New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Verify PR

by Azure in Azure/LogicAppsUX

Verify PR readiness before requesting review or merging. An agent skill from Azure/LogicAppsUX.

OfficialMITAuto-check passedTesting & QA

Install Verify PR

skills CLI
$ npx skills add Azure/LogicAppsUX --skill verify-pr -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Azure/LogicAppsUX verify-pr --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Azure/LogicAppsUX.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/verify-pr .claude/skills/verify-pr && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
verify-pr
GitHub stars
114
Token cost
~2.4k tokens
SKILL.md length
998 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Verify PR readiness before requesting review or merging. An agent skill from Azure/LogicAppsUX.

  • Works in 7 steps: Title Format → Description Template → Risk Label → …
  • Tasks that involve Test coverage
  • SKILL.md covers Repository Context, What This Skill Checks, Cross-References with Existing… and How to Invoke, plus 2 more sections
  • Calls pnpm

What it does

Verify PR is an agent skill from Azure/LogicAppsUX, published by the product's own GitHub organization. Verify PR readiness before requesting review or merging. Checks title format, description compliance with the team template, risk label alignment, review thread resolution, CI status, coverage report, and screenshot requirements. Reasons about each review comment to help the engineer understand what's being asked and decide how to respond — rather than auto-fixing blindly.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Test coverage. It works with Microsoft Azure, React, Node.js and pnpm. The licence is MIT.

When your agent uses it

  • Tasks that involve Test coverage

Example prompts

  • “/verify-pr”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Title Format
  2. Description Template
  3. Risk Label
  4. Review Threads
  5. CI Status
  6. Coverage Report
  7. Merge Readiness

What it can do on your machine

Read from SKILL.md and the folder at commit 04df5b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Verify PR loads about 2.4k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 998 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Azure/LogicAppsUX at commit 04df5b5, republished under its MIT licence (© Azure). 998 words, ~2,371 tokens.

Download SKILL.mdSave it as .claude/skills/verify-pr/SKILL.md (or your agent's skills folder).
name
verify-pr
description
Verify PR readiness before requesting review or merging. Checks title format, description compliance with the team template, risk label alignment, review thread resolution, CI status, coverage report, and screenshot requirements. Reasons about each review comment to help the engineer understand what's being asked and decide how to respond — rather than auto-fixing blindly.

Verify PR Skill

Use this skill when an engineer asks to "check my PR", "is this ready for review", "verify PR", or before requesting reviewers. It provides a structured assessment that the engineer acts on.

Repository Context

LogicAppsUX is a pnpm + turbo monorepo with this structure:

  • libs/ — shared libraries (designer, designer-ui, data-mapper-v2, logic-apps-shared, etc.)
  • apps/ — applications (vs-code-designer, vs-code-react, Standalone, iframe-app)
  • e2e/ — end-to-end tests
  • .squad/ — agent squad configuration, playbooks, knowledge

Build and test commands use turbo:

  • pnpm turbo run build — full build
  • pnpm turbo run test:lib — unit tests
  • pnpm turbo run lint — linting

What This Skill Checks

1. Title Format

The PR title must start with one of: feat:, fix:, chore:, refactor:, perf:, docs:, test: — with an optional scope in parentheses.

Good: feat(designer): add conditional action branching Good: fix(data-mapper): resolve schema loading for nested arrays Good: chore(ci): update pnpm lock workflow Good: fix: resolve token picker overflow in dark theme Bad: Update API endpoint (too vague, no prefix) Bad: [WIP] working on stuff (no prefix, not descriptive)

2. Description Template

The PR body must include these sections with real content (not just placeholders):

SectionRequired?What to check
Commit TypeYesAt least one [x] selected (feat, fix, refactor, perf, docs, test, chore)
Risk LevelYesExactly one [x] selected. Must match risk:* label.
What & WhyYes>50 chars of actual content explaining the change
Impact of ChangeYesAt least one of Users/Developers/System has content
Test PlanFor code PRsAt least one testing approach selected. If unit/e2e checked, verify tests exist in the diff.
Screenshots/VideosFor UI changesRequired when PR changes libs/designer-ui/src/ or libs/designer/src/ (non-test files)
ContributorsOptionalNudge if blank — remind to credit PMs/designers
3. Risk Label
  • PR must have exactly one label matching risk:low, risk:medium, or risk:high
  • The label must match what's selected in the Risk Level section
  • Estimate what the risk SHOULD be based on the diff:
    • High: security/auth changes, breaking API changes, credential handling, libs/logic-apps-shared core utilities that many packages depend on
    • Medium: libs/logic-apps-shared (shared across monorepo), apps/vs-code-designer (extension distribution), state management changes, new dependencies, CI/infra, multi-package changes
    • Low: docs, tests only, single-component UI fixes, config changes, generated files, libs/designer-ui cosmetic changes
  • If declared risk is lower than estimated, flag it clearly
4. Review Threads

For each unresolved review thread:

  1. Read the comment carefully — understand what the reviewer is actually asking
  2. Classify it:
    • Blocking bug — reviewer found a real issue that must be fixed
    • Design question — reviewer wants clarification on approach
    • Suggestion — reviewer proposes an improvement, not required
    • Nit — style/naming preference, non-blocking
    • Outdated — the code has changed since the comment was made
  3. Explain to the engineer what the reviewer wants and why
  4. Suggest a response — but let the engineer decide:
    • For bugs: "This needs a fix — here's what to change: ..."
    • For questions: "The reviewer is asking about X. You could respond with: ..."
    • For suggestions: "This is optional. The tradeoff is ... You can accept or explain why not."
    • For outdated: "This was about old code. Verify it's fixed, then resolve."

Do NOT auto-fix or auto-resolve. The engineer should understand each comment and make an informed decision.

5. CI Status

Check all CI check runs:

  • List any failures with the job name and a brief explanation of what likely failed
  • For passing checks, just confirm "all green"
  • If PR desc check failed, explain which sections need updating
  • Cross-reference with ci-sentinel: If CI failures are complex or flaky, recommend invoking @ci-sentinel for deeper diagnosis with log analysis
Show full SKILL.md (424 more words)Show less
6. Coverage Report
  • Check if the pr-coverage.yml workflow has posted its comment (look for the coverage report comment)
  • If coverage decreased, flag it and identify which changed files lack test coverage
  • If coverage report is not yet posted, note it as pending
  • Do NOT duplicate what pr-coverage already reports — just reference it as part of readiness
7. Merge Readiness

After checking everything, give a clear verdict:

## PR Readiness: [READY / NOT READY / NEEDS ATTENTION]

Title: fix(designer): resolve token picker overflow
Description: all sections filled
Risk: medium (declared) matches medium (estimated — touches libs/designer/)
Label: risk:medium present
CI: 14/14 checks green
Coverage: pr-coverage reports 87% on changed files (above threshold)
Review threads: 3 unresolved (1 blocking, 1 question, 1 nit)
Screenshots: provided (before/after token picker)

### Unresolved Threads

#### Thread 1 — Blocking (libs/designer-ui/src/tokenPicker/index.tsx:147)
**Reviewer says:** "This overflow fix might clip the dropdown in narrow panels. Have you tested in the VS Code webview?"
**What this means:** The reviewer is concerned about a different host environment where the panel may be narrower.
**Suggested action:** Test in the VS Code extension (Standalone host may be wider). If confirmed working, reply with a screenshot from VS Code.

#### Thread 2 — Question (libs/designer/src/core/state/tokens/tokenSlice.ts:22)
**Reviewer says:** "Why not use the existing selectTokensByNodeId selector?"
**What this means:** The reviewer wants to understand the design choice.
**Suggested response:** "selectTokensByNodeId returns all token types. This PR needs only expression tokens for the overflow fix, so a new selector avoids re-renders from unrelated token updates."

#### Thread 3 — Nit (libs/designer-ui/src/tokenPicker/styles.ts:88)
**Reviewer says:** "Consider using tokens.spacingHorizontalM instead of 12px"
**What this means:** Minor style preference to use Fluent design tokens instead of hardcoded pixels.
**Suggested action:** Accept — using tokens is the project convention. Or respond "Kept as px because this needs to match a fixed-size icon."

Cross-References with Existing Agents

  • ci-sentinel: For complex CI failures, recommend the engineer invoke ci-sentinel for log-level diagnosis
  • customer-repro-tester: For bug-fix PRs, check if there's a linked customer issue. If so, recommend asking customer-repro-tester to validate the fix against the original repro steps
  • pr-orchestrator: This skill feeds INTO pr-orchestrator's lifecycle — verify-pr checks readiness, pr-orchestrator manages the full PR flow
  • release-scribe: If the PR body needs rewriting, reference release-scribe's conventions

How to Invoke

Engineers can use this skill in Copilot Chat:

  • "Load verify-pr and check my PR"
  • "Is PR #4521 ready for review?"
  • "What do I need to fix before merging?"

The skill works with the current branch's PR automatically, or with a specific PR number.

Continuous Monitoring

Once invoked, the skill should keep monitoring until the PR is fully green:

  1. Run the initial verification (title, body, labels, threads, CI, coverage)
  2. Report findings to the engineer
  3. After the engineer makes changes (commits, edits description, responds to threads):
    • Re-check what's changed
    • Report updated status: "2 of 3 issues resolved. Remaining: ..."
  4. Repeat until ALL of these are true:
    • Title matches prefix format
    • Description passes all template sections
    • Risk label present and matches body + estimated risk
    • All review threads resolved (or classified as non-blocking with response)
    • CI checks all green
    • pr-coverage report posted and above threshold
    • Screenshots present (if UI changes detected in libs/designer-ui or libs/designer)
  5. Then report: "PR is ready for review/merge. All checks pass."

The monitoring loop should feel like a helpful co-pilot sitting next to the engineer, not a nagging bot. After each check:

  • Only report what CHANGED since last check
  • Celebrate progress ("Risk level fixed — 2 items remaining")
  • If the engineer asks to stop monitoring: stop immediately

Important

  • Never auto-fix code — explain what needs to change and let the engineer decide
  • Never auto-resolve threads — help the engineer understand what to respond
  • Always explain WHY a comment was made, not just WHAT to do
  • Distinguish blocking from non-blocking — engineers should know what MUST be fixed vs what's optional
  • Check the diff — verify review comments are still relevant to the current code
  • Respect pr-coverage — don't duplicate its analysis; reference its comment as authoritative for coverage data

© Azure, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/verify-pr of Azure/LogicAppsUX.

Open the folder on GitHubat commit 04df5b5

Compare with similar skills

Verify PR next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Verify PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Verify PR this skillAzure/LogicAppsUX114—~2.4kAutomated safety check: PassMIT
Senior QAnicepkg/auto-company1923 repos~1.1kAutomated safety check: NotesNone
Gh Bot Commentjetstreamapp/jetstream125—~616Automated safety check: PassCustom licence
DeerFlow Smoke Testbytedance/deer-flow83k—~2.5kAutomated safety check: NotesMIT
Desktop Dual Repo TestEynzof/Hermes-CN-Desktop1.7k—~1.8kAutomated safety check: PassCustom licence
Verdaccio Change Testing Selectorverdaccio/verdaccio18k—~1.6kAutomated safety check: WarnMIT

Similar skills

  • Senior QA

    nicepkg/auto-company

    Comprehensive QA and testing skill for quality assurance, test automation, and testing strategies for ReactJS, NextJS, NodeJS applications.

    192 GitHub starsUsed in 3 repos~1.1k tokens
    Testing & QAAuto-check: notes

  • Gh Bot Comment

    jetstreamapp/jetstream

    Post GitHub PR/issue comments, reviews, and review replies as the Jetstream bot account instead of the user's personal account.

    125 GitHub stars~616 tokensUpdated yesterday
    DevelopmentAuto-check passed

  • DeerFlow Smoke Test

    bytedance/deer-flow

    Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.

    83k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check: notes

  • Desktop Dual Repo Test

    Eynzof/Hermes-CN-Desktop

    A skill your agent uses when starting or verifying Hermes Agent CN Desktop with the latest Hermes-CN-Desktop and Hermes-CN-Core branches — dev smoke test (pnpm tauri:dev), packaged beta/release…

    1.7k GitHub stars~1.8k tokensUpdated 16 days ago
    Testing & QAAuto-check passed

  • Verdaccio Change Testing Selector

    verdaccio/verdaccio

    Figures out which rebuild and test suites actually cover a change in the verdaccio monorepo, instead of a scoped run that passes untested.

    18k GitHub stars~1.6k tokensUpdated today
    Testing & QAAuto-check: warnings

  • JS Package Testing

    Opentrons/opentrons

    Vite demo and Playwright + Applitools tests for packed @opentrons JS packages in js-package-testing/.

    521 GitHub stars~1.2k tokensUpdated today
    Testing & QAAuto-check: notes

Works with

Categories

Questions about Verify PR

What does Verify PR do?

Verify PR readiness before requesting review or merging. An agent skill from Azure/LogicAppsUX. Verify PR is an agent skill from Azure/LogicAppsUX, published by the product's own GitHub organization. Verify PR readiness before requesting review or merging.

When should I use Verify PR?

Verify PR fits situations like: tasks that involve Test coverage.

How do I install Verify PR in Claude Code?

Run `npx skills add Azure/LogicAppsUX --skill verify-pr -a claude-code`. Or copy the skill folder (.github/skills/verify-pr in Azure/LogicAppsUX) into .claude/skills/verify-pr in your project. Claude Code loads it when a task matches its description.

How do I install Verify PR in Codex?

Run `npx skills add Azure/LogicAppsUX --skill verify-pr -a codex`. Or copy the skill folder (.github/skills/verify-pr in Azure/LogicAppsUX) into .agents/skills/verify-pr in your project. Codex loads it when a task matches its description.

Can I use Verify PR in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Azure/LogicAppsUX --skill verify-pr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verify-pr, .gemini/skills/verify-pr, .github/skills/verify-pr and .opencode/skills/verify-pr in your project.

What does Verify PR need to run?

Going by SKILL.md and its folder, Verify PR needs the command-line tools its instructions call (pnpm).

Does Verify PR access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Verify PR safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Verify PR use?

Verify PR is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Verify PR use?

About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Verify PR?

Skills that share tags, products or a category with Verify PR: Senior QA (nicepkg/auto-company, 192 stars), Gh Bot Comment (jetstreamapp/jetstream, 125 stars), DeerFlow Smoke Test (bytedance/deer-flow, 83k stars) and Desktop Dual Repo Test (Eynzof/Hermes-CN-Desktop, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verify PR?

Azure (a GitHub organization, an official publisher) maintains it in Azure/LogicAppsUX, which has 114 GitHub stars. The repository was last updated on October 7, 2026.

Source: Azure/LogicAppsUX on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.