Create azure agent
Skill richfrem/agent-plugins-skills/plugins/agent-scaffolders/skills/create-azure-agent
Deploys a skill as an Azure AI Foundry hosted agent. NOT for Docker runtime skills (use `create-docker-skill`) and NOT for MCP server integrations (use `create-mcp-integration`).From its SKILL.md
npx -y skills add richfrem/agent-plugins-skills --skill create-azure-agentAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.6 KB, 303 tokens by cl100k_base, as published. Nobody here has run it
Follow the create-azure-agent skill workflow to generate Azure AI Foundry deployment
wrappers for an existing agent skill.
Inputs
$ARGUMENTS— optional path to the skill directory to deploy. Omit to start with discovery.
Steps
- If
$ARGUMENTSprovides a skill directory, resolve and validate the path - Follow the create-azure-agent phased workflow: confirm the target skill, gather Azure
configuration (subscription, resource group, region, naming preferences), then run
scaffold_azure_agent.pyto generate Bicep templates and the Python Azure AI Projects SDK deployment wrapper - Summarize generated files in the skill's
azure_deployment/directory - Instruct on reviewing
.bicepparameters and runningaz deployment group create
Output
azure_deployment/azure_agent.py (Azure AI Projects SDK orchestration script) and
azure_deployment/main.bicep (Cosmos DB, AI Search, and Foundry Project infrastructure).
Edge Cases
- If
$ARGUMENTSis empty: ask for the target skill directory before proceeding - If Azure credentials are not configured: instruct user to run
az loginfirst - Azure AI Foundry enforces a 128-tool limit — scaffold generates a focused worker agent
- Offer to run
/agent-scaffolders:audit-pluginto validate the skill before deploying
What ships with it: 81 files
7.6 KB alongside SKILL.md, 8 of them executable
evals/
- evals.json883 B
- results.tsv417 B
references/
- acceptance-criteria.md42 B
- fallback-tree.md36 B
- hitl-interaction-design.md46 B
- pattern-decision-matrix.md46 B
- patterns/action-forcing-output-with-deadline-attribution.md82 B
- patterns/adversarial-objectivity-constraint.md69 B
- patterns/anti-pattern-vaccination.md59 B
- patterns/anti-symptom-triage.md54 B
- patterns/artifact-embedded-execution-audit-trail.md74 B
- patterns/artifact-generation-xss-compliance-gate.md74 B
- patterns/artifact-lifecycle.md53 B
- patterns/artifact-state-interrogative-routing.md71 B
- patterns/asynchronous-benchmark-metric-capture.md72 B
- patterns/audience-segmented-information-filtering.md75 B
- patterns/category-calibrated-benchmark-anchoring.md74 B
- patterns/category-semantic-deferred-tool-binding.md74 B
- patterns/chained-command-invocation.md61 B
- patterns/chained-commands.md51 B
- patterns/client-side-compute-sandbox-constraint.md73 B
- patterns/complexity-tiered-output.md59 B
- patterns/conditional-step-inclusion.md61 B
- patterns/connector-placeholders.md57 B
- patterns/cyclical-state-propagation-contract.md70 B
- patterns/delegated-constraint-verification-loop.md73 B
- patterns/dual-mode-degradation.md56 B
- patterns/dual-mode-meta-skill.md55 B
- patterns/dual-register-communication-enforcement.md74 B
- patterns/dynamic-specification-fetching.md65 B
- patterns/embedded-deterministic-scoring-formula.md73 B
- patterns/escalation-taxonomy.md54 B
- patterns/explicit-seed-anchored-determinism.md69 B
- patterns/graduated-autonomy.md53 B
- patterns/graduated-source-attributed-elicitation.md74 B
- patterns/highly-procedural-fallback-trees.md67 B
- patterns/iteration-directory-isolation.md64 B
- patterns/lifecycle-aware-knowledge.md60 B
- acceptance-criteria.md385 B
- fallback-tree.md1.4 KB
41 more files not listed here. See all 81 in the repository.
Gives 0 of the 12 instructions most mcp tooling skills give in 303 tokens
Counted across 638 of the 750 authors here whose files we hold, read 2026-08-07
- Create ten complex or independent read-only evaluation questionsin 69 of 638, across 15 files
- Test servers using MCP Inspectorin 61 of 638, across 19 files
- Provide actionable error messages with specific next stepsin 54 of 638, across 12 files
- Prioritize comprehensive API coverage over specific workflows or workflow toolsin 54 of 638, across 12 files
- Use TypeScript and Streamable HTTP for remote servers or clientsin 54 of 638, across 8 files
- Define structured output schemas where possiblein 50 of 638, across 8 files
- Use Zod or Pydantic for input schemasin 47 of 638, across 5 files
- Fetch MCP specification pages with markdown suffixin 46 of 638, across 4 files
- Load framework documentation using WebFetchin 45 of 638, across 3 files
- Verify each evaluation answer independentlyin 45 of 638, across 3 files
- Implement API client with authentication and paginationin 45 of 638, across 3 files
- Define input schemas with validationin 27 of 638, across 9 files
Said here and by no other author read
- validate the provided skill directory path
- ask for a skill directory if arguments are empty
- gather Azure configuration from the user
- run scaffold_azure_agent.py
- summarize the generated files
- instruct on reviewing bicep parameters
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.