foundry-agent-sync
Create and synchronize prompt-based AI agents directly within Azure AI Foundry via REST API, from a local JSON manifest. Unlike scaffolding skills that only generate local code, this skill registers agents in the Foundry service itself — making them immediately available for invocation. Use when the user asks to create agents in Foundry, sync, deploy, register, or push agents to Foundry, update agent instructions, or scaffold the manifest and sync script for a new repository. Triggers: 'create agent in foundry', 'sync foundry agents', 'deploy agents to foundry', 'register agents in foundry', 'push agents', 'create foundry agent manifest', 'scaffold agent sync'.
- License 许可
- MIT
- 最近更新
- 2026-08-19
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- foundry-agent-sync
- description
- Create and synchronize prompt-based AI agents directly within Azure AI Foundry via REST API, from a local JSON manifest. Unlike scaffolding skills that only generate local code, this skill registers agents in the Foundry service itself — making them immediately available for invocation. Use when the user asks to create agents in Foundry, sync, deploy, register, or push agents to Foundry, update agent instructions, or scaffold the manifest and sync script for a new repository. Triggers: 'create agent in foundry', 'sync foundry agents', 'deploy agents to foundry', 'register agents in foundry', 'push agents', 'create foundry agent manifest', 'scaffold agent sync'.
03 SKILL.md 正文
Foundry Agent Sync
Overview
Create and synchronize prompt-based AI agents directly within Azure AI Foundry via the Agent Service REST API. This skill registers agents in the Foundry service itself — making them immediately available for invocation, evaluation, and management through the Foundry portal or API. Each agent is created or updated idempotently via a named POST call, using definitions from a local JSON manifest file.
Key distinction: This skill creates agents inside AI Foundry (server-side). It does not scaffold local agent code or container images — for that, use the
microsoft-foundryskill'screatesub-skill.
Prerequisites
The user must have:
- An Azure AI Foundry project with a deployed model (e.g.
gpt-5-4) - Azure CLI (
az) authenticated with access to the Foundry project - The Azure AI User role (or higher) on the Foundry project resource
Collect these values before proceeding:
| Value | How to get it |
|---|---|
| Foundry project endpoint | Azure Portal → AI Foundry project → Overview → Endpoint, or az resource show |
| Subscription ID | az account show --query id -o tsv |
| Model deployment name | The model name deployed in the Foundry project (e.g. gpt-5-4) |
Manifest Format
The manifest is a JSON array where each entry defines one agent. Look for it at common paths: infra/foundry-agents.json, foundry-agents.json, or .foundry/agents.json. If none exists, scaffold one.
[
{
"useCaseId": "alert-triage",
"description": "Short description of what this agent does.",
"baseInstruction": "You are an assistant that... <system prompt for the agent>"
}
]
Field Reference
| Field | Required | Description |
|---|---|---|
useCaseId |
Yes | Kebab-case identifier; used to build the agent name ({prefix}-{useCaseId}) |
description |
Yes | Human-readable description stored as agent metadata |
baseInstruction |
Yes | System prompt / base instructions for the agent |
Sync Script
PowerShell (interactive / CI)
Create or locate the sync script. The canonical path is infra/scripts/sync-foundry-agents.ps1 but adapt to the repo layout.
param(
[Parameter(Mandatory)]
[string]$SubscriptionId,
[Parameter(Mandatory)]
[string]$ProjectEndpoint,
[string]$ManifestPath = (Join-Path $PSScriptRoot '..\foundry-agents.json'),
[string]$ModelName = 'gpt-5-4',
[string]$AgentNamePrefix = 'myproject',
[string]$ApiVersion = '2025-11-15-preview'
)
$ErrorActionPreference = 'Stop'
# Optional: append a common instruction suffix to every agent
$commonSuffix = ''
az account set --subscription $SubscriptionId | Out-Null
$accessToken = az account get-access-token --resource https://ai.azure.com/ --query accessToken -o tsv
if (-not $accessToken) { throw 'Failed to acquire Foundry access token.' }
$definitions = Get-Content -Raw -Path $ManifestPath | ConvertFrom-Json
$headers = @{ Authorization = "Bearer $accessToken" }
$results = @()
foreach ($def in $definitions) {
$agentName = "$AgentNamePrefix-$($def.useCaseId)"
$instructions = if ($commonSuffix) { "$($def.baseInstruction)`n`n$commonSuffix" } else { $def.baseInstruction }
$body = @{
definition = @{ kind = 'prompt'; model = $ModelName; instructions = $instructions }
description = $def.description
metadata = @{ useCaseId = $def.useCaseId; managedBy = 'foundry-agent-sync' }
} | ConvertTo-Json -Depth 8
$uri = "$($ProjectEndpoint.TrimEnd('/'))/agents/$agentName`?api-version=$ApiVersion"
$resp = Invoke-RestMethod -Method Post -Uri $uri -Headers $headers -ContentType 'application/json' -Body $body
$version = $resp.version ?? $resp.latest_version ?? $resp.id ?? 'unknown'
Write-Host "Synced $agentName ($version)"
$results += [pscustomobject]@{ name = $agentName; version = $version }
}
$results | Format-Table -AutoSize
Bash (Bicep deployment script / CI)
For automated deployment via Microsoft.Resources/deploymentScripts, use a bash script that:
- Authenticates with a managed identity:
az login --identity --username "$CLIENT_ID" - Acquires a Foundry token:
az account get-access-token --resource https://ai.azure.com/ - Iterates definitions from the
FOUNDRY_AGENT_DEFINITIONSenvironment variable (JSON string) - POSTs each agent to
{endpoint}/agents/{name}?api-version=2025-11-15-preview
Bicep Integration (optional)
To run the sync automatically during infrastructure deployment:
-
Load the manifest at compile time:
var agentDefinitions = loadJsonContent('foundry-agents.json') -
Create a User-Assigned Managed Identity with the Azure AI User role on the Foundry project.
-
Create a
Microsoft.Resources/deploymentScriptsresource (kindAzureCLI) that:- Uses the managed identity
- Loads the bash sync script via
loadTextContent - Passes the project endpoint, definitions, and model as environment variables
Gate behind a deployFoundryAgents parameter so teams can opt in/out.
Workflow
Step 1 — Locate or scaffold the manifest
Search the repo for foundry-agents.json. If it doesn't exist, ask the user what agents they need and create the manifest.
Step 2 — Locate or scaffold the sync script
Search for sync-foundry-agents.ps1 or foundry-agent-sync.sh. If missing, create the PowerShell script using the template above, adapting:
$AgentNamePrefixto match the project name$ModelNameto the user's deployed model$ManifestPathto the actual manifest location
Step 3 — Collect parameters
Ask the user for:
- Foundry project endpoint
- Subscription ID
- Model deployment name (default:
gpt-5-4) - Agent name prefix (default: repo name in kebab-case)
Step 4 — Run the sync
Execute the PowerShell script with the collected parameters:
.\infra\scripts\sync-foundry-agents.ps1 `
-SubscriptionId '<sub-id>' `
-ProjectEndpoint '<endpoint>' `
-ModelName '<model>' `
-AgentNamePrefix '<prefix>'
Step 5 — Verify
Confirm synced agents by listing them:
$token = az account get-access-token --resource https://ai.azure.com/ --query accessToken -o tsv
$endpoint = '<project-endpoint>'
Invoke-RestMethod -Uri "$endpoint/agents?api-version=2025-11-15-preview" `
-Headers @{ Authorization = "Bearer $token" }
REST API Reference
| Operation | Method | URL |
|---|---|---|
| Create/update agent | POST | {projectEndpoint}/agents/{agentName}?api-version=2025-11-15-preview |
| List agents | GET | {projectEndpoint}/agents?api-version=2025-11-15-preview |
| Get agent | GET | {projectEndpoint}/agents/{agentName}?api-version=2025-11-15-preview |
| Delete agent | DELETE | {projectEndpoint}/agents/{agentName}?api-version=2025-11-15-preview |
Create/Update Payload
{
"definition": {
"kind": "prompt",
"model": "<deployed-model-name>",
"instructions": "<system prompt>"
},
"description": "<agent description>",
"metadata": {
"useCaseId": "<use-case-id>",
"managedBy": "foundry-agent-sync"
}
}
Troubleshooting
| Symptom | Cause | Fix |
|---|---|---|
401 Unauthorized |
Token expired or wrong audience | Re-run az account get-access-token --resource https://ai.azure.com/ |
403 Forbidden |
Missing Azure AI User role | Assign the role on the Foundry project scope |
404 Not Found |
Wrong project endpoint | Verify endpoint includes /api/projects/{projectName} |
| Model not found | Model not deployed in project | Deploy the model in AI Foundry portal first |
| Empty definitions | Manifest path wrong | Check -ManifestPath points to the JSON file |
04 同仓库更多 Skills
youtube-transcript
Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar). Supports output with or without timestamps.
youtube-thumbnail-design
YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image
youtube-short-maker
Make YouTube Shorts that hold attention with Pexo — vertical 9:16, fast-paced, hook in the first 3 seconds. Describe your topic and Pexo writes the script, generates the shots, picks the models, and assembles a finished Short with music and captions. Use for YouTube Shorts: "youtube short", "make a youtube short", "shorts video", "short-form video". NOT for long-form or landscape video.
xcode-project-setup
Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing touches your codebase) or "build it in" (install the SDK and write the key + code into your project). Walks through wallet setup, funding, .env, and a ~$1 test run. Use when the user asks about x402, pay-per-use, USDC payments, or wants Browser Use Cloud without an API key. For the free-tier signup (reverse-CAPTCHA → API key), use `browser-use cloud signup` or the `cloud` skill instead.
x-twitter-scraper
Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, hosted Apify Actor runs, MCP tools, TweetClaw OpenClaw plugin installs, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.