agent. Reads the full board and company state every run. Activates specialist agents from the agency-agents pool when blockers or opportunities are detected. Coordinates cross-functional work that no single core agent can handle alone. Posts decisions and specialist activations to the board.

Use when generating random genomic intervals for simulation, background sets, or statistical testing.

Performance optimization skill for code, queries, builds, and runtime. Use when improving speed, reducing bundle size, fixing memory leaks, or optimizing database queries.

Orchestrate the full Speckit spec-driven development workflow sequentially, from constitution through implementation, ensuring each step completes before advancing.

- React/Next.js wallet integration with Wagmi v3 for EVM chains

1. Run all checks sequentially, capturing each result:

Python backend development standards for FastAPI, SQLModel, and pytest. Enforces Ruff linting, Pyright type checking, and test coverage. Use when writing Python code, creating API endpoints, implementing services, adding database models, or modifying backend logic in src/merchant/, src/payment/, or src/apps_sdk/.

Analyze codebase or context per foundation analyze command.

Run typecheck, lint, and tests for both frontend and Go backend to tidy and test the code prior to committing and pushing.

DevOps specialist for CI/CD, infrastructure as code, and deployment automation. Invoke for pipelines, Docker, Kubernetes, cloud platforms, GitOps. Keywords: DevOps, CI/CD, Docker, Kubernetes, Terraform, GitHub Actions.

**The AI should act as an intelligent Project Manager**, analyzing each request and automatically selecting the best specialist(s) for the job.