Agent skill

Reviewing Documentation

by microsoft-foundry in microsoft-foundry/foundry-agent-webapp

Provides documentation audit checklists and quality standards.

MITAuto-check passedAgent Workflows

Install Reviewing Documentation

skills CLI
$ npx skills add microsoft-foundry/foundry-agent-webapp --skill reviewing-documentation -a claude-code

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

GitHub CLI
$ gh skill install microsoft-foundry/foundry-agent-webapp reviewing-documentation --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-foundry/foundry-agent-webapp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/reviewing-documentation .claude/skills/reviewing-documentation && 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
reviewing-documentation
GitHub stars
127
Token cost
~1.1k tokens
SKILL.md length
498 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
MIT

At a glance

Provides documentation audit checklists and quality standards.

  • Reviewing README files
  • SKILL.md covers Architecture Maintenance, SKILL.md Quality Gates, .agent.md Quality Gates and copilot-instructions.md, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Agent definitions

What it does

Reviewing Documentation is an agent skill from microsoft-foundry/foundry-agent-webapp. Provides documentation audit checklists and quality standards. Use when reviewing README files, SKILL.md files, agent definitions, copilot-instructions.md, or ARCHITECTURE-FLOW.md for quality and consistency.

Its SKILL.md is about 1.1k 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 Agent Workflows, covering Agent instruction files, Audit readiness and Skill authoring. The repository describes itself as: GitHub Copilot enabled repo for building and deploying a web application with Entra ID authentication and integrated with Azure AI Foundry Agents. The licence is MIT.

When your agent uses it

  • Reviewing README files
  • Agent definitions
  • Copilot-instructions.md
  • ARCHITECTURE-FLOW.md for quality and consistency

Example prompts

  • “Use the reviewing-documentation skill to provide documentation audit checklists and quality standards”
  • “/reviewing-documentation”

What it can do on your machine

Read from SKILL.md and the folder at commit f6cb362. 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

Reviewing Documentation loads about 1.1k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 498 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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-foundry/foundry-agent-webapp at commit f6cb362, republished under its MIT licence (© microsoft-foundry). 498 words, ~1,097 tokens.

Download SKILL.mdSave it as .claude/skills/reviewing-documentation/SKILL.md (or your agent's skills folder).
name
reviewing-documentation
description
Provides documentation audit checklists and quality standards. Use when reviewing README files, SKILL.md files, agent definitions, copilot-instructions.md, or ARCHITECTURE-FLOW.md for quality and consistency.

Documentation Review Guidance

Audit, improve, and maintain documentation quality across the repository. Search for doc files — don't rely on hardcoded paths.

Architecture Maintenance

For ARCHITECTURE-FLOW.md updates, load .github/skills/understanding-architecture/SKILL.md first — it has validation commands and source-of-truth mappings.

SKILL.md Quality Gates

Naming rules (agentskills.io spec):

  • ✅ writing-csharp-code (lowercase, hyphens, max 64 chars)
  • ❌ WritingCSharpCode | writing--csharp | -writing-code

Required frontmatter: name (must match directory name), description (must explain WHAT and WHEN, max 1024 chars)

Body must include: goal statement, practical code examples, common mistakes, related skill cross-references.

.agent.md Quality Gates

Required frontmatter: name, description, argument-hint, tools, model

Verify: handoffs reference valid agent name values from other agent files.

copilot-instructions.md

Loads on every request — keep it lean. Must have: architecture quick reference, dev commands, agents table, skills table.

Audit Checklists

ARCHITECTURE-FLOW.md
  • Mermaid diagrams render without syntax errors
  • State machines match appState.ts type definitions
  • SSE events match Program.cs Write*Event methods
  • Actions match AppAction type union
README.md
  • Quick start works for new users
  • Commands table is accurate
  • Links to sub-READMEs resolve
Skills & Agents
  • Valid YAML frontmatter on all files
  • SDK versions in examples match *.csproj / package.json
  • Cross-references between skills are valid
Cross-Document Consistency
  • Architecture tables match across all docs
  • Port numbers consistent (5173, 8080)
  • SDK versions match actual dependencies

Review Output Format

For each document reviewed:

Document: path/to/file.md — ✅ Good | ⚠️ Needs Improvement | ❌ Broken

Issues: numbered list with suggested fixes

Cross-Reference Issues: broken links, version mismatches

Content Quality Rules

All documentation must state how things work now, not history or rationale for past changes.

Show full SKILL.md (255 more words)Show less
Must NOT contain
  • Version numbers in prose — reference *.csproj or package.json instead. Hardcoded versions go stale silently.
  • Issue/PR tracker links — these are PR artifacts, not reference docs. Exception: links to external tracking if explicitly requested.
  • Duplicate information — if a fact is stated in one section, don't restate it in another. Cross-reference instead.
  • Narrative or history — "we changed X because Y happened" belongs in commit messages, not docs. State the current behavior.
  • "Fallback" or "automatic" language for mutually exclusive paths — if two modes are mutually exclusive, say so explicitly. Don't imply graceful degradation that doesn't exist.
  • Stale comments — // TODO (if added) when the thing exists, // backward compat without explaining what it's compatible with.
Must contain (for AI agent effectiveness)
  • Non-obvious constraints — things an AI agent would get wrong by reading only the code (e.g., "consent to Azure ML Services, not Cognitive Services")
  • Mutually exclusive choices — state which modes exist and that they don't mix
  • Error signatures — what error an AI agent will see if it does the wrong thing (e.g., AADSTS65001, AADSTS500131)
  • File-to-concept mapping — which file controls which behavior, so agents don't search blindly
Package/SDK version references
  • Tables with versions: remove the version column, point to source of truth
  • Prose references: say "pre-release" or "beta" without specific version numbers
  • If a version matters for API compatibility, state the minimum version and why

Style Rules

  • Code blocks: always include language identifier (```typescript not ```)
  • Links: relative paths for internal, absolute for external
  • Tables: consistent column widths

Constraints

  • ❌ Don't change code (only docs)
  • ❌ Don't invent features not in codebase

© microsoft-foundry, 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/reviewing-documentation of microsoft-foundry/foundry-agent-webapp.

Open the folder on GitHubat commit f6cb362

Compare with similar skills

Reviewing Documentation 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.

Reviewing Documentation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Reviewing Documentation this skillmicrosoft-foundry/foundry-agent-webapp127—~1.1kAutomated safety check: PassMIT
Writing Skillspedronauck/skills6341 repos~919Automated safety check: PassNone
Writing Agents Mdpedronauck/skills6341 repos~769Automated safety check: PassNone
Skill Best Practicesaiskillstore/marketplace430—~3.7kAutomated safety check: PassNone
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Dsh Web Documentationzhu1090093659/dsh-web8.5k—~479Automated safety check: PassApache-2.0

Similar skills

  • Writing Skills

    pedronauck/skills

    Create, refactor, or debug agent skills and their loading. An agent skill from pedronauck/skills.

    634 GitHub starsUsed in 1 repo~919 tokens
    Agent WorkflowsAuto-check passed
  • Writing Agents Md

    pedronauck/skills

    Write or audit AGENTS.md/CLAUDE.md instructions. An agent skill from pedronauck/skills.

    634 GitHub starsUsed in 1 repo~769 tokens
    Agent WorkflowsAuto-check passed
  • Skill Best Practices

    aiskillstore/marketplace

    Guide for creating, structuring, and improving Claude skills (SKILL.md).

    430 GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Dsh Web Documentation

    zhu1090093659/dsh-web

    A skill your agent uses when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.

    8.5k GitHub stars~479 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • ShellLM Skill Author

    laude-institute/headlong

    Scaffolds new ShellLM skills with the right frontmatter, directory layout and agent-facing writing style, so an agent can extend its own capabilities.

    1.2k GitHub stars~1.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from microsoft-foundry/foundry-agent-webapp

All 19 skills in this repo
  • Committing Code

    microsoft-foundry/foundry-agent-webapp

    Provides commit message format and workflow for this repository.

    127 GitHub stars~512 tokensUpdated 5 mo ago
    Auto-check passed
  • Implementing Chat Streaming

    microsoft-foundry/foundry-agent-webapp

    Provides SSE streaming patterns for the chat API and frontend.

    127 GitHub stars~1.9k tokensUpdated 5 mo ago
    Auto-check passed
  • Planning Features

    microsoft-foundry/foundry-agent-webapp

    Provides structured plan template for feature implementation.

    127 GitHub stars~548 tokensUpdated 5 mo ago
    Auto-check passed
  • Researching Azure AI SDK

    microsoft-foundry/foundry-agent-webapp

    Provides research patterns for Foundry Agent Service SDK. An agent skill from microsoft-foundry/foundry-agent-webapp.

    127 GitHub stars~4.7k tokensUpdated 5 mo ago
    Auto-check passed
  • Deploying To Azure

    microsoft-foundry/foundry-agent-webapp

    Provides deployment commands and troubleshooting for Azure Container Apps.

    127 GitHub stars~2.2k tokensUpdated 5 mo ago
    Auto-check: warnings
  • Syncing MCP Servers

    microsoft-foundry/foundry-agent-webapp

    Synchronize MCP server configuration between VS Code (.vscode/mcp.json) and Copilot CLI (~/.copilot/mcp-config.json).

    127 GitHub stars~1.3k tokensUpdated 5 mo ago
    Auto-check passed

Questions about Reviewing Documentation

What does Reviewing Documentation do?

Provides documentation audit checklists and quality standards. Reviewing Documentation is an agent skill from microsoft-foundry/foundry-agent-webapp. Provides documentation audit checklists and quality standards.

When should I use Reviewing Documentation?

Reviewing Documentation fits situations like: reviewing README files; agent definitions; copilot-instructions.md; ARCHITECTURE-FLOW.md for quality and consistency.

How do I install Reviewing Documentation in Claude Code?

Run `npx skills add microsoft-foundry/foundry-agent-webapp --skill reviewing-documentation -a claude-code`. Or copy the skill folder (.github/skills/reviewing-documentation in microsoft-foundry/foundry-agent-webapp) into .claude/skills/reviewing-documentation in your project. Claude Code loads it when a task matches its description.

How do I install Reviewing Documentation in Codex?

Run `npx skills add microsoft-foundry/foundry-agent-webapp --skill reviewing-documentation -a codex`. Or copy the skill folder (.github/skills/reviewing-documentation in microsoft-foundry/foundry-agent-webapp) into .agents/skills/reviewing-documentation in your project. Codex loads it when a task matches its description.

Can I use Reviewing Documentation 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-foundry/foundry-agent-webapp --skill reviewing-documentation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reviewing-documentation, .gemini/skills/reviewing-documentation, .github/skills/reviewing-documentation and .opencode/skills/reviewing-documentation in your project.

What does Reviewing Documentation need to run?

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

Does Reviewing Documentation 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 Reviewing Documentation 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 Reviewing Documentation use?

Reviewing Documentation 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 Reviewing Documentation use?

About 1.1k tokens (SKILL.md is roughly 4.4k 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 Reviewing Documentation?

Skills that share tags, products or a category with Reviewing Documentation: Writing Skills (pedronauck/skills, 634 stars), Writing Agents Md (pedronauck/skills, 634 stars), Skill Best Practices (aiskillstore/marketplace, 430 stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reviewing Documentation?

microsoft-foundry (a GitHub organization) maintains it in microsoft-foundry/foundry-agent-webapp, which has 127 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on April 21, 2026.

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