SKILLEMALL.ai
GitHub ↗ RU Sign in

CF microsoft-foundry

Expert knowledge for Microsoft Foundry (aka Azure AI Foundry) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents with Azure OpenAI, AI Gateway, Entra RBAC, BYO VNet networking, or MCP/voice integrations, and other Microsoft Foundry related development tasks. Not for Content Safety in Foundry Control Plane (use azure-content-safety), Azure Content Understanding in Foundry Tools (use azure-content-understanding), Azure Speech in Foundry Tools (use azure-speech), Microsoft Foundry Classic (use microsoft-foundry-classic).

MicrosoftDocs/Agent-Skills Agent Skills author: MicrosoftDocs CC-BY-4.0 1 file body ≈ 13 765 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Expert knowledge for Microsoft Foundry (aka Azure AI Foundry) development including troubleshooting, best practices, decision making, architecture & design…

As a process F 32/100 · No process to follow — References files that are not bundled: security.md

IntegrationAzureGitHubInfrastructuretype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
85/100
safety, quality, tests
Safety 60%
98
Quality 40%
65
Run on models
none yet
Process rating
F
32/100
No process to follow
References files that are not bundled: security.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 2

✓ No critical or high findings

Medium and low: 2
  • low Risky intent intent-offensive-security SKILL.md:357
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Run AI Red Teaming Agent scans locally | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/run-scans-ai-red-teaming-agent |
  • low Risky intent intent-offensive-security SKILL.md:422
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Run AI Red Teaming Agent scans in cloud | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/run-ai-red-teaming-cloud |

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 13765 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: security.md

Process rating: all ten parameters 32/100

Will not run. References files that are not bundled: security.md
  • 0Tools and files. 1 referenced file(s) missing: security.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 78 mutating operations with no state check
  • 40Execution cost. Instruction body is 13765 tokens: crowds the task out of the window
  • 50Steps. 2 steps
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 699: enough signal without eating the budget
  • +4Structure: 12 headings

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.