Official agent skill

Generate Readme

by microsoft in microsoft/Agent365-Samples

Generates or updates a README.md for an Agent 365 sample agent.

OfficialMITAuto-check: notesDevelopment

Install Generate Readme

skills CLI
$ npx skills add microsoft/Agent365-Samples --skill generate-readme -a claude-code

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

GitHub CLI
$ gh skill install microsoft/Agent365-Samples generate-readme --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/Agent365-Samples.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/generate-readme .claude/skills/generate-readme && 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
generate-readme
GitHub stars
112
Token cost
~2.6k tokens
SKILL.md length
649 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Generates or updates a README.md for an Agent 365 sample agent.

  • Works in 12 steps: Title + Description → What This Sample Demonstrates → Prerequisites → …
  • Tasks that involve Technical documentation
  • SKILL.md covers Instructions, README Template, Detection Rules and Rules
  • Reaches learn.microsoft.com and opensource.microsoft.com

What it does

Generate Readme is an agent skill from microsoft/Agent365-Samples, published by the product's own GitHub organization. Generates or updates a README.md for an Agent 365 sample agent. Detects the agent type (interactive or autonomous), programming language (.NET, Node.js, Python), and authentication model, then produces a README following the standard template with all required sections.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: ["claude-code"]

It sits in Development, covering Technical documentation and Authentication. It works with Python, .NET and Node.js. The licence is MIT.

When your agent uses it

  • Tasks that involve Technical documentation
  • Tasks that involve Authentication

Example prompts

  • “Use the generate-readme skill to generate or updates a README.md for an Agent 365 sample agent”
  • “/generate-readme”

Requirements

  • Python 3
  • Node.js
  • Compatibility (from SKILL.md): ["claude-code"]
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Grep, Glob, Bash, AskUserQuestion

Workflow steps

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

  1. Title + Description
  2. What This Sample Demonstrates
  3. Prerequisites
  4. Authentication + Identity
  5. Environment Configuration
  6. Running the Agent Locally
  7. Deploying the Agent
  8. Observability
  9. Support
  10. Contributing
  11. Additional Resources
  12. Trademarks

What it can do on your machine

Read from SKILL.md and the folder at commit ecbf899. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Grep
    • Glob
    • Bash
    • AskUserQuestion

    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 markdown).

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • learn.microsoft.com
    • opensource.microsoft.com
    • cla.opensource.microsoft.com
    • go.microsoft.com

    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

    ["claude-code"]

    From compatibility in the SKILL.md frontmatter.

Context cost

Generate Readme loads about 2.6k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 649 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:109
    figuration reference — either a table of .env variables or appsettings.json keys. Include "Set by" column (CLI or Manual
  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Grep, Glob, Bash, AskUserQuestion

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/Agent365-Samples at commit ecbf899, republished under its MIT licence (© microsoft). 649 words, ~2,631 tokens.

Download SKILL.mdSave it as .claude/skills/generate-readme/SKILL.md (or your agent's skills folder).
name
generate-readme
description
Generates or updates a README.md for an Agent 365 sample agent. Detects the agent type (interactive or autonomous), programming language (.NET, Node.js, Python), and authentication model, then produces a README following the standard template with all required sections.
allowed-tools
Read, Write, Edit, Grep, Glob, Bash, AskUserQuestion
compatibility
["claude-code"]
user-invocable
true
argument-hint
Optional: path to sample agent directory
model
sonnet

Generate README

Generate or update a README.md for a sample agent in the Agent365-Samples repository.

Instructions

  1. Detect the agent — identify the programming language, orchestrator, and whether it is interactive (message-driven) or autonomous (background service).
  2. Detect authentication + identity model — determine which combination applies (see table below).
  3. Generate the README using the exact template structure defined in this skill.
  4. Adapt content from the existing README if one exists — preserve sample-specific details (tool names, service names, configuration keys) but restructure to match the template.

README Template

The README MUST contain the following sections in this exact order. Do not add, remove, or reorder sections unless noted.

1. Title + Description
markdown
# <Sample Title> — <Language> Sample

<1–3 sentence description of what the sample demonstrates. State whether it is interactive or autonomous, what SDK/orchestrator it uses, and what makes it a useful reference.>

For comprehensive documentation, visit the [Microsoft Agent 365 Developer Documentation](https://learn.microsoft.com/en-us/microsoft-agent-365/developer/).
2. What This Sample Demonstrates

A table of patterns demonstrated and their file locations:

markdown
## What This Sample Demonstrates

| Pattern | Where |
|---------|-------|
| <pattern description> | `<file path>` |
3. Prerequisites
markdown
## Prerequisites

- <Runtime/SDK version>
- [Azure CLI](https://learn.microsoft.com/cli/azure/install-azure-cli)
- [Agent 365 CLI](https://learn.microsoft.com/en-us/microsoft-agent-365/developer/agent-365-cli) (install: `dotnet tool install --global Microsoft.Agents.A365.DevTools.Cli --prerelease`)
- An Azure OpenAI resource with a deployed model (e.g., `gpt-4o`)
- An Entra tenant with at minimum the **Agent ID Developer** role
- <Any additional prerequisites specific to the sample>
4. Authentication + Identity

This section describes the authentication and identity model used by the agent. Pick exactly ONE auth model and ONE identity model from the tables below. If it is unclear which model is used from the code/existing README, ask the user.

Auth models (pick one):

Auth ModelDescriptionWhen to use
Agent userThe agent authenticates as its own agentic user identity.AI Teammates with Teams/Copilot chat capabilities.
On behalf of the userThe agent acts on behalf of the signed-in user via OBO token exchange.Interactive or autonomous agents that call resources as the user.
App-basedThe agent authenticates using application credentials with no user context.Interactive or autonomous agents that call resources as the app.

Identity models (pick one):

Identity ModelDescriptionWhen to use
Agent user with own identityThe agent has an agentic user account in the tenant.AI Teammates with Teams/Copilot chat capabilities.
Agent identityThe agent has an identity service principal that serves as an instance of the blueprint.Agent 365 blueprint-based agents that use the Agent identity model (service principal instance of the blueprint).
Entra app service principalThe agent authenticates as a standard Entra app registration (no blueprint, no FMI).Simple agents using direct client credentials without the A365 identity model.

Write the section as:

markdown
## Authentication + Identity

| Aspect | Model |
|--------|-------|
| **Authentication** | <one of: Agent user, On behalf of the user, App-based> |
| **Identity** | <one of: Agent user with own identity, Agent identity, Entra app service principal> |

<1–2 sentences explaining how auth works in this specific sample. Reference the relevant code file.>
5. Environment Configuration
markdown
## Environment Configuration

### Agent 365 Setup

<Steps to provision the agent using the A365 CLI. Include `a365 setup all`, admin consent, and manual configuration (e.g., Azure OpenAI keys).>

### Configuration

<Configuration reference — either a table of .env variables or appsettings.json keys. Include "Set by" column (CLI or Manual).>

For Python and Node.js samples, include ENABLE_A365_OBSERVABILITY_EXPORTER, ENABLE_A365_OBSERVABILITY, OTEL_LOG_LEVEL, and A365_OBSERVABILITY_LOG_LEVEL in the configuration table. If they are not set, prompt the user and ask if they would like them to be added. If yes, add them. Default values are ENABLE_A365_OBSERVABILITY_EXPORTER=true, ENABLE_A365_OBSERVABILITY=true, A365_OBSERVABILITY_LOG_LEVEL=info, and OTEL_LOG_LEVEL=Debug. For .NET samples, these environment variables do not apply — the A365 exporter is controlled in code via ExportTarget.Agent365, and log levels are configured in appsettings.json under Logging:LogLevel. The .NET equivalents are: Logging:LogLevel:OpenTelemetry (equivalent of OTEL_LOG_LEVEL) and Logging:LogLevel:Microsoft.Agents.A365.Observability (equivalent of A365_OBSERVABILITY_LOG_LEVEL).

Show full SKILL.md (220 more words)Show less
6. Running the Agent Locally
markdown
## Running the Agent Locally

### Quick start (Azure OpenAI only)

<Minimal setup — just LLM credentials, no A365.>

### Local development (with A365 observability)

<Full setup with A365 credentials and observability export.>

For interactive agents, reference the Configure Agent Testing guide and Microsoft 365 Agents Playground.

7. Deploying the Agent
markdown
## Deploying the Agent

<Production deployment instructions. Include MSI/FIC requirements, environment variables, and hosting provider guidance.>
8. Observability
markdown
## Observability

<Describe the tracing spans produced by the agent (e.g., InvokeAgentScope, InferenceScope, ExecuteToolScope). For agents with a custom token flow, describe the FMI chain briefly. Link to the observability guide.>

Keep this section concise — no ASCII art diagrams. Reference the Agent observability guide for details.

9. Support
markdown
## Support

For issues, questions, or feedback:

- **Issues**: Please file issues in the [GitHub Issues](https://github.com/microsoft/Agent365-Samples/issues) section
- **Documentation**: See the [Microsoft Agent 365 Developer Documentation](https://learn.microsoft.com/en-us/microsoft-agent-365/developer/)
- **Security**: For security issues, please see [SECURITY.md](../../../../SECURITY.md)
10. Contributing
markdown
## Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit <https://cla.opensource.microsoft.com>.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/). For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.
11. Additional Resources
markdown
## Additional Resources

- [Microsoft Agent 365 Developer Documentation](https://learn.microsoft.com/en-us/microsoft-agent-365/developer/)
- [Agent observability guide](https://learn.microsoft.com/en-us/microsoft-agent-365/developer/observability)
- <Language-specific SDK repository link>
- <Any other relevant links>
12. Trademarks
markdown
## Trademarks

*Microsoft, Windows, Microsoft Azure and/or other Microsoft products and services referenced in the documentation may be either trademarks or registered trademarks of Microsoft in the United States and/or other countries. The licenses for this project do not grant you rights to use any Microsoft names, logos, or trademarks. Microsoft's general trademark guidelines can be found at http://go.microsoft.com/fwlink/?LinkID=254653.*
13. License
markdown
## License

Copyright (c) Microsoft Corporation. All rights reserved.

Licensed under the MIT License — see the [LICENSE](../../../../LICENSE.md) file for details.

Adjust the relative path to LICENSE.md based on the sample's depth in the repository.

Detection Rules

Programming Language
  • .csproj file exists → .NET
  • package.json exists → Node.js/TypeScript
  • pyproject.toml or .py files → Python
Agent Type
  • Has /api/messages endpoint, TurnContext, AgentApplication, or message handler → Interactive
  • Has BackgroundService, background loop, no message endpoint → Autonomous
Auth + Identity Detection
  • Has TurnContext with Activity.From + agentic user references → Agent user auth + Agent user with own identity
  • Has exchangeToken / OBO flow → On behalf of the user
  • Has only client credentials / MSI with no user context → App-based + Agent identity
  • Has WithFmiPath / fmi_path / FMI chain → Agent identity
  • Has simple ClientSecretCredential with no FMI → Entra app service principal

Rules

  • Do NOT include How It Works or Project Structure sections.
  • Do NOT include ASCII art diagrams.
  • Do NOT invent content — only document what exists in the code.
  • Do NOT include sample-specific SDK repository links unless you can verify the URL exists.
  • ALWAYS read the agent's source code before generating the README.
  • If an existing README exists, preserve any sample-specific details that are accurate.

© 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 .claude/skills/generate-readme of microsoft/Agent365-Samples.

Open the folder on GitHubat commit ecbf899

Compare with similar skills

Generate Readme 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.

Generate Readme compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Generate Readme this skillmicrosoft/Agent365-Samples112—~2.6kAutomated safety check: NotesMIT
Copilot SDKaiskillstore/marketplace4305 repos~3.8kAutomated safety check: PassNone
Copilot SDKintellectronica/agent-skills295—~3.2kAutomated safety check: PassCC0-1.0
Copilot SDKmicrosoft/skills3.1k—~7.1kAutomated safety check: PassMIT
README and DESIGN Generatorfengshao1227/ccg-workflow5.9k—~410Automated safety check: NotesMIT
Release Coherencemacalbert/envilder138—~1.3kAutomated safety check: PassMIT

Similar skills

  • Copilot SDK

    aiskillstore/marketplace

    Build applications that programmatically interact with GitHub Copilot.

    430 GitHub starsUsed in 5 repos~3.8k tokens
    Agent WorkflowsAuto-check passed
  • Copilot SDK

    intellectronica/agent-skills

    This skill helps with GitHub Copilot SDK work across Node.js/TypeScript, Python, Go, .NET, and Java.

    295 GitHub stars~3.2k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed
  • Copilot SDK

    microsoft/skills

    Official

    Build applications powered by GitHub Copilot using the Copilot SDK.

    3.1k GitHub stars~7.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • README and DESIGN Generator

    fengshao1227/ccg-workflow

    Generates README.md and DESIGN.md skeletons for a module by scanning its structure with a Node script, then lists what to fill in by hand.

    5.9k GitHub stars~410 tokensUpdated 22 days ago
    DevelopmentAuto-check: notes
  • Release Coherence

    macalbert/envilder

    Unified release coherence workflow for any component (CLI, GHA, or SDK).

    138 GitHub stars~1.3k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • SDK Release Checklist

    macalbert/envilder

    Checklist for adding a new SDK or releasing a new SDK version.

    138 GitHub stars~1.5k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

Categories

Questions about Generate Readme

What does Generate Readme do?

Generates or updates a README.md for an Agent 365 sample agent. Generate Readme is an agent skill from microsoft/Agent365-Samples, published by the product's own GitHub organization.md for an Agent 365 sample agent.

When should I use Generate Readme?

Generate Readme fits situations like: tasks that involve Technical documentation; tasks that involve Authentication.

How do I install Generate Readme in Claude Code?

Run `npx skills add microsoft/Agent365-Samples --skill generate-readme -a claude-code`. Or copy the skill folder (.claude/skills/generate-readme in microsoft/Agent365-Samples) into .claude/skills/generate-readme in your project. Claude Code loads it when a task matches its description.

How do I install Generate Readme in Codex?

Run `npx skills add microsoft/Agent365-Samples --skill generate-readme -a codex`. Or copy the skill folder (.claude/skills/generate-readme in microsoft/Agent365-Samples) into .agents/skills/generate-readme in your project. Codex loads it when a task matches its description.

Can I use Generate Readme 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/Agent365-Samples --skill generate-readme -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/generate-readme, .gemini/skills/generate-readme, .github/skills/generate-readme and .opencode/skills/generate-readme in your project.

What does Generate Readme need to run?

SKILL.md names no scripts, command-line tools or credentials: Generate Readme is instructions for the agent only. Our summary lists: Python 3; Node.js. Its frontmatter pre-approves these tools: Read, Write, Edit, Grep, Glob, Bash, AskUserQuestion. Compatibility (from SKILL.md): ["claude-code"].

Does Generate Readme access the network?

SKILL.md names 4 domains. In commands or code: learn.microsoft.com, opensource.microsoft.com, cla.opensource.microsoft.com and go.microsoft.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Generate Readme safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Generate Readme use?

Generate Readme 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 Generate Readme use?

About 2.6k tokens (SKILL.md is roughly 11k 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 Generate Readme?

Skills that share tags, products or a category with Generate Readme: Copilot SDK (aiskillstore/marketplace, 430 stars), Copilot SDK (intellectronica/agent-skills, 295 stars), Copilot SDK (microsoft/skills, 3.1k stars) and README and DESIGN Generator (fengshao1227/ccg-workflow, 5.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Generate Readme?

microsoft (a GitHub organization, an official publisher) maintains it in microsoft/Agent365-Samples, which has 112 GitHub stars. The repository was last updated on October 1, 2026.

Source: microsoft/Agent365-Samples on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.