This is an AI-first project: any contributor — human or model — should be able to land a change that respects the architecture without needing to read the whole codebase first. The rules below are che

>

SoNash project context injected into agent definitions via skills: field

This skill identifies and prevents common testing anti-patterns that make test suites unreliable, slow, and difficult to maintain. It provides detection strategies and refactoring solutions for health

>

Run unit and integration tests

>

>

>

>

Create and install Codex custom agent roles in ~/.codex/config.toml, generate role config files, enforce supported keys, and guide users through required role inputs (model, reasoning effort, developer_instructions).

Generate structured test cases from requirements and specification documents using test model-based approach per ISO 29119-4.

Create a structured specification document from user ideas and requirements. Use when the user wants to create a spec, write a specification, document requirements, or start a new feature design.

'Work with Cargo commands, workspace configuration, dependency management, and build systems. Use when managing dependencies, configuring workspaces, building projects, running tests, or publishing crates. Handles Cargo.toml configuration, workspace setup, dependency resolution, and build commands.'

Builds and optimizes DSPy (dspy) programs end-to-end: signatures, modules, compilation/optimization, evaluation, and debugging. Use when the user mentions dspy/DSPy, Signature, Module, teleprompter/optimizer, compile, evaluate, few-shot, RAG, tool use, or local LLM endpoints (Ollama/vLLM/LM Studio).

Use this skill for Pest PHP testing in Laravel projects only. Trigger whenever any test is being written, edited, fixed, or refactored — including fixing tests that broke after a code change, adding assertions, converting PHPUnit to Pest, adding datasets, and TDD workflows. Always activate when the user asks how to write something in Pest, mentions test files or directories (tests/Feature, tests/Unit) or architecture tests. Covers: test()/it()/expect() syntax, datasets, mocking, browser testing, arch(), Livewire component tests, RefreshDatabase, and all Pest 3 features. Do not use for editing factories, seeders, migrations, controllers, models, or non-test PHP code.

>-

name: CI

Plans a user-provided feature idea by reading SPEC and code (read-only), analyzing scope, proposing a design aligned with existing architecture, optionally clarifying underspecified requirements with focused questions, and opening a GitHub issue that documents requirements, assumptions, design, subtasks with dependencies, and acceptance criteria—without modifying the repository. Use when the user wants a feature scoped and filed as an issue before any implementation, spec edits, or PR work.

E2E testing conventions for Protocol Designer and Labware Library using Playwright + pytest in e2e-testing/. Use when writing, running, or modifying end-to-end tests, page objects, or Playwright tests.

Documentation style guide and rules for creating documentation

Build and integrate with the Mesh Multisig (Cardano multisig wallet) codebase. Use when working on multisig wallets, bot API, v1 REST endpoints, wallet flows, governance, or Cardano treasury tooling.

>-

Create and configure Claude Agent SDK applications with TypeScript or Python, including MCP integration, subagents, permissions, and custom tools. Use when building Claude Code agents, integrating MCP servers, or creating specialized AI agents.

Run, configure, and verify the Zelf backend API. Use when working on backend setup, local execution, tests, Mongo requirements, route verification, or docs-related backend workflows.

When triggered, execute the following steps in order. Each step should be a distinct phase with a clear handoff.

This is a new rule

Interactive PRD exploration and Product Decision Record creation (greenfield)

Implements backend features and bug fixes in this Go project, maintains router-based backend API documentation with request/response JSON contracts, updates Postman collections, and validates changes with build and test commands.

Test that components send correct query parameters or request arguments. Use when testing filtering, sorting, pagination, or any read operation where request parameters matter. Use for test-scoped mock customization.

Create valid Opentrons Python API protocols for OT-2 and Flex robots. Use when creating, writing, editing, or helping with protocol files, liquid handling automation, or Opentrons protocol development. Also use when debugging protocol errors to trace into API source code.

Deploy RHDH to an OpenShift cluster using local-run.sh for E2E test execution, with autonomous error recovery for deployment failures

Maintains the @ekaone/mask-card TypeScript library (credit card masking). Use when working on PAN/credit card masking, maskCard/maskCardAuto/detectCardType/isValidCard changes, PCI display guidance (first 6 + last 4), docs/examples, Vitest tests, tsup builds, versioning, or npm publishing for this repo.

Updates benchmark documentation with latest results including README tables, speedup plots, and library metadata. Use when updating documentation, generating comparison tables, or when the user mentions update_docs.sh or documentation generation.

Analyzes Claude Code usage patterns and provides comprehensive recommendations. Runs usage analysis, discovers GitHub community resources, suggests CLAUDE.md improvements, and fetches latest docs on-demand. Use when user wants to optimize their Claude Code workflow, create configurations (agents/skills/commands), or set up project documentation.

Build tool for Go projects. Use when the user wants to create, edit, or understand Way-specific Magefiles, build targets, or automate Go project tasks.

Living documentation auditor that compares requirements vs UI/behavior vs API contract vs test results to detect spec drift, outdated docs, and undocumented features.

tiptap

Use to verify if the code/logic aligns with the Vietnamese business spec. Mandatory cross-referencing with BR-* rules before implementation.

Use when working in the ackermann_rover_humble repository or changing its Docker, Gazebo, RTAB-Map, Nav2, ros2_control, RealSense, PX4, rover monitoring, Control Center, tmux session, or verification flows. Provides the repo-specific subsystem map, launch/script entrypoints, architecture references, and mandatory validation workflow.

Set or refine source-control policy for repository structure, branch naming, merge strategy, commit hygiene, and secrets-in-git discipline. Use when bootstrapping a repo, tightening PR flow, or documenting branch and release policy.

Enforce the main OpenSpec spec format with overview, scope, interfaces, and requirements.

Refresh hackathon submission materials for this repo whenever features, docs, or product positioning change. Use when the user asks to update submission content, rewrite judging criteria answers, regenerate the latest product summary, or prepare current demo/pitch artifacts from the codebase state.

Analyze, trim, and optimize project dependencies

Apply ML/AI project delivery guidance for data exploration, feasibility, experimentation, testing, responsible AI, and operating ML systems. Use when the repo includes model training, inference, data science workflows, or ML-specific delivery planning.

Apply when designing or implementing REST API endpoints, routes, or controllers. Covers URL conventions, HTTP methods, status codes, error responses, pagination, versioning, authentication, security, caching, file uploads, health checks, and common API antipatterns. Framework-agnostic HTTP-level patterns. Project conventions always override these defaults.

>

Validate readiness to advance between development phases. Produces a PASS/CONCERNS/FAIL verdict with specific blockers and required artifacts.

Guide for designing and implementing native-feeling, "good Mac citizen" apps: fast, elegant, accessible, and deeply integrated with macOS workflows.

Use when a user brings a new capability, feature request, or enhancement need for greater in vague terms. Interviews conversationally and produces a scoped-need document. Applies Gate 1 (greater-mission alignment), Gate 2 (narrowest scope with API stability), Gate 3 (specialist routing).