Azure AI Projects Python SDK
microsoft/skills
Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.
Primary entrypoint for coding agents using CAIRA as reference material to design and build generative AI solutions with Azure AI Foundry, Azure OpenAI-compatible endpoints, agent frameworks, APIs…
Install Caira
$ npx skills add microsoft/CAIRA --skill caira -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install microsoft/CAIRA caira --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/CAIRA.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/caira .claude/skills/caira && 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 "caira" agent skill from https://github.com/microsoft/CAIRA/tree/main/skills/caira into .claude/skills/caira/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "caira", 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/CAIRA/tree/main/skills/cairaType 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/CAIRA --skill caira -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install microsoft/CAIRA caira --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/CAIRA.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/caira .agents/skills/caira && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "caira" agent skill from https://github.com/microsoft/CAIRA/tree/main/skills/caira into .agents/skills/caira/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "caira", 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/CAIRA --skill caira -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install microsoft/CAIRA caira --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/CAIRA.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/caira .cursor/skills/caira && 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 "caira" agent skill from https://github.com/microsoft/CAIRA/tree/main/skills/caira into .cursor/skills/caira/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "caira", 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/CAIRA.git --path skills/caira--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/CAIRA --skill caira -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install microsoft/CAIRA caira --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/CAIRA.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/caira .gemini/skills/caira && 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 "caira" agent skill from https://github.com/microsoft/CAIRA/tree/main/skills/caira into .gemini/skills/caira/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "caira", 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/CAIRA cairaInstalls 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/CAIRA --skill caira -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/microsoft/CAIRA.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/caira .github/skills/caira && 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 "caira" agent skill from https://github.com/microsoft/CAIRA/tree/main/skills/caira into .github/skills/caira/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "caira", 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/CAIRA --skill caira -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/CAIRA caira --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/CAIRA.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/caira .opencode/skills/caira && 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 "caira" agent skill from https://github.com/microsoft/CAIRA/tree/main/skills/caira into .opencode/skills/caira/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "caira", 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
caira- GitHub stars
- 229
- Token cost
- ~1.2k tokens
- SKILL.md length
- 588 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Primary entrypoint for coding agents using CAIRA as reference material to design and build generative AI solutions with Azure AI Foundry, Azure OpenAI-compatible endpoints, agent frameworks, APIs…
- Works in 5 steps: What outcome is the user trying to build? → Do they already have Foundry/OpenAI… → What kind of networking isolation or… → …
- Tasks that involve Building AI agents
- SKILL.md covers Intake before generating changes, Core rules, Current reference components and How to use CAIRA references
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Caira is an agent skill from microsoft/CAIRA, published by the product's own GitHub organization. Primary entrypoint for coding agents using CAIRA as reference material to design and build generative AI solutions with Azure AI Foundry, Azure OpenAI-compatible endpoints, agent frameworks, APIs, and frontends tailored to a user's scenario.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Needs access to the github.com/microsoft/caira repository.
It sits in AI & LLM Engineering, covering Building AI agents. It works with Azure AI Foundry, Azure OpenAI and GitHub. The repository describes itself as: Composable AI Reference Architectures (CAIRA). The licence is MIT.
When your agent uses it
- Tasks that involve Building AI agents
Example prompts
- “/caira”
Requirements
- Docker
- Compatibility (from SKILL.md): Needs access to the github.com/microsoft/caira repository.
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- What outcome is the user trying to build?
- Do they already have Foundry/OpenAI endpoints, hosting, identity, observability, or frontend/API code?
- What kind of networking isolation or security boundaries are needed?
- Which programming languages or frameworks does the user prefer? If the user prefers something that's not directly in the CAIRA references…
- Which components are needed now: Foundry, Container Apps, API, frontend, or only app code? If the answer shows the user only needs one…
What it can do on your machine
Read from SKILL.md and the folder at commit a36d043. 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.
Compatibility
Needs access to the github.com/microsoft/caira repository.
From compatibility in the SKILL.md frontmatter.
Context cost
Caira loads about 1.2k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 588 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/CAIRA at commit a36d043, republished under its MIT licence (© microsoft). 588 words, ~1,214 tokens.
Download SKILL.mdSave it as
.claude/skills/caira/SKILL.md (or your agent's skills folder).- name
- caira
- description
- Primary entrypoint for coding agents using CAIRA as reference material to design and build generative AI solutions with Azure AI Foundry, Azure OpenAI-compatible endpoints, agent frameworks, APIs, and frontends tailored to a user's scenario.
- compatibility
- Needs access to the github.com/microsoft/caira repository.
- metadata.author
- Microsoft
- metadata.version
- 0.4.3
CAIRA
Use this skill when a user wants to build or extend a generative AI solution. CAIRA is a reference library, not an application generator: inspect the repository, select the smallest relevant reference components, and adapt them into the user's workspace.
Intake before generating changes
Ask only what is needed to choose components:
- What outcome is the user trying to build?
- Do they already have Foundry/OpenAI endpoints, hosting, identity, observability, or frontend/API code?
- What kind of networking isolation or security boundaries are needed?
- Which programming languages or frameworks does the user prefer? If the user prefers something that's not directly in the CAIRA references, try to follow the same architectural patterns and design principles shown in the CAIRA reference components, but adapt them to the user's preferred languages or frameworks.
- Which components are needed now: Foundry, Container Apps, API, frontend, or only app code? If the answer shows the user only needs one component, use only that component.
Core rules
- Use the
reference-architecturesdirectory in thegithub.com/microsoft/caira/repository as the canonical source of truth. Inspect it either with the GitHub MCP server if available, through GitHub raw URLs, or clone the repository temporarily to inspectreference-architectures/locally. - When reviewing the reference architectures, read the full code of the desired component. Do not limit the investigation to the README or docs. The source of truth is the code.
- Prefer small component references over full-stack copying.
- For scenarios that need OpenAI-compatible endpoints, prefer the Foundry IaC reference unless the user already has endpoints or asks for a different approach.
- Determine what the user already has before proposing new infrastructure.
- Always use managed identities or other passwordless identity patterns. NEVER USE API keys, static credentials, or secrets, unless the user explicitly asks for an API-key- or secret-based approach.
- When implementing IaC for Foundry, use the Azure Verified Module, as shown in the reference architectures. Don't use standalone Terraform resources related to Foundry unless explicitly requested.
- If an API that communicates with Foundry needs to be implemented, ALWAYS prefer using Foundry resources instead of Azure OpenAI resources, unless the user explicitly asks for Azure OpenAI. Even with the OpenAI Agents SDK.
- Before proposing repository security scans, check whether the target repository already uses or has configured Gitleaks, Trivy, or similar tools for secret, dependency, container, or IaC scanning. If similar scanning is missing, ask whether the user wants to add Gitleaks and/or Trivy scans before implementing them.
- Keep recommendations focused on the current reference components listed below.
- Explain which CAIRA paths influenced the recommendation or generated files.
- Always ask follow-up questions to narrow down the user's needs and avoid unnecessary copying of reference code.
- Before start implementing, confirm the user's scenario, needs, and which CAIRA reference components, configuration, networking, and security boundaries will be used.
Show full SKILL.md (122 more words)Show less
Current reference components
| Need | CAIRA reference path |
|---|---|
| Foundry foundation | reference-architectures/iac/foundry/ |
| Container Apps hosting for API + frontend | reference-architectures/iac/container-apps/ |
| TypeScript API using OpenAI Agents SDK | reference-architectures/app/api/typescript/openai-agents-sdk/ |
| TypeScript API using Foundry Agent Service | reference-architectures/app/api/typescript/foundry-agent-service/ |
| C# API using Microsoft Agent Framework | reference-architectures/app/api/csharp/microsoft-agent-framework/ |
| React frontend | reference-architectures/app/frontend/typescript/react/ |
| Frontend/API contract | reference-architectures/app/API_CONTRACT.md |
How to use CAIRA references
- Inspect the relevant component source files.
- Copy or adapt only the files needed for the user's stack.
- Remove sample text, model names, env vars, or Terraform variables that do not apply to the user's scenario.
- Preserve the component's validation style: npm scripts for TypeScript, .NET build for C#, Terraform validation for IaC, Docker builds for containers.
- Mention the exact CAIRA paths used and what was intentionally left out.
© 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 skills/caira of microsoft/CAIRA.
Open the folder on GitHubat commit a36d043
Compare with similar skills
Caira 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 |
|---|---|---|---|---|---|---|
| Caira this skillmicrosoft/CAIRA | 229 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Azure AI Projects Python SDKmicrosoft/skills | 3.1k | 6 repos | ~2.8k | Automated safety check: Pass | MIT | |
| Code Reviewlangchain-ai/langchain-azure | 147 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Create Agent Catalog Sourcekubeflow/hub | 186 | — | ~5.4k | Automated safety check: Notes | Apache-2.0 | |
| Microsoft Docsmicrosoft/ai-agents-for-beginners | 77k | 3 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Submit Integrationlangchain-ai/docs | 425 | — | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
- Official
- Official
Code Review
langchain-ai/langchain-azure
Reviews changes in the langchain-azure monorepo using package-specific knowledge of langchain-azure-ai, langchain-azure-compute, langchain-azure-cosmosdb, langchain-azure-postgresql…
Create Agent Catalog Source
kubeflow/hub
A skill your agent uses when the user asks to "create an agent catalog", "generate agent catalog source", "build agent catalog from repo", "catalog my agents", or wants to scan a repository…
- Official
Microsoft Docs
microsoft/ai-agents-for-beginners
Query official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub, and more.
- Official
Submit Integration
langchain-ai/docs
Create a LangChain docs integration listing from a structured GitHub issue submission (issue form fields as JSON).
- Official
Agent Framework Azure AI Py
microsoft/skills
Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai).
Related
Works with
Categories
Questions about Caira
What does Caira do?
Primary entrypoint for coding agents using CAIRA as reference material to design and build generative AI solutions with Azure AI Foundry, Azure OpenAI-compatible endpoints, agent frameworks, APIs…. Caira is an agent skill from microsoft/CAIRA, published by the product's own GitHub organization. Primary entrypoint for coding agents using CAIRA as reference material to design and build generative AI solutions with Azure AI Foundry, Azure OpenAI-compatible endpoints, agent frameworks, APIs, and frontends tailored to a user's scenario.
When should I use Caira?
Caira fits situations like: tasks that involve Building AI agents.
How do I install Caira in Claude Code?
Run `npx skills add microsoft/CAIRA --skill caira -a claude-code`. Or copy the skill folder (skills/caira in microsoft/CAIRA) into .claude/skills/caira in your project. Claude Code loads it when a task matches its description.
How do I install Caira in Codex?
Run `npx skills add microsoft/CAIRA --skill caira -a codex`. Or copy the skill folder (skills/caira in microsoft/CAIRA) into .agents/skills/caira in your project. Codex loads it when a task matches its description.
Can I use Caira 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/CAIRA --skill caira -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/caira, .gemini/skills/caira, .github/skills/caira and .opencode/skills/caira in your project.
What does Caira need to run?
SKILL.md names no scripts, command-line tools or credentials: Caira is instructions for the agent only. Our summary lists: Docker. Compatibility (from SKILL.md): Needs access to the github.com/microsoft/caira repository..
Does Caira 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 Caira 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 Caira use?
Caira 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 Caira use?
About 1.2k tokens (SKILL.md is roughly 4.9k 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 Caira?
Skills that share tags, products or a category with Caira: Azure AI Projects Python SDK (microsoft/skills, 3.1k stars), Code Review (langchain-ai/langchain-azure, 147 stars), Create Agent Catalog Source (kubeflow/hub, 186 stars) and Microsoft Docs (microsoft/ai-agents-for-beginners, 77k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Caira?
microsoft (a GitHub organization, an official publisher) maintains it in microsoft/CAIRA, which has 229 GitHub stars. The repository was last updated on September 22, 2026.
Source: microsoft/CAIRA on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.