pr-review SKILL.md skillA
pr-review from eagerworks/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add eagerworks/skills/pr-review@v2.1.0Pins v2.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- eagerworks/skills
- Path
skills/pr-review/SKILL.md- Versions recorded
- 6
- Latest version
- v2.1.0, committed Sep 12, 2026
- First version recorded
- Aug 21, 2026
- Size
- 9,016 bytes
- Repository stars
- 15
- License
- MIT
Reviews a branch, PR, staged, or working-tree diff for correctness, security, repo-convention, test-coverage, and documentation gaps, returning severity-rated findings without editing code. Use when asked to "review my branch/PR", "is this ready to merge", "check this diff before I push", "does this need an ADR", or to apply fixes for findings from a previous review round. When the target is a GitHub PR, the same report is also posted to the PR — as inline comments on each finding's line plus…
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
# PR Review Skill Reviews a diff — a branch, a PR, staged changes, or working-tree changes — against five fixed lenses: correctness, security & data integrity, repo-convention conformance, test coverage, and documentation & decision capture. Returns structured, evidence-backed findings with severities. This is **not** a linter and does **not** replace CI: skip anything a linter or type checker already catches, and don't re-derive what a failing test already proves. By default this is a **read-only** review: no file is edited, no commit is made, nothing is pushed. See `references/workflow.md` if the user explicitly wants findings fixed automatically. When the review targets a GitHub PR (`review PR #N`, or the branch under review has an open PR), the report is printed to the console **and** posted to the PR so it stays with the PR and the whole team can read it — by default as a GitHub review with inline comments on each finding's line plus a summary body, or as a single plain comment when `.eagerworks/pr-review.json` sets `review.commentStyle: "summary"`. If `gh` isn't installed or authenticated, the report is still printed and the skill offers to post it once the user sets up… …
Read the whole file at its exact version.
How to install
mdr add eagerworks/skills/pr-review@sha256:02ef1eccd8fc3331The line at the top of this page pins the label v2.1.0, 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.
[](https://markdownregistry.com/a/art_tu7n343sdtbe4e6d)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Aug 21, 2026 and Sep 12, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.1.0 latest | 2026-09-12 | 6a65db8 | 9,016 B | A | view · diff |
| v1.0.0 | 2026-09-01 | 1cc32b5 | 9,016 B | A | view · diff |
| v1.0.0 | 2026-09-01 | 34725e6 | 8,554 B | A | view · diff |
| v1.0.0 | 2026-08-28 | 056013f | 8,195 B | A | view · diff |
| v1.0.0 | 2026-08-28 | bb12a15 | 7,571 B | A | view · diff |
| git:20260821.2a2da0f | 2026-08-21 | 2a2da0f | 8,079 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9016 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 prompt-injection phrasing
- 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
Source
eagerworks/skills · 15 stars · license MIT · pushed 2026-09-12 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_tu7n343sdtbe4e6d GET https://markdownregistry.com/api/v1/resolve?ref=eagerworks/skills/pr-review GET https://markdownregistry.com/api/v1/blob/02ef1eccd8fc3331f3049bfb64157780367cb5faedef5c5c9e7a5357fe61998c
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 eagerworks/skills
Every file in eagerworks/skills