New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Update Guidelines

by Azure in Azure/azure-sdk-tools

Ingest guideline changes from the azure-sdk repo into the knowledge base.

OfficialMITAuto-check passedKnowledge Management

Install Update Guidelines

skills CLI
$ npx skills add Azure/azure-sdk-tools --skill update-guidelines -a claude-code

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

GitHub CLI
$ gh skill install Azure/azure-sdk-tools update-guidelines --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/Azure/azure-sdk-tools.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/python-packages/apiview-copilot/.github/skills/update-guidelines .claude/skills/update-guidelines && 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
update-guidelines
GitHub stars
134
Token cost
~1.9k tokens
SKILL.md length
856 words
Files
1
Skills in repo
35
Repo updated
First seen
Licence
MIT

At a glance

Ingest guideline changes from the azure-sdk repo into the knowledge base.

  • Works in 2 steps: Dry Run → Apply
  • : update guidelines
  • SKILL.md covers When to Use, Overview, Environment and Language Filter, plus 6 more sections
  • Calls python; reaches api.github.com and github.com

What it does

Update Guidelines is an agent skill from Azure/azure-sdk-tools, published by the product's own GitHub organization. Ingest guideline changes from the azure-sdk repo into the knowledge base. Use for: update guidelines, ingest guidelines, sync guidelines, guideline changes, kb update, update KB, guideline ingestion, sync KB, guideline PR, guideline diff.

Its SKILL.md is about 1.9k 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 Knowledge Management, covering Knowledge bases. It works with Microsoft Azure, Azure Cosmos DB and GitHub. The repository describes itself as: Tools repository leveraged by the Azure SDK team. The licence is MIT.

When your agent uses it

  • : update guidelines
  • Ingest guidelines
  • Sync guidelines
  • Guideline changes

Example prompts

  • “/update-guidelines”

Requirements

  • Python 3

Workflow steps

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

  1. Dry Run
  2. Apply

What it can do on your machine

Read from SKILL.md and the folder at commit 69f4006. 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

    Shell commands in SKILL.md call:

    • python

    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:

    • api.github.com
    • github.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.

Context cost

Update Guidelines loads about 1.9k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 856 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 Azure/azure-sdk-tools at commit 69f4006, republished under its MIT licence (© Azure). 856 words, ~1,872 tokens.

Download SKILL.mdSave it as .claude/skills/update-guidelines/SKILL.md (or your agent's skills folder).
name
update-guidelines
description
Ingest guideline changes from the azure-sdk repo into the knowledge base. Use for: update guidelines, ingest guidelines, sync guidelines, guideline changes, kb update, update KB, guideline ingestion, sync KB, guideline PR, guideline diff.
argument-hint
PR link, two SHAs, or two dates (e.g. 'PR #1234', 'abc123..def456', 'April 1 to April 30')

Update Guidelines

When to Use

  • Syncing guideline changes from the Azure/azure-sdk repo into the Copilot knowledge base
  • Ingesting a specific PR's guideline changes
  • Syncing guideline changes between two dates or two commit SHAs

Overview

The avc db ingest-guidelines command detects changes in the azure-sdk repo's guideline markdown files and syncs them to Cosmos DB. It compares a base SHA against a target SHA to find changed files, parses them, and upserts/deletes guidelines, examples, and memories accordingly.

This skill supports three input scenarios for resolving the base and target SHAs:

  1. PR link — Extract SHAs from a GitHub pull request
  2. Explicit SHAs — Use the SHAs directly
  3. Date range — Find the closest commits on main to the given dates

IMPORTANT: Always run a dry-run first and confirm with the user before applying changes.

Environment

The user MUST specify which environment to update: staging or production. If not specified, ask the user — do NOT assume. This determines which Cosmos DB and App Configuration instance is modified.

Always pass --environment <env> to the CLI commands.

Language Filter

The user may optionally specify one or more languages to narrow the ingestion scope. If languages are specified, only guideline files for those languages (plus cross-language "general" guidelines) are processed.

Pass --language <lang1> <lang2> (or -l <lang1> <lang2>) to the CLI commands. Valid language names: python, java, dotnet, typescript, golang, cpp, rust, ios, android, clang. Case-insensitive aliases like C#, Go, Swift are also accepted.

If the user does not mention specific languages, omit the flag to process all languages.

The user provides a GitHub PR link (e.g. https://github.com/Azure/azure-sdk/pull/1234).

Step 1a: Extract the PR number

Parse the PR number from the URL.

Step 1b: Fetch PR details from GitHub API

Run this command to get the base and merge commit SHAs:

powershell
Invoke-RestMethod -Uri "https://api.github.com/repos/Azure/azure-sdk/pulls/<PR_NUMBER>" -Headers @{ "User-Agent" = "apiview-copilot" } | Select-Object -Property @{N='base_sha';E={$_.base.sha}}, @{N='merge_commit_sha';E={$_.merge_commit_sha}}, @{N='title';E={$_.title}}, @{N='state';E={$_.state}}, @{N='merged';E={$_.merged}} | Format-List
  • Use base.sha as the base SHA
  • Use merge_commit_sha as the target SHA
  • If merged is false, warn the user that the PR is not merged and the merge commit SHA may change
Step 1c: Confirm with user

Show the user:

  • PR title and state
  • Base SHA (first 8 chars)
  • Target SHA (first 8 chars)
  • Environment (staging or production)

Ask for confirmation before proceeding.

Then go to Phase 2: Dry Run.

Scenario 2: Explicit SHAs

The user provides two commit SHAs directly.

Confirm with the user:

  • Base SHA (first 8 chars)
  • Target SHA (first 8 chars)
  • Environment (staging or production)

Then go to Phase 2: Dry Run.

Scenario 3: Date Range

The user provides two dates (e.g. "April 1 to April 30", "March 15 and March 20").

Step 3a: Resolve dates to SHAs

For each date, find the closest commit on main of the Azure/azure-sdk repo.

Use the GitHub Commits API with the until parameter to find the most recent commit on or before the given date:

For the base date:

powershell
(Invoke-RestMethod -Uri "https://api.github.com/repos/Azure/azure-sdk/commits?sha=main&until=<BASE_DATE>T23:59:59Z&per_page=1" -Headers @{ "User-Agent" = "apiview-copilot" })[0] | Select-Object -Property @{N='sha';E={$_.sha}}, @{N='date';E={$_.commit.committer.date}}, @{N='message';E={$_.commit.message.Split("`n")[0]}} | Format-List

For the target date:

powershell
(Invoke-RestMethod -Uri "https://api.github.com/repos/Azure/azure-sdk/commits?sha=main&until=<TARGET_DATE>T23:59:59Z&per_page=1" -Headers @{ "User-Agent" = "apiview-copilot" })[0] | Select-Object -Property @{N='sha';E={$_.sha}}, @{N='date';E={$_.commit.committer.date}}, @{N='message';E={$_.commit.message.Split("`n")[0]}} | Format-List

Replace <BASE_DATE> and <TARGET_DATE> with ISO dates (e.g. 2025-04-15).

Show full SKILL.md (374 more words)Show less
Step 3b: Confirm with user

The resolved commit dates may not exactly match the user's requested dates. Always show the user what was resolved and ask for confirmation, especially if the commit date differs from the requested date by more than a day.

Show:

  • Requested base date → Resolved commit date and SHA (first 8 chars) and commit message
  • Requested target date → Resolved commit date and SHA (first 8 chars) and commit message
  • Environment (staging or production)

Ask: "These are the closest commits to your requested dates. Proceed with dry run?"

Then go to Phase 2: Dry Run.

Phase 2: Dry Run

Always run a dry-run first. Use a 300-second timeout (the command can be slow due to LLM enrichment).

powershell
python cli.py db ingest-guidelines --environment <ENV> --base-sha <BASE_SHA> --target-sha <TARGET_SHA> --details [--language <LANG1> <LANG2>]

Include --language flags only if the user specified languages to filter.

Interpreting results

Read the terminal output. The command prints:

  • Guidelines: N to create, N to update, N to delete, N unchanged
  • Examples: N to create, N to update, N to delete, N unchanged
  • Memories: N to absorb, N to retain
  • Errors: any errors encountered

With --details, the JSON output includes before/after content for each change.

Present to user

Summarize what the dry run found:

  • How many guidelines will be created/updated/deleted
  • How many examples will be created/updated/deleted
  • How many memories will be absorbed
  • Any errors
  • Remind them which environment this targets

Ask: "Ready to apply these changes to {environment}?"

Phase 3: Apply

Only after the user confirms the dry-run results, run the actual ingestion:

powershell
python cli.py db ingest-guidelines --environment <ENV> --base-sha <BASE_SHA> --target-sha <TARGET_SHA> --apply [--language <LANG1> <LANG2>]

Use a 300-second timeout. Include the same --language flags used in the dry run.

After completion, report the final counts to the user.

Gotchas

  • Always dry-run first. Never skip the dry run. The ingestion modifies Cosmos DB and App Configuration.
  • Environment matters. Staging and production have separate Cosmos DB instances. Double-check with the user.
  • Large diffs are slow. If many files changed, the LLM enrichment step can take several minutes. Use --details only on dry runs to inspect changes; omit it on the real run to save time.
  • Language filter. Use --language to scope to specific languages when debugging or testing. The filter also includes cross-language ("general") guidelines automatically.
  • Merged PRs only. If a PR is not yet merged, the merge commit SHA is provisional and may change. Warn the user.

© Azure, 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 packages/python-packages/apiview-copilot/.github/skills/update-guidelines of Azure/azure-sdk-tools.

Open the folder on GitHubat commit 69f4006

Compare with similar skills

Update Guidelines 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.

Update Guidelines compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Update Guidelines this skillAzure/azure-sdk-tools134—~1.9kAutomated safety check: PassMIT
Code Reviewlangchain-ai/langchain-azure147—~2.3kAutomated safety check: PassMIT
Datachain Knowledgedatachain-ai/datachain2.8k—~3kAutomated safety check: PassApache-2.0
Knowledge Opsaffaan-m/ECC274k2 repos~1.7kAutomated safety check: PassMIT
Copilot Spacesgithub/awesome-copilot40k1 repos~2.2kAutomated safety check: PassMIT
Foundry Iqmicrosoft/GitHub-Copilot-for-Azure255—~872Automated safety check: PassMIT

Similar skills

  • Code Review

    langchain-ai/langchain-azure

    Official

    Reviews changes in the langchain-azure monorepo using package-specific knowledge of langchain-azure-ai, langchain-azure-compute, langchain-azure-cosmosdb, langchain-azure-postgresql…

    147 GitHub stars~2.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Datachain Knowledge

    datachain-ai/datachain

    A skill your agent uses whenever datasets, cloud storage buckets, or data pipelines are mentioned — creating, saving, querying, listing, exploring, deleting, or processing data in S3, GCS, Azure…

    2.8k GitHub stars~3k tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Knowledge Ops

    affaan-m/ECC

    Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos).

    274k GitHub starsUsed in 2 repos~1.7k tokens
    Knowledge ManagementAuto-check passed

  • Copilot Spaces

    github/awesome-copilot

    Official

    Use Copilot Spaces to provide project-specific context to conversations.

    40k GitHub starsUsed in 1 repo~2.2k tokens
    Knowledge ManagementAuto-check passed

  • Foundry Iq

    microsoft/GitHub-Copilot-for-Azure

    Official

    Foundry IQ knowledge bases. An agent skill from microsoft/GitHub-Copilot-for-Azure.

    255 GitHub stars~872 tokensUpdated today
    Knowledge ManagementAuto-check passed

  • GitHub Kb

    sundial-org/awesome-openclaw-skills

    Manage a local GitHub knowledge base and provide GitHub search capabilities via gh CLI.

    663 GitHub stars~1.2k tokensUpdated 7 mo ago
    Knowledge ManagementAuto-check passed

More from Azure/azure-sdk-tools

All 35 skills in this repo

  • Apiview Feedback Resolution

    Azure/azure-sdk-tools

    Official

    Analyze and resolve APIView review feedback on Azure SDK PRs.

    134 GitHub stars~547 tokensUpdated today
    Auto-check passed

  • Azsdk Common Live And Recorded Tests

    Azure/azure-sdk-tools

    Official

    Deploy test resources and run Azure SDK tests in live, record, or playback mode.

    134 GitHub stars~1.5k tokensUpdated today
    Auto-check: notes

  • Azsdk Common Pipeline Analysis

    Azure/azure-sdk-tools

    Official

    Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format.

    134 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Azsdk Common Prepare Release Plan

    Azure/azure-sdk-tools

    Official

    Create, get, update, abandon, and link SDK PRs to release plan work items for Azure SDK releases.

    134 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Azure Typespec Assessment

    Azure/azure-sdk-tools

    Official

    Assess Azure TypeSpec Git diffs for semantic intent, REST and downstream SDK breaking changes, Azure Guidelines compliance, and documentation completeness.

    134 GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Update Guidelines

What does Update Guidelines do?

Ingest guideline changes from the azure-sdk repo into the knowledge base. Update Guidelines is an agent skill from Azure/azure-sdk-tools, published by the product's own GitHub organization. Ingest guideline changes from the azure-sdk repo into the knowledge base.

When should I use Update Guidelines?

Update Guidelines fits situations like: : update guidelines; ingest guidelines; sync guidelines; guideline changes.

How do I install Update Guidelines in Claude Code?

Run `npx skills add Azure/azure-sdk-tools --skill update-guidelines -a claude-code`. Or copy the skill folder (packages/python-packages/apiview-copilot/.github/skills/update-guidelines in Azure/azure-sdk-tools) into .claude/skills/update-guidelines in your project. Claude Code loads it when a task matches its description.

How do I install Update Guidelines in Codex?

Run `npx skills add Azure/azure-sdk-tools --skill update-guidelines -a codex`. Or copy the skill folder (packages/python-packages/apiview-copilot/.github/skills/update-guidelines in Azure/azure-sdk-tools) into .agents/skills/update-guidelines in your project. Codex loads it when a task matches its description.

Can I use Update Guidelines 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 Azure/azure-sdk-tools --skill update-guidelines -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/update-guidelines, .gemini/skills/update-guidelines, .github/skills/update-guidelines and .opencode/skills/update-guidelines in your project.

What does Update Guidelines need to run?

Going by SKILL.md and its folder, Update Guidelines needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Update Guidelines access the network?

SKILL.md names 2 domains. In commands or code: api.github.com and github.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Update Guidelines 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 Update Guidelines use?

Update Guidelines 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 Update Guidelines use?

About 1.9k tokens (SKILL.md is roughly 7.5k 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 Update Guidelines?

Skills that share tags, products or a category with Update Guidelines: Code Review (langchain-ai/langchain-azure, 147 stars), Datachain Knowledge (datachain-ai/datachain, 2.8k stars), Knowledge Ops (affaan-m/ECC, 274k stars) and Copilot Spaces (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Update Guidelines?

Azure (a GitHub organization, an official publisher) maintains it in Azure/azure-sdk-tools, which has 134 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 6, 2026.

Source: Azure/azure-sdk-tools on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.