Megatron-LM Base Image Bump
NVIDIA/Megatron-LM
Moves Megatron-LM CI to a newer NVIDIA PyTorch base image, updating both the GitHub and GitLab pins together and handling the CI follow-up.
Route code and dependency changes to relevant review dimensions based on affected files and folders.
Install Expert Reviewing
$ npx skills add microsoft/vstest --skill expert-reviewing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install microsoft/vstest expert-reviewing --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/microsoft/vstest.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/expert-review .claude/skills/expert-reviewing && rm -rf skills-srcUse ~/.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/
Install the "expert-reviewing" agent skill from https://github.com/microsoft/vstest/tree/main/.github/skills/expert-review into .claude/skills/expert-reviewing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-reviewing", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/microsoft/vstest/tree/main/.github/skills/expert-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add microsoft/vstest --skill expert-reviewing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install microsoft/vstest expert-reviewing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/vstest.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/expert-review .agents/skills/expert-reviewing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "expert-reviewing" agent skill from https://github.com/microsoft/vstest/tree/main/.github/skills/expert-review into .agents/skills/expert-reviewing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-reviewing", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add microsoft/vstest --skill expert-reviewing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install microsoft/vstest expert-reviewing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/vstest.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/expert-review .cursor/skills/expert-reviewing && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "expert-reviewing" agent skill from https://github.com/microsoft/vstest/tree/main/.github/skills/expert-review into .cursor/skills/expert-reviewing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-reviewing", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/microsoft/vstest.git --path .github/skills/expert-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add microsoft/vstest --skill expert-reviewing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install microsoft/vstest expert-reviewing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/vstest.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/expert-review .gemini/skills/expert-reviewing && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "expert-reviewing" agent skill from https://github.com/microsoft/vstest/tree/main/.github/skills/expert-review into .gemini/skills/expert-reviewing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-reviewing", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install microsoft/vstest expert-reviewingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add microsoft/vstest --skill expert-reviewing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/microsoft/vstest.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/expert-review .github/skills/expert-reviewing && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "expert-reviewing" agent skill from https://github.com/microsoft/vstest/tree/main/.github/skills/expert-review into .github/skills/expert-reviewing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-reviewing", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add microsoft/vstest --skill expert-reviewing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install microsoft/vstest expert-reviewing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/vstest.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/expert-review .opencode/skills/expert-reviewing && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "expert-reviewing" agent skill from https://github.com/microsoft/vstest/tree/main/.github/skills/expert-review into .opencode/skills/expert-reviewing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-reviewing", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
expert-reviewing- GitHub stars
- 969
- Token cost
- ~2k tokens
- SKILL.md length
- 753 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Route code and dependency changes to relevant review dimensions based on affected files and folders.
- Works in 4 steps: Agent loads this skill and identifies… → This skill's routing table maps folders… → Agent activates the matched dimensions… → …
- Including Dependabot updates
- SKILL.md covers Folder → Dimension Routing Table, Quick Reference: Dimension…, Common Review Scenarios and Integration with…
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Expert Reviewing is an agent skill from microsoft/vstest, published by the product's own GitHub organization. Route code and dependency changes to relevant review dimensions based on affected files and folders. Use when reviewing PRs, including Dependabot updates, GitHub Actions and generated workflow changes, or specific vstest subsystems.
Its SKILL.md is about 2k 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 DevOps & Cloud, covering Dependency management and CI/CD. It works with GitHub Actions. The repository describes itself as: Visual Studio Test Platform is the runner and engine that powers test explorer and vstest.console. The licence is MIT.
When your agent uses it
- Including Dependabot updates
- GitHub Actions and generated workflow changes
- Specific vstest subsystems
Example prompts
- “/expert-reviewing”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Agent loads this skill and identifies changed files/folders in the PR. Bot authorship, generated files, and absence of C# changes are not…
- This skill's routing table maps folders to applicable dimensions
- Agent activates the matched dimensions and applies their CHECK items
- Agent produces findings limited to activated dimensions only
What it can do on your machine
Read from SKILL.md and the folder at commit 05cd781. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Expert Reviewing loads about 2k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 753 words of instructions outside code blocks.
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 microsoft/vstest at commit 05cd781, republished under its MIT licence (© microsoft). 753 words, ~1,983 tokens.
Download SKILL.mdSave it as
.claude/skills/expert-reviewing/SKILL.md (or your agent's skills folder).- name
- expert-reviewing
- description
- Route code and dependency changes to relevant review dimensions based on affected files and folders. Use when reviewing PRs, including Dependabot updates, GitHub Actions and generated workflow changes, or specific vstest subsystems.
Expert Review Routing
This skill maps changed folders to review dimensions, enabling focused expert reviews of vstest PRs.
Folder → Dimension Routing Table
| Folder | Primary Dimensions |
|---|---|
.github/workflows/ (including .md, shared sources, and .lock.yml) | Build Script & Infrastructure Hygiene, Dependency & Package Integrity |
.github/aw/, .github/dependabot.yml | Build Script & Infrastructure Hygiene, Dependency & Package Integrity |
eng/ | Build Script & Infrastructure Hygiene, Dependency & Package Integrity, Source Build & Cross-Platform Compliance |
src/Microsoft.TestPlatform.CrossPlatEngine/ | Parallel Execution & Scheduling Safety, Error Reporting & Diagnostic Clarity, Process Architecture & Host Resolution |
src/vstest.console/ | RunSettings Validation & Inference, Process Architecture & Host Resolution, Environment Variable & Feature Flag Contracts |
test/Microsoft.TestPlatform.Acceptance.IntegrationTests/ | Acceptance Test Coverage Design, Cross-TFM & Framework Resolution, Parallel Execution & Scheduling Safety |
src/Microsoft.TestPlatform.Extensions.BlameDataCollector/ | Crash & Hang Dump Reliability, Error Reporting & Diagnostic Clarity, Environment Variable & Feature Flag Contracts |
src/testhost/ | Testhost Assembly Loading & Resolution, Cross-TFM & Framework Resolution, Process Architecture & Host Resolution |
src/Microsoft.TestPlatform.CommunicationUtilities/ | IPC Transport & Protocol Stability, Error Reporting & Diagnostic Clarity, Dependency & Package Integrity |
src/Microsoft.TestPlatform.ObjectModel/ | Public API Surface Protection, Backward Compatibility & Rollback Safety, Cross-TFM & Framework Resolution |
src/package/ | Dependency & Package Integrity, Build Script & Infrastructure Hygiene, Cross-TFM & Framework Resolution |
src/Microsoft.TestPlatform.Common/ | Backward Compatibility & Rollback Safety, Error Reporting & Diagnostic Clarity, Null Safety & Boundary Validation |
src/Microsoft.TestPlatform.VsTestConsole.TranslationLayer/ | IPC Transport & Protocol Stability, Error Reporting & Diagnostic Clarity, Backward Compatibility & Rollback Safety |
src/Microsoft.TestPlatform.Client/ | IPC Transport & Protocol Stability, Backward Compatibility & Rollback Safety, Public API Surface Protection |
src/datacollector/ | Crash & Hang Dump Reliability, Dependency & Package Integrity, Error Reporting & Diagnostic Clarity |
src/Microsoft.TestPlatform.CoreUtilities/ | Process Architecture & Host Resolution, Environment Variable & Feature Flag Contracts, Error Reporting & Diagnostic Clarity |
src/Microsoft.TestPlatform.TestHostProvider/ | Process Architecture & Host Resolution, Environment Variable & Feature Flag Contracts, Testhost Assembly Loading & Resolution |
Quick Reference: Dimension Summaries
| Dimension | Focus |
|---|---|
| Dependency & Package Integrity | Version conflicts, transitive deps, package content correctness |
| Cross-TFM & Framework Resolution | Multi-TFM builds, binding redirects, framework-specific behavior |
| Process Architecture & Host Resolution | x86/x64/ARM64 selection, DOTNET_ROOT propagation, muxer resolution |
| Parallel Execution & Scheduling Safety | Race conditions, lock scopes, worker slot assignment, cancellation |
| IPC Transport & Protocol Stability | Wire compatibility, connection timeouts, protocol versioning |
| Crash & Hang Dump Reliability | Dump capture under compound failures, detach timing, file validity |
| Error Reporting & Diagnostic Clarity | Actionable messages, trace formatting, exception propagation |
| Environment Variable & Feature Flag Contracts | Naming conventions, propagation, stable contract semantics |
| RunSettings Validation & Inference | Defensive XML parsing, defaults, source precedence |
| Backward Compatibility & Rollback Safety | Disable flags, version-guarded behavior, migration paths |
| Public API Surface Protection | Unintentional exposure, PublicAPI.txt management, interface evolution |
| Acceptance Test Coverage Design | Focused matrices, OS coverage, measurement-backed claims |
| Testhost Assembly Loading & Resolution | deps.json alignment, RID assets, TypeLoadException handling |
| Build Script & Infrastructure Hygiene | Exit codes, cross-platform scripts, source-build compatibility |
| Null Safety & Boundary Validation | Boundary checks, nullable annotations, defensive parsing |
| Source Build & Cross-Platform Compliance | Source-build mode, Linux/macOS paths, shell compatibility |
Show full SKILL.md (345 more words)Show less
Common Review Scenarios
PR touches src/Microsoft.TestPlatform.CrossPlatEngine/
→ Activate: Parallel Execution & Scheduling Safety, Error Reporting & Diagnostic Clarity, Process Architecture & Host Resolution
PR modifies eng/ scripts or build infrastructure
→ Activate: Build Script & Infrastructure Hygiene, Dependency & Package Integrity, Source Build & Cross-Platform Compliance
PR changes ObjectModel public API
→ Activate: Public API Surface Protection, Backward Compatibility & Rollback Safety, Cross-TFM & Framework Resolution
PR updates CommunicationUtilities or TranslationLayer
→ Activate: IPC Transport & Protocol Stability, Backward Compatibility & Rollback Safety, Error Reporting & Diagnostic Clarity
PR modifies blame/datacollector components → Activate: Crash & Hang Dump Reliability, Environment Variable & Feature Flag Contracts, Error Reporting & Diagnostic Clarity
PR adds or bumps package dependencies → Activate: Dependency & Package Integrity, Cross-TFM & Framework Resolution, Backward Compatibility & Rollback Safety
Dependabot PR updates GitHub Actions, or a PR recompiles workflow .lock.yml files
→ Activate: Build Script & Infrastructure Hygiene, Dependency & Package Integrity. Apply the canonical Generated workflow action versions checks, even when the .md sources are not in the diff.
PR changes only workflow .md sources or shared imports
→ Activate: Build Script & Infrastructure Hygiene, Dependency & Package Integrity. These are executable configuration, not documentation-only changes.
PR touches testhost or TestHostProvider → Activate: Testhost Assembly Loading & Resolution, Process Architecture & Host Resolution, Cross-TFM & Framework Resolution
PR modifies RunSettings handling in vstest.console → Activate: RunSettings Validation & Inference, Environment Variable & Feature Flag Contracts, Backward Compatibility & Rollback Safety
Integration with @expert-reviewer
This skill provides the routing configuration that tells the expert-reviewer agent which dimensions to activate for a given PR. The agent owns the full CHECK methodology and review logic.
Invocation: Reference @expert-reviewer in a PR comment or use the pr-expert-reviewer workflow.
How routing works:
- Agent loads this skill and identifies changed files/folders in the PR. Bot authorship, generated files, and absence of C# changes are not scope exclusions.
- This skill's routing table maps folders to applicable dimensions
- Agent activates the matched dimensions and applies their CHECK items
- Agent produces findings limited to activated dimensions only
Scope boundaries:
- This skill: folder-to-dimension mapping, dimension summaries, scenario examples
- The agent: full CHECK items, severity classification, comment formatting, review decisions
vstest-build-testskill: build/test commands (not review logic)trx-analysisskill: test result file parsing (not code review)
© microsoft, 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/expert-review of microsoft/vstest.
Open the folder on GitHubat commit 05cd781
Compare with similar skills
Expert Reviewing 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Expert Reviewing this skillmicrosoft/vstest | 969 | — | ~2k | Automated safety check: Pass | MIT | |
| Megatron-LM Base Image BumpNVIDIA/Megatron-LM | 18k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Kubelb Dependency Updateskubermatic/kubelb | 148 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Bump Sentry Dependencygetsentry/sentry | 46k | — | ~815 | Automated safety check: Pass | Custom licence | |
| Running GitHub Actions Efficientlykajisho5/ffmpeg-skill | 1.9k | — | ~3.3k | Automated safety check: Notes | MIT | |
| Depot GitHub RunnersPostHog/posthog | 40k | — | ~2.8k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Kubelb Dependency Updates
kubermatic/kubelb
Sweep and update every dependency surface in the kubelb repo (go.mod, Makefile tool versions, prow images, GitHub Actions, hack/ci pins, addon Helm charts, pinned container images) and split the…
- Official
Bump Sentry Dependency
getsentry/sentry
Bumps an existing Python dependency in getsentry/sentry through the repository's self-serve GitHub Actions workflow.
Running GitHub Actions Efficiently
kajisho5/ffmpeg-skill
Cut GitHub Actions minutes and wall-clock time without losing coverage — the OS billing multiplier (macOS 10x / Windows 2x / Linux 1x), trigger hygiene that stops push+pullrequest double-firing…
- Official
Depot GitHub Runners
PostHog/posthog
Configures Depot-managed GitHub Actions runners as a drop-in replacement for GitHub-hosted runners.
Sicurezza GitHub
ccplugins/awesome-claude-code-plugins
Aggiunge alle repository GitHub dei siti workflow di sicurezza automatici - scansione dipendenze vulnerabili, ricerca di segreti/chiavi nel codice, analisi statica CodeQL e Dependabot.
More from microsoft/vstest
- Official
Trx Analysis
microsoft/vstest
Parse and analyze Visual Studio TRX test result files. An agent skill from microsoft/vstest.
- Official
Validate Skills
microsoft/vstest
Validate that commands documented in skill files actually work.
- Official
Vstest Build Test
microsoft/vstest
Build, test, and validate changes in the vstest repository. An agent skill from microsoft/vstest.
- Official
Creating Skills
microsoft/vstest
Create custom agent capabilities when discovering novel tools, receiving task-agnostic tips from reviewers, or after researching specialized workflows not covered in existing instructions.
Related
Works with
Categories
Questions about Expert Reviewing
What does Expert Reviewing do?
Route code and dependency changes to relevant review dimensions based on affected files and folders. Expert Reviewing is an agent skill from microsoft/vstest, published by the product's own GitHub organization. Route code and dependency changes to relevant review dimensions based on affected files and folders.
When should I use Expert Reviewing?
Expert Reviewing fits situations like: including Dependabot updates; GitHub Actions and generated workflow changes; specific vstest subsystems.
How do I install Expert Reviewing in Claude Code?
Run `npx skills add microsoft/vstest --skill expert-reviewing -a claude-code`. Or copy the skill folder (.github/skills/expert-review in microsoft/vstest) into .claude/skills/expert-reviewing in your project. Claude Code loads it when a task matches its description.
How do I install Expert Reviewing in Codex?
Run `npx skills add microsoft/vstest --skill expert-reviewing -a codex`. Or copy the skill folder (.github/skills/expert-review in microsoft/vstest) into .agents/skills/expert-reviewing in your project. Codex loads it when a task matches its description.
Can I use Expert Reviewing 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 microsoft/vstest --skill expert-reviewing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/expert-reviewing, .gemini/skills/expert-reviewing, .github/skills/expert-reviewing and .opencode/skills/expert-reviewing in your project.
What does Expert Reviewing need to run?
SKILL.md names no scripts, command-line tools or credentials: Expert Reviewing is instructions for the agent only.
Does Expert Reviewing 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 Expert Reviewing 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 Expert Reviewing use?
Expert Reviewing 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 Expert Reviewing use?
About 2k tokens (SKILL.md is roughly 7.9k 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 Expert Reviewing?
Skills that share tags, products or a category with Expert Reviewing: Megatron-LM Base Image Bump (NVIDIA/Megatron-LM, 18k stars), Kubelb Dependency Updates (kubermatic/kubelb, 148 stars), Bump Sentry Dependency (getsentry/sentry, 46k stars) and Running GitHub Actions Efficiently (kajisho5/ffmpeg-skill, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Expert Reviewing?
microsoft (a GitHub organization, an official publisher) maintains it in microsoft/vstest, which has 969 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 8, 2026.
Source: microsoft/vstest on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.