mryll
UserPortable agent skills for AI coding agents — works with Claude Code, OpenAI Codex CLI, Gemini CLI, Cursor & GitHub Copilot: code review, vertical-slice architecture, Go testing strategy, low cognitive-complexity & AGENTS.md generation. Markdown-only — install with npx skills.
Categories
Indexed Skills (15)
agentmd
Generate a single canonical AGENTS.md context file plus minimal CLI-specific shim files that @-import it for coding agents that do not read AGENTS.md natively (Claude Code, Gemini CLI, Qwen Code). Based on "Evaluating AGENTS.md" (ETH Zurich, Feb 2026) which found auto-generated context files DECREASE performance by ~3% and increase costs by 20-23%, while minimal human-written files improve performance by ~4%. Use when the user says "generate CLAUDE.md", "create AGENTS.md", "generate context file", "agentmd", "create recommended CLAUDE.md", "generate agent instructions", "init context file", or any request to create/improve a coding agent context file for a repository. Replaces the default /init command which generates bloated, counterproductive context files.
codex-discuss
Iterative non-code discussion between the local agent and Codex CLI on any open-ended topic: diet, fitness, writing, decisions, strategy, study plans, life choices, brainstorming. Orchestrates an automatic back-and-forth debate where both agents critique, propose alternatives, and iterate on the user's idea until reaching consensus. Codex CLI runs READ-ONLY, forms its own opinions, and normally does not navigate the filesystem unless the user provides file paths. Use when the user says discuss with codex, iterate with codex, consult codex, debate with codex, ask codex for a second opinion, get codex's take, or brainstorm with codex, including pasting or describing a plan, draft, idea, decision, or proposal and wanting a critical iterative review. Does NOT trigger on code review, plan-mode review of implementation plans, architecture discussions, or any technical software-engineering analysis; use codex-review for those.
codex-review
Iterative code review and planning discussion between the local agent and Codex CLI. Orchestrates an automatic back-and-forth debate where both agents discuss findings, architecture decisions, or implementation plans until reaching consensus. Codex CLI runs READ-ONLY and never modifies files; model and reasoning effort come from the user's local Codex config. Supports plan mode: when the local agent has a plan ready, Codex evaluates and iterates on it before implementation, producing an updated consensus plan. Use when the user asks to review with codex, analyze with codex, discuss code with codex, iterate with codex, consult codex, ask codex, review the plan with codex, validate plan with codex, or any Codex CLI request for code review, architecture review, plan review, or implementation strategy. Does NOT trigger on non-code topics like diet, fitness, writing, life decisions, or general strategy; use codex-discuss for those.
como-si-fuera-de-boca
Explain anything — code, an error, a concept, or a non-technical topic — in the simplest, most plain-language way possible, ELI5-style, with a natural Río de la Plata (Argentine) voice that puts clarity first. Use ONLY when the user explicitly asks to have something dumbed down or simplified. Triggers (Spanish + English): 'explicámelo como si fuera de Boca' (or de River / de cualquier cuadro), 'explicámelo simple', 'explicalo fácil', 'más fácil', 'bajámelo un cambio', 'en criollo', 'como si tuviera 5 años', 'para tontos', 'ELI5', 'explain like I'm 5', 'dumb it down', 'in plain terms'. Optimized for technical material (code, architecture, tooling, errors) but the same method works for any topic. Do NOT use when the user wants full technical depth, a code review, or did not ask to simplify — this skill is for deliberate, on-request simplification, not for talking down to the user by default.
dual-testing
Language-agnostic strategy for testing code at the boundary with external infrastructure (databases, APIs, queues): integration tests with real infrastructure (e.g. Testcontainers) prove the full chain works for happy paths; unit/slice tests with mocks prove error-handling and mapping logic (domain error to status, input validation, infra failure). Works in any language/framework — Go, .NET/C#, Java, Python, TypeScript and more — with concrete references for Go, .NET (ASP.NET Core) and Java (Spring Boot) and an explicit path to adapt when no reference matches your language. Apply when designing a test strategy, creating a handler/feature/worker that needs tests, or deciding what type of test a scenario needs. Triggers: 'dual testing', 'integration vs unit', 'testcontainers vs mocks', 'what type of test', 'where should this test go', 'error path coverage'. Does NOT trigger on writing individual test assertions or test naming conventions (use test-namer for those).
explain-pr
Explain a GitHub Pull Request (PR) or GitLab Merge Request (MR) to the user in plain, easy-to-understand language: WHAT was done, WHY/what for, and HOW — with the relevant code snippets embedded. Invoke this proactively and automatically right after creating or finishing a PR/MR (e.g. after running `gh pr create`, `glab mr create`, or pushing a branch and opening a PR/MR), even if the user did not explicitly ask for an explanation. Also use whenever the user asks to explain, summarize, walk through, recap, or 'tell me what you did' about a PR/MR or the changes in a branch. Works with any coding agent and relies on the local git diff, so it does NOT require gh/glab to function. Do NOT use for unrelated code reviews, bug hunting, or writing the PR/MR description itself — this skill only explains finished work back to the user.
low-complexity
Enforce low Cognitive Complexity (SonarSource) and low Cyclomatic Complexity in ALL code written or modified, in any programming language, framework, or platform. This skill MUST activate automatically whenever code is being written, generated, modified, or refactored — no explicit trigger needed. Triggers include writing any function, method, class, module, script, handler, endpoint, test, or code block. Also triggers on "low complexity", "cognitive complexity", "cyclomatic complexity", "reduce complexity", "simplify code", "too complex", "refactor for readability", "clean code", "implement", "fix bug", "add feature", "generate test", "optimize", "rewrite", "scaffold".
pr-quiz
Use when a PR/MR explanation was just delivered (e.g. right after the explain-pr skill finishes) and the change was substantially agent-written, or whenever the user asks to be quizzed on a change: 'quiz me on this change', 'tomame el quiz', 'quiz del MR', 'tomame la lección', '/pr-quiz'. Counters comprehension debt: a formative, change-specific check that the user can defend code they delegated to a coding agent. Do NOT use for code review, bug hunting, or explaining changes (that's explain-pr) — this skill asks questions and grades answers.
study-session
Use when the user asks for a guided comprehension/study session over existing code: '/study-session', 'study session', 'sesión de estudio', 'repasemos <subsystem>', 'help me understand <area>', or a recurring comprehension-recovery ritual. Recovers AND measures the mental model of code the user delegated to coding agents. Two modes: deep (45-60 min) and checkpoint (10-15 min). Do NOT use for implementing features, fixing bugs, or code review — nothing is modified in a study session except the comprehension tracking page.
test-namer
Guide for writing expressive, behavior-focused tests following Vladimir Khorikov's testing principles. Apply when writing, reviewing, or renaming any test (unit, integration, e2e) in any programming language. Triggers: writing tests, creating test files, adding test cases, reviewing test names, 'test naming', 'rename tests', 'Khorikov', or any test creation task. Covers: naming conventions (plain English over rigid policies), what to test (behavior not implementation), testing styles (output > state > communication), and pragmatic test investment.
vertical-slice-architecture
Enforce Vertical Slice Architecture (VSA) when building applications in any language (Go, .NET/C#, Java, Kotlin, TypeScript, Python, etc.) and any type (web API, mobile backend, CLI, event-driven). Organize code by feature/use-case instead of technical layers. Each feature is a self-contained vertical slice with a single entry point that receives the router/framework handle and its dependencies. Use when the user says "vertical slice architecture", "VSA", "organize by feature", "feature-based architecture", "slice architecture", or when building a new app or feature and the project already follows VSA conventions. Also use when reviewing or refactoring code to align with VSA principles.
c4-model
Create or review C4 model architecture documentation (official c4model.com notation) as diagrams-as-code in Markdown — C4-PlantUML where the target renders it (GitLab.com does; verify Self-Managed instances), Mermaid flowchart/sequence conventions otherwise. Use whenever the user wants to visualize or document the architecture of a system or codebase — even if they never say "C4" — for requests like "diagram this service", "document the architecture", "how do the pieces of this repo fit together", "draw the system/containers/components", or when reviewing existing C4/Mermaid architecture diagrams for correctness. Covers system context, system landscape, container, component, dynamic, and deployment views. Do not use for generic flowcharts, ER diagrams, standalone Kubernetes topology, API contract documentation (OpenAPI/AsyncAPI), or architecture prose without diagrams.
claude-discuss
Iterative non-code discussion between the local agent and Claude Code CLI on any open-ended topic: diet, fitness, writing, decisions, strategy, study plans, life choices, brainstorming. Orchestrates an automatic back-and-forth debate where both agents critique, propose alternatives, and iterate on the user's idea until reaching consensus. Claude Code runs READ-ONLY (headless plan mode), forms its own opinions, and normally does not navigate the filesystem unless the user provides file paths. Use when the user says discuss with claude, iterate with claude, consult claude, debate with claude, ask claude for a second opinion, get claude's take, or brainstorm with claude, including pasting or describing a plan, draft, idea, decision, or proposal and wanting a critical iterative review. Does NOT trigger on code review, plan review of implementation plans, architecture discussions, or any technical software-engineering analysis; use claude-review for those.
claude-review
Iterative code review and planning discussion between the local agent and Claude Code CLI. Orchestrates an automatic back-and-forth debate where both agents discuss findings, architecture decisions, or implementation plans until reaching consensus. Claude Code runs READ-ONLY (headless plan mode) and never modifies files; model and effort come from the user's local Claude Code config. Supports plan review: when the local agent has a plan ready, Claude evaluates and iterates on it before implementation, producing an updated consensus plan. Use when the user asks to review with claude, analyze with claude, discuss code with claude, iterate with claude, consult claude, ask claude, review the plan with claude, validate plan with claude, or any Claude Code request for code review, architecture review, plan review, or implementation strategy. Does NOT trigger on non-code topics like diet, fitness, writing, life decisions, or general strategy; use claude-discuss for those.
ste
Write, rewrite, translate, or check content in Simplified Technical English (ASD-STE100), with four compliance levels (verified / marked / clean / raw) backed by the official dictionary and a checker script. Explicit invocation only: run this skill ONLY when the user types /ste or explicitly asks for the ste skill by name. NEVER auto-invoke it on mentions of STE, STE100, ASD-STE100, Simplified Technical English, or controlled language, and NEVER on a request to answer or write in ASD-STE100 - that is a request about tone, not a request to run this skill.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.