Foundry Iq

MicrosoftOfficialCreated by Microsoft

Skill
Workflow
Data and AI
MIT
Medium risk
Has scripts

From the author

Foundry IQ knowledge bases. WHEN: make local or Blob documents searchable; create/diagnose KBs; triage unsupported connectors or multi-source KB creation/reconfiguration (even with classic-search terms); connect existing KB to agents (including multi-source KBs); create/reuse a Search service; retrieve from an existing knowledge base with citations; no brand words needed. Read its procedure before query/target questions. NOT: other KB providers, repository-file search, classic Azure AI Search index/query/app work with no Foundry IQ KB or connector request, generic agent creation.

— the description by Microsoft

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

Foundry IQ provides a structured framework for creating, diagnosing, and connecting knowledge bases to AI agents. It supports making local or Blob-based documents searchable, managing multi-source knowledge configurations, and retrieving information with citations. The skill emphasizes strict adherence to defined procedures for service discovery, resource creation, and troubleshooting to ensure reliable agent-knowledge integration.

What it does

Creates searchable knowledge bases from local or Azure Blob storage documents.
Connects existing knowledge bases to AI agents.
Diagnoses issues with knowledge base configurations or unsupported connectors.
Retrieves information from knowledge bases with source citations.
Manages the lifecycle of search services and knowledge sources.
Routes requests based on specific operational needs rather than source counts.

When to use it

When you need to make local or cloud-stored documents searchable by an AI agent.
When connecting an existing knowledge base to a new or current agent.
When troubleshooting or diagnosing a knowledge base configuration.
When you need to create a new search service or knowledge source.
When performing retrieval tasks that require citations from a knowledge base.

Advantages

Provides a clear, procedural approach to knowledge base management.
Ensures consistent handling of multi-source knowledge configurations.
Includes built-in diagnostic paths for troubleshooting.
Supports secure, citation-backed retrieval for agent responses.
Prevents unauthorized or unsupported configuration changes.

Usage examples

“Create a new knowledge base from my Azure Blob container.”: The agent will initiate the knowledge base creation procedure, validating the source and setting up the necessary search indexing.
“Connect my existing knowledge base to the current agent.”: The agent will follow the connection workflow to link the specified knowledge base to the agent's retrieval pipeline.
“Why is my multi-source knowledge base failing to index?”: The agent will trigger the diagnostic procedure to identify configuration drifts or unsupported connector issues.
“Retrieve information about project timelines from the knowledge base.”: The agent will query the knowledge base and provide an answer with citations from the source documents.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/microsoft/foundry-iq/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip foundry-iq.zip -d .agents/skills

Documentation by Microsoft

Foundry IQ

Read one procedure before questions/actions; invocation is not a read. Read the owning procedure before blocked/unsupported responses too. Before mutation plans/approval, successfully read its required pre-action references, selected branches only. Do not reload successful reads. On failure, try only permitted bounded exact-path reads with any supported reader; never bypass restrictions or search broadly. If still unavailable: blocked: reference-unavailable, name missing references and inability to plan. Never invent requirements/plans. Failures first.

Cleanup and receipt-backed execution go directly to their lifecycle/producer owner; do not reopen Search intake, provisioning or hardening.

Before expensive service discovery, reuse supplied resource/intent; otherwise ask one early USE EXISTING / FIND CANDIDATES / CREATE NEW choice. Only FIND enumerates; supplied identity uses exact/minimum scoped resolution. CREATE checks its proposed name, not existing-service inventories. Preserve these answers across source/KB/CU/model handoffs; selection is not write approval.

Searchable docs: KB + validated retrieval. Confirm intent once; KS-only must be explicit. Child success is not KB completion. Unclear/compound/mode/completion: read.

Route by requested operation, not existing KB source count. Connecting an existing KB with two or more sources, without changing the KB, uses Connect. Read-only operations use their owning procedure and actual helper constraints; this does not add retrieval modes or supported source kinds. Explicit unsupported provisioning or multi-source KB creation/reconfiguration uses Diagnose and stops before discovery, even when connecting an agent is also requested. This routing takes precedence over classic-search terms (e.g. hybrid search) in compound requests. Never end in a plain refusal: Diagnose gives the boundary, docs pointer and agent handoff; writes still need an approved concrete plan. Do not silently execute only the supported part of a compound request. If existing-KB connection versus KB creation/reconfiguration is unclear, read intent-routing and clarify that scope before Azure discovery. Never infer KB mutation.

Outcome	Read
Cleanup	Plan cleanup
Failure/drift	Diagnose
Unsupported connector provisioning / multi-source KB creation or reconfiguration	Diagnose
Connect	Connect
Read KB	Query
Search only	Search
File KS only	File
Blob/ADLS KS only	Blob
Searchable/KB	KB

Generic agents: microsoft-foundry. Reads: no approval; approve unchanged plans before writes. Hide hashes. No Search/Storage keys, scope widening, guessed identity/boundaries, drift repair or joint cleanup/creation approval. Acceptance != success.

Files

ATTRIBUTION.mdAdded by AutoGineer977 B
LICENSELicence file added by AutoGineer1.1 KiB
SKILL.md3.7 KiB
agents/connect-hosted-toolbox.md7.8 KiB
agents/connect-hosted.md7.8 KiB
agents/connect-prompt-sdk-fallback.md7.8 KiB
agents/connect.md7.8 KiB
agents/create-missing-agent.md7.8 KiB
helpers/_blob_observation.pyScript4.4 KiB
helpers/_blob_source_read.pyScript39.5 KiB
helpers/_bootstrap_io.pyScript30.1 KiB
helpers/_cleanup_dependencies.pyScript27.5 KiB
helpers/_cleanup_receipts.pyScript13.5 KiB
helpers/_common.pyScript36.2 KiB
helpers/_document_adapters.pyScript15.0 KiB
helpers/_document_limits.pyScript3.9 KiB
helpers/_embedding.pyScript7.0 KiB
helpers/_file_inventory.pyScript24.4 KiB
helpers/_file_source_config.pyScript15.6 KiB
helpers/_indexer_observation.pyScript7.1 KiB
helpers/_initial_prompt.pyScript12.5 KiB
helpers/_private_json.pyScript2.4 KiB
helpers/_progress.pyScript12.1 KiB
helpers/_prompt_read.pyScript17.7 KiB
helpers/_search_read.pyScript6.0 KiB
helpers/_source_readback.pyScript1.6 KiB
helpers/blob-contracts.md7.8 KiB
helpers/blob-cu-contracts.md7.8 KiB
helpers/blob_inventory.pyScript17.1 KiB
helpers/blob_recheck.pyScript64.6 KiB
helpers/blob_source.pyScript35.8 KiB
helpers/bootstrap-contracts.md7.8 KiB
helpers/bootstrap_azure.pyScript41.5 KiB
helpers/cleanup_plan.pyScript41.4 KiB
helpers/contracts.md7.8 KiB
helpers/cu_ingestion_auth.pyScript12.5 KiB
helpers/document-assessment.md7.8 KiB
helpers/document_assess.pyScript14.0 KiB
helpers/file-upload-recovery.md7.8 KiB
helpers/file_cu_canary.pyScript32.7 KiB
helpers/file_cu_mi.pyScript9.6 KiB
helpers/file_ingest.pyScript15.4 KiB
helpers/file_source.pyScript31.7 KiB
helpers/file_upload.pyScript53.7 KiB
helpers/hosted_connect.pyScript30.8 KiB
helpers/kb-contracts.md7.8 KiB
helpers/knowledge_base_retrieve.pyScript7.7 KiB
helpers/model-discovery-contracts.md7.8 KiB
helpers/model-discovery-scopes.md7.8 KiB
helpers/model_discovery.pyScript23.7 KiB
helpers/private-artifacts.md7.2 KiB
helpers/private_artifacts.pyScript4.8 KiB
helpers/prompt_cleanup.pyScript22.0 KiB
helpers/prompt_connect.pyScript62.3 KiB
helpers/requirements-assessment.txt103 B
helpers/retrieval-verification-contracts.md7.8 KiB
helpers/retrieval_verify.pyScript19.6 KiB
helpers/search-intake-contracts.md7.6 KiB
helpers/search_intake.pyScript18.4 KiB
helpers/search_reconcile.pyScript59.7 KiB
helpers/source_vector.pyScript33.2 KiB
helpers/throttle-recovery.md5.0 KiB
helpers/vector-contracts.md7.8 KiB
knowledge-bases/create.md8.1 KiB
knowledge-bases/retrieve.md7.8 KiB
knowledge-sources/create-azure-blob.md7.8 KiB
knowledge-sources/create-file.md7.8 KiB
lifecycle/cleanup.md7.8 KiB
references/abstention.md1.0 KiB
references/blob-binding-evidence.md7.8 KiB
references/blob-indexer-observation.md7.7 KiB
references/blob-ingestion-progress.md6.5 KiB
references/blob-readiness-recheck.md7.8 KiB
references/blob-vector-readiness.md2.6 KiB
references/bootstrap-azure.md7.8 KiB
references/content-fit.md7.8 KiB
references/cu-ingestion.md7.8 KiB
references/file-cu-canary.md7.8 KiB
references/intent-routing.md7.7 KiB
references/owner.md2.1 KiB
references/platform-contracts.md7.7 KiB
references/platform-interfaces.md7.8 KiB
references/resource-intake.md7.8 KiB
references/search-substrate.md7.8 KiB
references/standard-cu.md7.8 KiB
search-services/create.md7.8 KiB
troubleshooting/diagnose.md8.7 KiB

references/platform-interfaces.md

Interfaces and versions

Operation	Contract
Search substrate management	management API `2025-05-01`
Resource group prerequisite	ARM `2022-09-01`
AI account	ARM `2025-06-01`; File CU GET/listKeys `2024-10-01`
Search data plane	Entra audience `https://search.azure.com/.default`
File knowledge source and file operations	`2026-08-01-preview`
Blob knowledge source	GA `2026-04-01`; preview for selected preview features
ADLS Gen2 knowledge source	This helper uses `2026-08-01-preview`
Existing Blob validation	Entra audience `https://storage.azure.com/.default`; Blob `x-ms-version: 2025-11-05`
Existing Prompt Agent connection	authenticated Foundry MCP preferred; `azure-ai-projects>=2.4.0,<3` typed fallback; Agent API `v1`; project-connection ARM API `2025-10-01-preview`; KB MCP endpoint `2026-08-01-preview`
Existing Hosted Agent connection	GET-only toolbox assessment; source-backed azd recipe; `AgenticIdentityToken`; KB MCP `2026-08-01-preview`

Execution surfaces:

Workflow	Surface
Missing group/Search/models/RBAC	Conditional `references/bootstrap-azure.md`: native Azure CLI/ARM; no host fixture
File read-only plan / approved source plus upload	`helpers/file_source.py --plan request.json` / `--input approved-envelope.json`
Blob/ADLS read-only plan / approved application	`helpers/blob_source.py --plan intent.json` / `--input approved.json`
Source vector verification plan / separately approved query	`helpers/source_vector.py --plan verify.json` / `--input approved-query.json`; contract
Knowledge-base reconciliation / source or KB cleanup	`helpers/search_reconcile.py`
Existing Prompt fallback connect/delete	`helpers/prompt_connect.py` / `helpers/prompt_cleanup.py`
Hosted assessment / source-backed connection	`helpers/hosted_connect.py --plan intent.json` / `agents/connect-hosted.md`

Receipts preserve the first nonempty case-insensitive value for x-ms-request-id or Azure Search's request-id, preferring the former when both are present. Client-generated/echoed request IDs are not server provenance; missing server IDs remain missing.

Standalone retrieval uses Entra-authenticated Search REST: GET /knowledgebases('<escaped-name>')?api-version=<version>, then POST /knowledgebases/<name>/retrieve?api-version=<version>. GA and preview minimal use intents; preview low/medium can use messages. Read the selected definition and preserve its API/mode/effort. See Retrieve for request construction, permission forwarding and response verification. No MCP connection is required.

Prompt/Hosted Agent connections still use the exact KB's native MCP endpoint (/knowledgebases/<knowledge-base>/mcp?api-version=<api-version>) and knowledge_base_retrieve. REST retrieval is not proof of agent tool use. Neither path substitutes the generic Azure MCP Server search_* group or an index query. Preserve first errors; never persist tokens or use Search/Storage keys.

Hosted connection readback

An azd projection may omit audience; a typed MCP reader may return UnknownConnectionPropertiesV2 for AgenticIdentityToken. For those schema gaps, read the observed Microsoft.CognitiveServices/accounts/projects/connections resource ID without fetching credentials:

az resource show --ids <exact-connection-resource-id> --api-version 2025-10-01-preview --query "{id:id,category:properties.category,authType:properties.authType,target:properties.target,audience:properties.audience}" --output json

Require the approved ID, RemoteTool, AgenticIdentityToken, KB MCP target and https://search.azure.com/ audience. Compare other protected fields when needed. Never use --show-credentials, keys or secret endpoints. This supported ARM GET is diagnostic readback, not an alternative mutation surface or an authorization bypass. Denial, mismatch or missing required fields still blocks.

API selection

Request	Service availability and helper choice
File non-image minimal	Service: `2026-05-01-preview`/`2026-08-01-preview`; helper August (multipart metadata, 200 files)
File CU or images	`2026-08-01-preview`, `standard`; planner and executor supported. May rejects images; minimal returns 415 in both. CU is independent of source vectors
Blob minimal or standard CU	`2026-04-01` GA unless a selected feature requires preview; CU alone does not force preview
ADLS in this helper	`2026-08-01-preview`; do not describe a helper restriction as a platform prohibition
Permission/private ingestion	Preview properties require `2026-08-01-preview`; this source planner does not implement either, schedules or user-assigned identities
KB low/medium, synthesis or agent connection	Explicit preview configuration; GA helper is minimal/extractive. KB models and source embeddings/CU are separate

File --plan optional api_version defaults to August; unsupported: compatible-client handoff, never silent upgrade. Choose source/KB APIs separately; no GA preview fields, silent downgrade, unsupported helper features or skillset edits.

Source formats

Admission is not content fit: owners assess structure/answer needs.

The File service detects content type; MIME cannot override it. Minimal accepts PDF, DOC/DOCX, PPT/PPTX, XLS/XLSX, JSON, shell scripts and detected text/*, including TXT/MD/HTML/CSV. The helper preserves bytes and deterministic filename hints, not detected types. Unknown/extensionless files use application/octet-stream. Search-detected images need August standard; hints cannot require CU or block minimal.

Upload only selected paths; never execute scripts, unpack archives or auto-include hidden files. Credential targets, including selected root components, are blocked; this is not a secret scan. Preserve tier/count/root/link guards and historical artifact bytes/MIME/fingerprints. Server 415 stops ingestion, retaining earlier writes/source ownership and first failure; never completed.

Blob indexer formats apply to Blob/ADLS knowledge sources: CSV, EML, EPUB, GZ, HTML, JSON, KML, MD, DOC/DOCX/DOCM, XLS/XLSX/XLSM, PPT/PPTX/PPTM, MSG, Word XML 2003/2006, ODT/ODS/ODP, PDF, plain text, RTF, XML and ZIP. Generic Storage MIME is not grounds for rejection. Compound/archives are one blob document before chunking, not one KB document per entry. Never unpack/upload/modify blobs or widen scope. Require successful ingestion, not just source acceptance.

CU skill formats are PDF, JPEG/JPG, PNG, BMP, HEIF, TIFF, DOCX, XLSX, PPTX, HTML, TXT, MD, RTF, EML. Blob indexer acceptance does not prove CU support for ZIP/legacy Office. Both limits apply, including the five-minute CU timeout; no universal support. File follows its detected-type contract, not this Blob CU list. CU image descriptions/semantic chunking: preview since 2026-05-01-preview; not exposed by this planner.

Sources

Authorities: failure/conflict/uncertainty only.

File, Blob indexer, CU skill. Schemas: RG, AI ARM. Scope and assignments.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Python

The author says: Azure

Security

What our scanner noticed· Medium risk

References to credential files
Instructions that use the network
Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by

Microsoft

Publisher

Microsoft (Official)

Source

microsoft/skills · .github/plugins/foundry-iq-skills/skills/foundry-iq · commit 0696600

Licence

MIT License (redistribution allowed)

LICENSE (added by AutoGineer from .github/plugins/foundry-iq-skills/LICENSE)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-09

AutoGineer is not affiliated with or endorsed by Microsoft or Microsoft.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download foundry-iq.zip