
Azure AI contentsafety ts
Lets an agent scan text and images for harmful content with Azure AI Content Safety
- Scripts
- None
- Platforms
- Claude Code, Codex, Cursor
- GitHub stars
- 3.2K
- Last commit
- 1 day ago
- License
- MIT
- Listing updated
- today
Similar skills
About Azure AI contentsafety ts
Azure AI contentsafety ts is an open-source agent skill for cloud and infrastructure. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.
This skill gives the agent a working reference for the Azure AI Content Safety REST client in TypeScript. It covers creating the client with either an API key or Azure identity credentials, then sending text or images to the analyze endpoints and reading back severity scores for hate, sexual, violence and self-harm categories. Severity can be returned on a four-level or eight-level scale.
Beyond single analyses, the skill walks through managing custom blocklists: creating and deleting them, adding or listing terms, and checking text against them during analysis. It also includes a small moderation helper that turns category severities and blocklist hits into an allow or reject decision with a configurable threshold, plus a severity table suggesting how to act at each level.
The code is TypeScript and expects the @azure-rest/ai-content-safety, @azure/identity and @azure/core-auth packages, along with a Content Safety endpoint and key or a credential configured through environment variables. The skill ships as a single SKILL.md file with no bundled scripts.
When your agent uses it
Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual content, or self-harm, or managing custom blocklists.
From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.
What it can access
From a static check of its 1 file (8 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.
Check another skill before you install it.
Install
Copy the skill folder to ~/.claude/skills/azure-ai-contentsafety-ts to use it in all your projects:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/azure-ai-contentsafety-ts &&
cp -R "$tmp/.github/plugins/azure-sdk-typescript/skills/azure-ai-contentsafety-ts" ~/.claude/skills/azure-ai-contentsafety-ts &&
rm -rf "$tmp"For one project only, put the folder in .claude/skills/azure-ai-contentsafety-ts inside it instead.
Copy the skill folder to ~/.agents/skills/azure-ai-contentsafety-ts to use it in every repository:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/azure-ai-contentsafety-ts &&
cp -R "$tmp/.github/plugins/azure-sdk-typescript/skills/azure-ai-contentsafety-ts" ~/.agents/skills/azure-ai-contentsafety-ts &&
rm -rf "$tmp"For one repository only, put the folder in .agents/skills/azure-ai-contentsafety-ts inside it instead.
Copy the skill folder to ~/.cursor/skills/azure-ai-contentsafety-ts to use it in every project:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/azure-ai-contentsafety-ts &&
cp -R "$tmp/.github/plugins/azure-sdk-typescript/skills/azure-ai-contentsafety-ts" ~/.cursor/skills/azure-ai-contentsafety-ts &&
rm -rf "$tmp"For one project only, put the folder in .cursor/skills/azure-ai-contentsafety-ts inside it instead.
Run in a terminal (add --scope workspace to install it for the current workspace only):
gemini skills install https://github.com/microsoft/skills.git --path .github/plugins/azure-sdk-typescript/skills/azure-ai-contentsafety-tsOr copy the folder to ~/.gemini/skills/azure-ai-contentsafety-ts yourself.
For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/azure-ai-contentsafety-ts:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/azure-ai-contentsafety-ts &&
cp -R "$tmp/.github/plugins/azure-sdk-typescript/skills/azure-ai-contentsafety-ts" ~/.copilot/skills/azure-ai-contentsafety-ts &&
rm -rf "$tmp"For one project only, put the folder in .github/skills/azure-ai-contentsafety-ts inside it instead.
Get the folder:
git clone --depth 1 https://github.com/microsoft/skills.gitThen copy skills/.github/plugins/azure-sdk-typescript/skills/azure-ai-contentsafety-ts into your agent's skills folder as azure-ai-contentsafety-ts. Agents that support SKILL.md read one folder per skill.
What it does
- Text harm analysis
- Scores submitted text across hate, sexual, violence and self-harm categories.
- Image harm analysis
- Checks images sent as base64 content or from a blob storage URL.
- Custom blocklist management
- Creates, updates, lists and deletes blocklists and their terms.
- Blocklist matching
- Reports which custom blocklist terms appear in analyzed text.
- Authentication setup
- Shows API key and Azure identity credential configuration for the client.
- Moderation decision helper
- Provides a function that converts severity and blocklist results into allow or block.
Good for
- Screen user comments for hate speech or violent language before publishing
- Check uploaded images for sexual or violent content
- Maintain a custom list of banned terms and test messages against it
- Build a moderation step that flags self-harm mentions for human review
Azure AI contentsafety ts FAQ
What does the skill need to run?
It expects the @azure-rest/ai-content-safety, @azure/identity and @azure/core-auth npm packages, a Content Safety endpoint, and either an API key or Azure credentials set through environment variables.
Does it include scripts or tools that run on their own?
No. The skill is a single SKILL.md file with instructions and code examples, and it bundles no scripts.
Which harm categories does it cover?
Hate, Sexual, Violence and SelfHarm, with severity output as either four levels (0, 2, 4, 6) or eight levels (0 to 7).
How do I install Azure AI contentsafety ts in Claude Code?
Copy the skill folder from GitHub to ~/.claude/skills/azure-ai-contentsafety-ts to use it in all your projects, or to .claude/skills/azure-ai-contentsafety-ts in one project.
Does Azure AI contentsafety ts run scripts?
No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.
Which AI agents can use Azure AI contentsafety ts?
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.
What are the best alternatives to Azure AI contentsafety ts?
The closest alternatives to Azure AI contentsafety ts are Reverse engineer anything, Rea tool design, Codebase design, Prototype and Web artifacts builder.
Where this comes from
- Description: from the skill's own SKILL.md.
More from microsoft/skills

Finds AKS scheduling, bin-packing, node scaling and storage cost inefficiencies
- Open source
- 3.2K GitHub stars
- Cloud and infrastructure

Diagnoses AKS GPU and KAITO incidents using read-only cluster evidence
- Open source
- 3.2K GitHub stars
- Cloud and infrastructure

Matches exact AKS error signatures to documented fixes, with citations and read-only
- Open source
- 3.2K GitHub stars
- Cloud and infrastructure

Guides bounded packet captures on AKS nodes and Azure network evidence collection
- Open source
- 3.2K GitHub stars
- Cloud and infrastructure

Investigates live AKS incidents read-only, tracing pod, node, network and quota failures
- Open source
- 3.2K GitHub stars
- Cloud and infrastructure

Builds Azure portal deep links to the blade that performs a given operation
- Open source
- 3.2K GitHub stars
- Cloud and infrastructure
Alternatives to Azure AI contentsafety ts

Reverse engineers binaries, apps and firmware with REA and builds web app environments
- Open source
- 465K GitHub stars
- Security

Rea tool design
SkillAudits and designs REA investigation tools, CLI and MCP contracts and Evidence semantics
- Open source
- 465K GitHub stars
- Design and media

Codebase design
SkillTeaches a deep-module vocabulary for designing interfaces, seams and testable code
- Open source
- 326K GitHub stars
- Design and media

Prototype
SkillBuilds a throwaway prototype to settle a design question: a logic demo or UI variants
- Open source
- 326K GitHub stars
- Developer tools

Builds React and shadcn/ui artifacts and bundles them into one self-contained HTML file
- Free
- 196K GitHub stars
- Developer tools

Theme factory
SkillApplies one of ten preset color and font themes, or a custom one, to slides and docs
- Free
- 196K GitHub stars
- Design and media


