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.

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.

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

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.

> 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'.

Expert in macOS app development using AppKit, SwiftUI for Mac, and XPC. Specializes in system extensions, menu bar apps, and deep OS integration.

Expert knowledge for Go development in Pennybot. Includes Bazel workflow, nogo linting, gazelle commands, and naming conventions. Use when writing, testing, or building Go code.

Build and troubleshoot lazygit customCommands in config.yml. Use for prompt-driven commands, context-specific keybindings, commandMenus, template-based construction, and conventional-commit style workflows.

>

Implement a quest from its spec without changing the spec. Use when a quest is in implementation and the user wants the spec executed fully, with decisions recorded in decisions.md.

Expert API testing specialist focused on comprehensive API validation, performance testing, and quality assurance across all systems and third-party integrations

HTTP client and API testing tool. Use when making HTTP requests, testing REST APIs, debugging endpoints, or when user mentions 'HTTP', 'REST', 'API', 'endpoint', 'GET', 'POST', 'curl', 'requests', 'status code', 'header', 'JSON API'. Supports GET/POST/PUT/DELETE/PATCH methods, custom headers, query parameters, request body handling, response analysis, and error handling.

Use when bootstrapping vibe-validate in a new repo, adjusting the config, or diagnosing setup. Covers vv init, vv doctor, vv config, templates, heterogeneous-language setup, generate-workflow, and dependency-lock-check.

Use the Linear MCP from the scaffolded Linear link to align implementation with issues/projects, suggest card updates, and keep Linear documentation in sync.

Integrates Firebase In-App Messaging into Flutter apps. Use when setting up in-app messaging, triggering or suppressing messages, managing user privacy and opt-in data collection, or testing campaigns.

Help the user turn vague guardrail ideas into a concrete project-level hook policy.

Use when integrating or maintaining applications built with keep-starknet-strange/starkzap. Covers StarkSDK setup, onboarding (Signer/Privy/Cartridge), wallet lifecycle, sponsored transactions, ERC20 transfers, staking flows, tx builder batching, examples, tests, and generated presets.

Autonomous long-running iteration for Codex CLI. Use when the user wants Codex to plan or run an unattended improve-verify loop toward a measurable or verifiable outcome, especially for overnight runs; it also covers repeated debugging, fixing, security auditing, and ship-readiness workflows. Do not use for ordinary one-shot coding help or casual Q&A.

Use twitter-cli for ALL Twitter/X operations — reading tweets, posting, replying, quoting, liking, retweeting, following, searching, user lookups. Invoke whenever user requests any Twitter interaction.

Doodlestein Self-Releaser - Fallback release infrastructure for building and releasing tools locally when GitHub Actions is throttled. Cross-platform builds via SSH, supply chain security (SLSA/SBOM/signing), quality gates, and offline capability.

gstackplusplus

antidev

Base URL: `{base}`

Propose–Act protocol to compare an EARS specification against the codebase, produce Phase 1 gaps, Phase 2 impact analysis, and Phase 3 remediation plan.

Operations - deployment pipeline, CI/CD, git workflow, dependency management, code formatting, Vite build, and cross-package migrations. Use for deploying, CI configuration, git operations, branch strategy, dependency upgrades, formatting, build tooling, and release management.

Understand code execution paths, method call chains, and data flow in decompiled Android applications using JADX-AI-MCP tools.

Setup and configure oh-my-claudecode (the ONLY command you need to learn)

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

Check and fix non-ASCII characters in documentation source files. Replaces Unicode with proper RST/LaTeX/ASCII markup per context. Use when editing tutorials, docstrings, or any sphinx-gallery .py files.

Build, run, and debug Minecraft Console Client (MCC) against a real local Minecraft Java server on Linux, macOS, or WSL. Use this whenever the user wants to compile MCC, start or inspect a local test server, connect MCC to a server, debug protocol or login issues, validate a code change end-to-end, or run MCC commands on a real server instead of guessing from static code.

Dynamic agent composition and orchestration system - create custom agents with unique personalities, voices, and trait combinations on-the-fly

Run comprehensive code coverage analysis including Rust unit tests, Python E2E tests, and flow tests.

{{前文}}

This document covers how to build, publish, flush caches, and test the TPMJS sprites tools.

The Jido AI framework extends the core Jido Agent SDK with powerful artificial intelligence capabilities. Rather than being a standalone system, Jido AI builds upon the foundation of the Jido Agent ar

Professional skills and methodology for API security testing

Search existing paper notes by keyword, author, domain, or topic

Expert guide for tracking user analytics, events, conversions, A/B testing, and data-driven insights. Use when implementing analytics, tracking user behavior, or optimizing conversions.

Testing patterns - TDD workflow, Vitest unit tests, Playwright E2E, mock strategies, and coverage targets. Use when writing tests, setting up test infrastructure, following TDD, or diagnosing test failures.