Official agent skill

Run Al Tests

by microsoft in microsoft/AL

Runs a published AL test codeunit against the provisioned BCInsider sandbox through the public prerelease ALTool.

OfficialMITAuto-check passed

Install Run Al Tests

skills CLI
$ npx skills add microsoft/AL --skill run-al-tests -a claude-code

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

GitHub CLI
$ gh skill install microsoft/AL run-al-tests --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/microsoft/AL.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/run-al-tests .claude/skills/run-al-tests && 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
run-al-tests
GitHub stars
884
Token cost
~208 tokens
SKILL.md length
38 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Runs a published AL test codeunit against the provisioned BCInsider sandbox through the public prerelease ALTool.

  • Works in 5 steps: Invoke verify-prerelease-altool. → Publish the test app with publish-al-app. → Run structured tests → …
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Run Al Tests is an agent skill from microsoft/AL, published by the product's own GitHub organization. Runs a published AL test codeunit against the provisioned BCInsider sandbox through the public prerelease ALTool.

Its SKILL.md is about 210 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Home of the Dynamics 365 Business Central AL Language extension for Visual Studio Code. Used to track issues regarding the latest version of the AL compiler and developer tools… The licence is MIT.

Example prompts

  • “/run-al-tests”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Invoke verify-prerelease-altool.
  2. Publish the test app with publish-al-app.
  3. Run structured tests
  4. Add --testmethods only when specific procedures are requested.
  5. Preserve the JSON response and native exit code; report passed, failed, and skipped counts.

What it can do on your machine

Read from SKILL.md and the folder at commit 872adad. 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 (its code samples are powershell).

    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

Run Al Tests loads about 208 tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 38 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~208

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/AL at commit 872adad, republished under its MIT licence (© microsoft). 38 words, ~208 tokens.

Download SKILL.mdSave it as .claude/skills/run-al-tests/SKILL.md (or your agent's skills folder).
name
run-al-tests
description
Runs a published AL test codeunit against the provisioned BCInsider sandbox through the public prerelease ALTool.
argument-hint
<codeunit-id> [project-folder] [test-methods]
  1. Invoke verify-prerelease-altool.
  2. Publish the test app with publish-al-app.
  3. Run structured tests:
    powershell
    & $env:ALTOOL_PATH runtests $codeunitId `
        --project $projectPath `
        --server $env:BC_SERVER_URL `
        --serverinstance $env:BC_SERVER_INSTANCE `
        --port $env:BC_SERVER_PORT `
        --tenant $env:BC_TENANT `
        --authentication $env:BC_AUTHENTICATION `
        --environmenttype OnPrem
  4. Add --testmethods only when specific procedures are requested.
  5. Preserve the JSON response and native exit code; report passed, failed, and skipped counts.

© 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/run-al-tests of microsoft/AL.

Open the folder on GitHubat commit 872adad

Compare with similar skills

Run Al Tests 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.

Run Al Tests compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Run Al Tests this skillmicrosoft/AL884—~208Automated safety check: PassMIT
ESP32 CSI Node Provisioningruvnet/RuView97k—~579Automated safety check: PassMIT
Implementing Scim Provisioning With Oktamukul975/Anthropic-Cybersecurity-Skills34k—~2.3kAutomated safety check: PassApache-2.0
Implementing Just In Time Access Provisioningmukul975/Anthropic-Cybersecurity-Skills34k—~1.3kAutomated safety check: PassApache-2.0
Secondmate Provisioningkunchenguid/firstmate7.6k—~8.1kAutomated safety check: PassMIT
Cloud Provisioningelastic/agent-skills592—~5.4kAutomated safety check: PassApache-2.0

Similar skills

  • Builds, flashes and provisions an ESP32-S3 or C6 CSI node for RuView, with checksum-verified flashing, WiFi settings and boot-log evidence that CSI is flowing.

    97k GitHub stars~579 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Implementing Scim Provisioning With Okta

    mukul975/Anthropic-Cybersecurity-Skills

    Implement automated user lifecycle provisioning and deprovisioning using the SCIM 2.0 protocol with Okta as the identity provider.

    34k GitHub stars~2.3k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Implementing Just In Time Access Provisioning

    mukul975/Anthropic-Cybersecurity-Skills

    Implements Just-In-Time (JIT) access provisioning to eliminate standing privileges by granting temporary, time-bound access, covering approval workflows, automatic expiration/revocation, and PAM/IGA…

    34k GitHub stars~1.3k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Secondmate Provisioning

    kunchenguid/firstmate

    Agent-only reference for persistent secondmate setup and retirement.

    7.6k GitHub stars~8.1k tokensUpdated today
    Auto-check passed
  • Cloud Provisioning

    elastic/agent-skills

    Official

    Provision and operate Elastic Cloud infrastructure: create, connect to, update, and delete Serverless projects (Elasticsearch, Observability, Security); manage traffic filters (IP and AWS…

    592 GitHub stars~5.4k tokensUpdated 5 days ago
    Backend & APIsAuto-check passed
  • Official

    Generate a copy-paste Grafana data source provisioning file (YAML or Terraform) for any plugin from its standardized settings schema on the plugins CDN.

    278 GitHub stars~2.8k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

More from microsoft/AL

All 9 skills in this repo
  • Official

    Downloads exact Business Central symbol packages for a temporary AL reproduction project through the installed prerelease ALTool.

    884 GitHub stars~273 tokensUpdated 21 days ago
    Auto-check passed
  • Publish Al App

    microsoft/AL

    Official

    Publishes one compiled AL app to the provisioned BCInsider sandbox through the public prerelease ALTool.

    884 GitHub stars~221 tokensUpdated 21 days ago
    Auto-check passed
  • Official

    Runs CodeCop, PerTenantExtensionCop, UICop, or AppSourceCop against a temporary project through the public prerelease ALTool.

    884 GitHub stars~302 tokensUpdated 21 days ago
    Auto-check passed
  • Run Al MCP Tool

    microsoft/AL

    Official

    Invokes one safe AL MCP tooling operation through the workflow-installed prerelease ALTool for independent reproduction of MCP and editor-tooling issues.

    884 GitHub stars~310 tokensUpdated 21 days ago
    Auto-check passed
  • Compile Al App

    microsoft/AL

    Official

    Compiles a temporary AL project through the workflow-installed public prerelease ALTool and verifies that a fresh app package was emitted.

    884 GitHub stars~164 tokensUpdated 21 days ago
    Auto-check passed
  • Verify Al E2E

    microsoft/AL

    Official

    Orchestrates the smallest production-path AL reproduction through the workflow-installed public prerelease ALTool and BCInsider sandbox.

    884 GitHub stars~241 tokensUpdated 21 days ago
    Auto-check passed

Questions about Run Al Tests

What does Run Al Tests do?

Runs a published AL test codeunit against the provisioned BCInsider sandbox through the public prerelease ALTool. Run Al Tests is an agent skill from microsoft/AL, published by the product's own GitHub organization. Runs a published AL test codeunit against the provisioned BCInsider sandbox through the public prerelease ALTool.

How do I install Run Al Tests in Claude Code?

Run `npx skills add microsoft/AL --skill run-al-tests -a claude-code`. Or copy the skill folder (.github/skills/run-al-tests in microsoft/AL) into .claude/skills/run-al-tests in your project. Claude Code loads it when a task matches its description.

How do I install Run Al Tests in Codex?

Run `npx skills add microsoft/AL --skill run-al-tests -a codex`. Or copy the skill folder (.github/skills/run-al-tests in microsoft/AL) into .agents/skills/run-al-tests in your project. Codex loads it when a task matches its description.

Can I use Run Al Tests 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/AL --skill run-al-tests -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/run-al-tests, .gemini/skills/run-al-tests, .github/skills/run-al-tests and .opencode/skills/run-al-tests in your project.

What does Run Al Tests need to run?

SKILL.md names no scripts, command-line tools or credentials: Run Al Tests is instructions for the agent only.

Does Run Al Tests 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 Run Al Tests 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 Run Al Tests use?

Run Al Tests 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 Run Al Tests use?

About 208 tokens (SKILL.md is roughly 832 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 Run Al Tests?

Skills that share tags, products or a category with Run Al Tests: ESP32 CSI Node Provisioning (ruvnet/RuView, 97k stars), Implementing Scim Provisioning With Okta (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Implementing Just In Time Access Provisioning (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Secondmate Provisioning (kunchenguid/firstmate, 7.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Run Al Tests?

microsoft (a GitHub organization, an official publisher) maintains it in microsoft/AL, which has 884 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 16, 2026.

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