What is mryll-skills?

A collection of Claude Code skills based on research, covering repository guidance, software design, code review, testing, explanations, study sessions, and discussions.

Use it for repository instructions, architecture discussions, code and pull-request reviews, testing guidance, technical explanations, and learning activities.

Related development tasks are grouped in one package instead of being installed and managed as separate skills.

mryll-skills — Plugin for Claude Code by mryll: A collection of Claude Code skills based on research…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add mryll/skills

agentmods

npx agentmods add plugins/mryll/skills/mryll-skills

Clone the repo

git clone --depth 1 https://github.com/mryll/skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/mryll/skills/mryll-skills.svg)](https://agentmods.dev/plugins/mryll/skills/mryll-skills)

Your own site

<a href="https://agentmods.dev/plugins/mryll/skills/mryll-skills"><img src="https://agentmods.dev/badge/plugins/mryll/skills/mryll-skills.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 16 skills cost 2,817 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

mryll-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json#mryll-skills · 25 lines

What it actually says

{
  "name": "mryll-skills",
  "source": "./",
  "description": "Mryll's collection of research-backed Claude Code skills",
  "version": "1.13.1",
  "strict": false,
  "skills": [
    "./skills/agentmd",
    "./skills/low-complexity",
    "./skills/vertical-slice-architecture",
    "./skills/codex-review",
    "./skills/codex-discuss",
    "./skills/test-namer",
    "./skills/dual-testing",
    "./skills/explain-pr",
    "./skills/como-si-fuera-de-boca",
    "./skills/pr-quiz",
    "./skills/study-session",
    "./skills/ste",
    "./skills/c4-model",
    "./skills/claude-review",
    "./skills/claude-discuss",
    "./skills/agent-context-auditor"
  ]
}

Contents

What it installs

The manifest is a name and a version. 16 skills travel with it, and installing the plugin installs all of them — 2,817 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside marketplace.json#mryll-skills in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

marketplace.json 952 B

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 25 lines scan A aff581a8745a

Subscribe to this mod's changes

mryll-skills is a plugin published in the GitHub repository mryll/skills (3 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Building agents Code review agent-instructions agent-skills agents-md ai-agents ai-coding-assistant claude

unit-tests-skills

Generate high-quality unit tests. Analyzes code, produces a reviewable Given-When-Then test case list, then writes the tests and verifies they compile and pass. Java support covers JUnit 5, Mockito, and AssertJ.

mavka-ai/unit-tests-skills · not measured

elon-stack

Five behavioral rules that stop a coding agent from optimizing things that should not exist. Karpathy's four rules hardened, plus a fifth on deletion.

AccountZero/elon-stack · not measured

agent-deck

Complete guide for managing AI coding agent sessions via agent-deck CLI - session lifecycle, MCP management, groups, profiles, and automation.

asheshgoplani/agent-deck · not measured

antimicrobial-resistance-scientist

Reasons from MIC distributions, ECOFFs, and phenotype–genotype concordance through EUCAST/CLSI AST, CARD/RGI and AMRFinderPlus resistomes, GLASS/WHONET/NARMS surveillance, carbapenemase/ESBL/MRSA mechanism panels, and heteroresistance PAP while treating breakpoint mixing, genotype-without-phenotype overclaim…

K-Dense-AI/scientific-agents · not measured

behavioral-ecologist

Reasons from versioned ethograms, Altmann focal/scan sampling, and activity budgets; scores with BORIS (Cohen’s κ), analyzes sequences with Markov/HMM tools, runs sham-controlled playbacks under ARRIVE 2.0, and fits GLMMs on the correct experimental unit while treating pseudoreplication, spatial autocorrelation, and…