explain-pr SKILL.md skillB

explain-pr from mryll/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add mryll/skills/explain-pr@v1.2.0

Pins v1.2.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
mryll/skills
Path
skills/explain-pr/SKILL.md
Versions recorded
5
Latest version
v1.2.0, committed Aug 4, 2026
First version recorded
May 29, 2026
Size
11,561 bytes
Repository stars
9
License
MIT

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…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Explain PR — explain a PR/MR in plain language

Turn a freshly created Pull Request / Merge Request into a clear, friendly explanation the user can read in one pass to understand **what** changed, **why** it was done, and **how** it works — with the relevant code shown inline.

This replaces the manual prompt a user would otherwise type ("explain what you did, why, and how, in simple terms, with the relevant code"). The point is that the user shouldn't *have* to ask: once a PR/MR exists, they almost always want this recap.

## When to use this skill

Trigger it on your own, without waiting to be asked, right after a PR/MR is created or finished — that's the moment the user wants the recap. Concretely:

- Just after `gh pr create`, `glab mr create`, or opening a PR/MR through any other means.
- When the user says things like "explain the PR", "what did you change?", "walk me through this MR", "recap the changes" — in any language.

If you just finished a PR/MR in this same conversation, you already did the work — you know most of the *why* firsthand. Use that, but still anchor the *what* and *how* in the real diff (see below) so nothing is misremembered or invented.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add mryll/skills/explain-pr@sha256:b3f27002de3c1e88

The line at the top of this page pins the label v1.2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ge2qhglsmxd6slqe.svg)](https://markdownregistry.com/a/art_ge2qhglsmxd6slqe)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between May 29, 2026 and Aug 4, 2026, about one every 17 days. Its first recorded version is graded F and its latest B.

versioncommittedcommitsizeaudit
v1.2.0 latest2026-08-04 d6129dc 11,561 BB view · diff
v1.2.02026-08-04 d90ab32 11,561 BB view · diff
v1.1.02026-07-13 43a1b85 11,070 BB view · diff
v1.0.02026-05-31 7e302ca 9,465 BA view · diff
v1.0.02026-05-29 df1eb43 9,469 BF view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No prompt-injection phrasing (matched: ignore previous instructions)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11561 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

mryll/skills · 9 stars · license MIT · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ge2qhglsmxd6slqe
GET https://markdownregistry.com/api/v1/resolve?ref=mryll/skills/explain-pr
GET https://markdownregistry.com/api/v1/blob/b3f27002de3c1e8877572c3bee98ae9c25374d3bd25b43c5da949e02c76bc417

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from mryll/skills

AGENTS.md AGENTS.md file
mryll/skills · AGENTS.md
git:20260831.dc93fe8 · audit A · 9 stars
CLAUDE.md CLAUDE.md file
mryll/skills · CLAUDE.md
git:20260601.048b127 · audit A · 9 stars
agent-context-auditor SKILL.md skill
mryll/skills · skills/agent-context-auditor/SKILL.md · Audita y produce los archivos de contexto de un repositorio para coding agents — AGENTS.md, CLAUDE.md…
v0.3.1 · audit A · 9 stars
agentmd SKILL.md skill
mryll/skills · skills/agentmd/SKILL.md · Generate a single canonical AGENTS.md context file plus minimal CLI-specific shim files that @-import it for coding…
v1.2.0 · audit A · 9 stars
c4-model SKILL.md skill
mryll/skills · skills/c4-model/SKILL.md · Create or review C4 model architecture documentation (official c4model.com notation) as diagrams-as-code in Markdown —…
v1.0.0 · audit A · 9 stars
claude-discuss SKILL.md skill
mryll/skills · skills/claude-discuss/SKILL.md · Iterative non-code discussion between the local agent and Claude Code CLI on any open-ended topic: diet, fitness…
v1.0.0 · audit B · 9 stars
claude-review SKILL.md skill
mryll/skills · skills/claude-review/SKILL.md · Iterative code review and planning discussion between the local agent and Claude Code CLI. Orchestrates an automatic…
v1.0.0 · audit B · 9 stars
codex-discuss SKILL.md skill
mryll/skills · skills/codex-discuss/SKILL.md · Iterative non-code discussion between the local agent and Codex CLI on any open-ended topic: diet, fitness, writing…
v1.2.3 · audit B · 9 stars
codex-review SKILL.md skill
mryll/skills · skills/codex-review/SKILL.md · Iterative code review and planning discussion between the local agent and Codex CLI. Orchestrates an automatic…
v1.3.1 · audit B · 9 stars
como-si-fuera-de-boca SKILL.md skill
mryll/skills · skills/como-si-fuera-de-boca/SKILL.md · Explain anything — code, an error, a concept, or a non-technical topic — in the simplest, most plain-language way…
v1.0.0 · audit A · 9 stars
dual-testing SKILL.md skill
mryll/skills · skills/dual-testing/SKILL.md · Language-agnostic strategy for testing code at the boundary with external infrastructure (databases, APIs, queues)…
v1.1.0 · audit A · 9 stars
low-complexity SKILL.md skill
mryll/skills · skills/low-complexity/SKILL.md · Enforce low Cognitive Complexity (SonarSource) and low Cyclomatic Complexity in ALL code written or modified, in any…
v1.0.1 · audit A · 9 stars

Every file in mryll/skills

Browse by kind, by grade B, or by owner.