gabrielmoreira

gabrielmoreira/agent-skills-mirror

Agent Claude Code

Pure planning agent for the SwiftlyS2 / SW2 plugin ecosystem. It only loads the workspace rules and the SwiftlyS2-Toolkit, orchestrates three plan subagents to generate and converge a method-level plan, does not directly edit code or implement fixes, and only outputs a final TDD-based plan. It generates a prompt plan…

gabrielmoreira/agent-skills-mirror

Agent Claude Code

Review subagent for SwiftlyS2 / SW2 plugin tasks. It reviews the main agent’s plans, audit conclusions, or code modification proposals, specifically looking for omissions, architectural drift, lifecycle gaps, threading risks, and unnecessary bridge / shared / intermediate layers, until it can issue an explicit pass or…

gabrielmoreira/agent-skills-mirror

Skill Claude Code

SwiftlyS2 toolkit for creating, modifying, auditing, planning, reviewing, and directly editing C#/.NET SwiftlyS2 plugins. Use when working on SwiftlyS2 plugins involving Commands, Events, Hooks, Modules, Workers, Services, high-frequency runtime loops, NetMessages, Schema access, or IPlayer lifecycle issues.

gabrielmoreira/agent-skills-mirror

Command Claude Code

Command "client-command-hook-template.cs" from gabrielmoreira/agent-skills-mirror, covering swiftlys2 clientcommandhookhandler template, suitable scenarios, basic pattern, multi-command interception pattern and key points.

gabrielmoreira/agent-skills-mirror

Command Claude Code

Command "command-attribute-template.cs" from gabrielmoreira/agent-skills-mirror, covering swiftlys2 attribute command template, usage principles, critical constraints, handler return type must be void and commandalias is a shorter alias, not a prefixed variant.

gabrielmoreira/agent-skills-mirror

Command Claude Code

Command "command-service-template.cs" from gabrielmoreira/agent-skills-mirror, covering swiftlys2 service-owned command template, usage principles, example skeleton and checklist.

gabrielmoreira/agent-skills-mirror

Skill Claude CodeCodex

Install the agent skills into $DEVOHOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

gabrielmoreira/agent-skills-mirror

Skill Claude CodeCodex

Use when a question requires deep investigation using online information or web search, broad source-backed research, comparison of multiple perspectives, or synthesis beyond a quick lookup.

gabrielmoreira/agent-skills-mirror

Skill Claude Code

A workflow that turns an academic paper into a complete Chinese invention patent application, including its claims, description, abstract, and drawing notes. A patent application is a formal document used to seek legal protection for an invention.

gabrielmoreira/agent-skills-mirror

Cursor rule Cursor

Paper2Patent repository workflow for maintaining the paper-to-patent skill, prompt templates, patent drafting rules, and privacy boundaries.

gabrielmoreira/agent-skills-mirror

Skill Claude Code

Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut 80% of Claude Code's system prompt with no eval loss). Finds overconstraint, conflicting instructions, redundancy, stale facts, and…

gabrielmoreira/agent-skills-mirror

Skill Claude Code

Scaffold an isolated CLOUD dev box per agent (via crabbox + Daytona) for any codebase — the parallel-safe counterpart to dev-local-setup. Each agent gets its own full stack (own DB + dev server) and an in-box browser for e2e, so concurrent loops never collide on ports/state. Sets up the snapshot image, .crabbox.yaml…

gabrielmoreira/agent-skills-mirror

Skill Claude Code

Scaffold a one-command dev-local launcher for ANY codebase. Investigates the repo to find its services, ports, and infra dependencies, then generates a single scripts/dev-local.sh (up/down/status/logs/restart) that runs every dev server in one tmux session, plus a short skill doc describing it. Use when someone says…

gabrielmoreira/agent-skills-mirror

Skill Claude Code

Set up an end-to-end test suite in any repo, following practices that make e2e a reliable per-PR gate: real flows over bypass, layered assertions, a reusable auth/session helper, video+trace evidence, and a compounding suite. Use when a repo has no e2e (or weak e2e) and you want system-level tests — "set up e2e", "add…

gabrielmoreira/agent-skills-mirror

Skill Claude Code

Spin up a new loop (domain) in a file-based knowledge base — bootstrap the substrate if it's missing, gather the loop's charter, scaffold domains/ /README.md, then do ONE real test run and record it in the loop's Timeline and LOG.md. Use when the user says "set up a new loop", "create a domain", "start a new…

gabrielmoreira/agent-skills-mirror

Skill Claude CodeCodex

Delegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration. Use when delegating work to a non-Claude CLI agent, when the user says "tmux delegate", "run agent in tmux", "delegate to codex/aider", or when executor work…

gabrielmoreira/agent-skills-mirror

Skill Claude CodeCodex

Use when deciding WHERE to point SEO effort, not how to write a page. Triggers: a new site or brand with no rankings and no authority ("cold start", "starting from zero", "nobody knows us"), deciding what to double down on, a page or cluster that ranks but earns nothing, hunting emerging or newly-coined keywords…

gabrielmoreira/agent-skills-mirror

Skill Claude Code

Master skill — set up the full agent harness for any repo so an agent can work it reliably: legible (map-not-manual docs + custom lints), executable (one-command dev stack), verifiable (e2e gate + a verify-before-ship loop), plus commit hygiene and entropy control. Use when onboarding a new/unfamiliar codebase to…

gabrielmoreira/agent-skills-mirror

Skill Claude Code

Set a repo up to prove engineering-task work actually works before it ships. Investigates the repo, ensures a one-command dev stack (dev-local) exists, asks whether verification runs locally or in a sandbox (crabbox), confirms/installs the driver (the playwright-cli skill for web by default). Outputs three artifacts…

gabrielmoreira/agent-skills-mirror

Skill Claude CodeCodex

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends AIPex's capabilities with specialized knowledge, workflows, or tool integrations.

gabrielmoreira/agent-skills-mirror

Skill Claude CodeCodex

Minimalist UX/Interaction Audit Expert that deconstructs complex interactions through cognitive load and operational efficiency lenses. Use this skill when you need to perform a UX walkthrough audit on a Figma prototype or web interface, evaluating usability based on principles like fewer clicks, less UI elements, no…

gabrielmoreira/agent-skills-mirror

Skill Claude CodeCodex

WCAG 2.2 Accessibility Audit skill that systematically evaluates web pages against 8 core Success Criteria (1.1.1, 1.4.3, 1.4.11, 2.1.1, 2.1.2, 2.4.3, 2.4.7, 4.1.2) using accessibility tree inspection and visual analysis. Use this skill when you need to perform accessibility testing/auditing on a live webpage.

gabrielmoreira/agent-skills-mirror

Skill Claude CodeCodex

AI-powered browser automation using the AIPex Chrome Extension via MCP bridge. Use this skill when the agent needs to control a Chrome browser — navigating pages, clicking elements, filling forms, capturing screenshots, managing tabs, or downloading content — by connecting to the AIPex MCP bridge.

gabrielmoreira/agent-skills-mirror

Skill Claude CodeCodex

Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…