code-review
/code-review
Reviews a pull request against this repository's blocking criteria and reports only findings that name a failure mode. Use when reviewing a change, a pull request or a diff.
- Author
- ralbac ↗
- Repository
- copilot-customization-blueprint ↗
- Licence
- MIT
- Last repository change
- 08.11.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 08.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Reviews a pull request against this repository's blocking criteria and reports only findings that name a failure mode. Use when reviewing a change, a pull request or a diff.
Arguments
/code-review [PR number, branch, or empty for the working tree]
Original author description
Reviews a pull request against this repository's blocking criteria and reports only findings that name a failure mode. Use when reviewing a change, a pull request or a diff.
How it works
- Process
- Report format
- Rules
SKILL.md preview
--- name: code-review description: Reviews a pull request against this repository's blocking criteria and reports only findings that name a failure mode. Use when reviewing a change, a pull request or a diff. license: MIT argument-hint: [PR number, branch, or empty for the working tree] context: fork --- # Repository code review The directory is named `code-review` on purpose. Copilot code review on GitHub reads skills from `.github/skills/`, and a review-focused directory name makes it far more likely that the reviewer loads this skill rather than a domain skill that happens to be adjacent. `context: fork` runs the skill in its own subagent context, so reading many files during a review does not consume the main conversation's context. Only the report comes back. ## Process 1. Establish intent before reading the diff: the PR description, the linked issue, or the commit message. A review without a stated goal drifts into style commentary. 2. Read the diff. Then read the code around each hunk — enough to know what the change affects. Judging a hunk in isolation produces findings about formatting and misses findings about behaviour. 3. Work through [the blocking checklist](./blocking-checklist.md) in order. 4. For each candidate finding, try to refute it. Ask: what would have to be true for this to be fine? Check that. Most candidate findings die here, and the ones that survive are worth the reader's attention. 5. Report. ## Report format Group by severity: **Blocker**, **Should fix**, **Consider**. Every finding contains: - `path:line` - The failure mode: what goes wrong, for whom, under which condition. - The smallest change that fixes it. A finding without a failure mode is not a finding. If you cannot complete that sentence, drop it or downgrade it to a question you actually need answered. ## Rules - Do not restate the diff. The author wrote it and has read it more recently than you. - Do not open with praise and do not close with a summary of findings already listed. - Do not request a change you would not make yourself in the same review. - Silence is a valid review of a sound change: one line saying so, then stop. - If the change touches a contract other code consumes, say who consumes it. That is the single most valuable thing a reviewer can add.
Files in this package (2)
- SKILL.md 2 KB
- blocking-checklist.md 2 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · ralbac/copilot-customization-blueprint | 90 | MIT |
| microsoft/aspire | 100 | MIT |
| kdlbs/kandev | 100 | AGPL-3.0 |
| dotnet/runtime | 100 | MIT |
| drosam/agents | 100 | MIT |
| ggml-org/llama.cpp | 100 | MIT |
| ShamelesAbyss/Nyx | 100 | Apache-2.0 |
| dzhng/jevgrep | 100 | MIT |
| iuliandita/skills | 100 | MIT |
Database snapshot: 13.11.2026 · package version 151432c4435a (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90reviews
Review a pull request or code change for code health. Use when a user asks to "code review", "review this PR", or "review this change". - 100review-pr
Review a pull request for code quality and security issues. Use when the user wants to review a PR, check PR code changes, or audit a pull request. Triggers on: "review PR", "review pull request", "check this PR", "the `review-pr` skill". - 90review
Review a pull request or diff for this repository against otari's project standards. Use when asked to review a PR, inspect a diff, or prepare review feedback. - 90abap-code-review
Use when asked to review ABAP - a diff, a transport request or task, a pull request, a class / function module / program, or "check my ABAP before release". Collects the change and its goal, checks facts on the system, runs an independent reviewer pass, and reports findings… - 90review-a-pull-request
A careful code review of a change, a branch or a pull request: correctness, tests, security, readability, with findings ordered by how much they matter. Use when the owner asks you to review code, a diff, a branch or a PR. - 100dx-code-review
Use when asked to review a pull request or merge request, posting findings as inline comments on the request itself. Triggers on "review this PR", "review this merge request", "give me feedback on this PR", "post findings to PR", "add review comments to the pull request", or any…