SkillA skill gives Relay a specialist method it can reuse on your work.Product and engineeringCommunity
Low riskSecurity review passed

code-review-and-quality

Conducts multi-axis code review.

How it works

What code-review-and-quality does

Use it when

Before merging any change.

Reviewing code written by yourself, another agent, or a human.

You need to assess code quality across multiple dimensions before it enters the main branch.

Inputs and results

What goes in, what comes back

  1. You give

    A short brief describing what you need

    Add a specialist method to the work.

  2. You get

    A finished result to review

    The method guides the work with your files and context.

  3. You check

    The sources and open questions

    Review the output against your brief.

Questions and answers

Questions about code-review-and-quality

Updated Aug 27, 2026.

What does code-review-and-quality do?

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

Who is code-review-and-quality for?

It is designed for teams that want to hand off recurring work and review the result before it is used.

What do I need to use it?

Nothing extra is needed. Sign in to Relay to run it with your own files and context.

What does code-review-and-quality produce?

A finished result to review. Results come back with their sources and any open questions for you to check before anything is used.

How much does code-review-and-quality cost?

It is free to use. Paid model usage, if any, is shown before a run.

Can an AI agent use it?

Yes. Agents can read its public definition through the Relay API and run it with a person’s authorization. See the For Agents page for how to connect.

Details

Trust, access and technical details

Trust and access

Visibility
Public: anyone can view
Status
Published and maintained
Pricing
Free
Low riskSecurity review passedBehavior not evaluated
Reviewed version
cmtas2r8o0031…
Reviewed
Aug 27, 2026
Static signals
1 signal
Source provenance
Commit pinned

Security review is a static package assessment, not a guarantee of safety or a behavioral qualification.

Use it from code or an agent

Read the public definition, then check cost and inputs with a preflight before a run.

Open definition

POST /api/v1/runs/preflight

How agents connect to Relay →

Tags and source

Repo
addyosmani/agent-skills
License
MIT

Connections

Where code-review-and-quality fits

Similar skills5

Skill · Product and engineering

Accessibility Qa

Plan and report accessibility QA for a web or app experience against WCAG 2.2 level AA. Defines scope and a page and flow sample, combines automated scans with manual keyboard, screen reader, zoom and reflow, contrast, semantics, and form-error testing, computes contrast ratios, logs each issue with the success criterion, affected users, severity, and a fix direction, and ends with retest criteria. Use when someone asks for accessibility testing, an accessibility audit plan or report, keyboard or screen reader checks, contrast checks, or WCAG review of a page or flow. Do not use for the overall test plan (use test-plan), the release verdict (use release-regression-report), visual design critique (use design-audit), or posting issue text (use jira-evidence-uploader).Free
Skill · Product and engineering

diagnosing-bugs

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.Free
Skill · Product and engineering

grilling

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.FreeCommunity
Skill · Product and engineering

Jira Evidence Uploader

Package QA findings into Jira-ready drafts without posting anything. Normalizes each finding to one defect, decides new issue versus comment versus link, writes the summary, preconditions, numbered reproduction steps, expected and actual results, severity proposal, and environment block, selects and names screenshots, recordings, and log excerpts, runs a redaction check for personal data, builds an attachment manifest with hashes, and drafts new-issue, evidence, and retest comments. Use when someone asks to write up a bug for Jira, turn QA findings into tickets, package screenshots and reproduction steps, or draft evidence comments. Do not use for writing epics or stories (use jira-epic-writer), the release verdict (use release-regression-report), test planning (use test-plan), or running the tests (use playwright-browser-runner).Free
Skill · Product and engineering

Playwright Browser Runner

Guide browser test execution with Playwright or a similar runner as a run plan the user carries out. Covers pre-flight checks, run modes (smoke, targeted, full, cross-browser, repeat for flake detection), command templates, evidence settings (trace, screenshot, video), a failure triage decision tree that separates product bugs from locator, data, environment, and flaky causes, repeat sizing, quarantine rules, and a stable run record for reporting. Use when someone asks how to run browser tests, capture evidence, triage Playwright failures, find flaky tests, or report a browser test run reliably. Do not use for the overall test strategy (use test-plan), the release verdict (use release-regression-report), accessibility checks (use accessibility-qa), or writing issue text (use jira-evidence-uploader).Free

Have a task this would help with?

Describe it. Relay plans the work, picks the right playbook and shows the cost before anything runs.

Loading request box