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

helpers/vector-contracts.md

Embeddings and vector verification

File/Blob/ADLS; existing models only. No provisioning/catalogs/role changes/ installs/index repairs/cleanup. New unresolved intent: recommend hybrid; keyword-only skips this contract.

Supported choices

minimal is extraction, not retrieval mode. Lexical omits embeddingModel: no source embedding model. Vectors and CU are independent choices for both File/local uploads and Blob/ADLS containers; see the source matrix. File --plan supports minimal and standard CU. KB reasoning/answer synthesis and agent tool use are separate; index verification proves neither.

File/ADLS: 2026-08-01-preview; Blob also 2026-04-01. Set File vectorization: "azureOpenAI" or Blob processing: "minimal-vector" / "standard-cu"; add this closed embedding object to the owning procedure's intent:

{"endpoint":"https://models.openai.azure.com","deployment":"embed","model":"text-embedding-3-large","dimensions":"service-managed","model_version":"deployment-managed","auth":"system-assigned","prerequisites":{"deployment":"<fresh selected deployment/model readback>","identity":"<Search managed identity and model role assignment readback>","network":"<approved model network reachability evidence>"}}

All fields required; deployment is not a model family. Models: text-embedding-ada-002, text-embedding-3-small, text-embedding-3-large. HTTPS endpoints: openai.azure.com, services.ai.azure.com, cognitiveservices.azure.com; no keys, credentials, paths, query strings, explicit ports or APIM in this slice. auth: system-assigned, using existing Search identity. Ingestion/query readbacks allow only absent/null/empty-string apiKey and absent/null authIdentity. Masked/nonempty/malformed keys or other identities block without echoing values. Embedding guards preserve File CU's MI or explicit ARM/ENV channel; legacy modes remain.

Owner: read deployment/model and effective Search-to-model RBAC/network: az cognitiveservices account deployment show --subscription <sub> --resource-group <group> --name <account> --deployment-name <deployment> plus identity/role/network readbacks, not test embeddings. Record evidence references: not independently verified by the planner. Missing evidence blocks; refresh before approval.

Source guidance requires Cognitive Services User; the Azure OpenAI vectorizer also documents Cognitive Services OpenAI User. Policy owner verifies effective model data actions at that scope; never guess equivalence or assign roles.

Wire: embeddingModel.kind: azureOpenAI, azureOpenAIParameters.resourceUri/deploymentId/modelName/authIdentity. Neither API exposes dimensions or model-version pins: custom values block. Observe generated dimensions: ada-002 requires 1536; 3-small allows 1–1536; 3-large allows 1–3072. Deployment upgrades remain owner-managed; Search readback cannot pin or prove a model version.

Source application

Planners return planned, unapproved execution_input, hash-free approval_summary of endpoint/deployment/auth/cost/data movement. No model/query calls; inconsistent choices/definitions block. Save only execution_input; apply via the owner's --input after explicit mutation/embedding-cost/data-transfer consent. Fresh exact reuse needs no mutation approval/executor: not readiness or retrieval.

Read-only verification plan

Retain artifact; use generated fields, never inferred names. Use index-get or REST GET /indexes('<index>')?api-version=<source-api> provides fields/profiles/vectorizers. Never modify or switch indexes.

python helpers/source_vector.py --plan verify.json

File:

{"schema_version":"1.0","source_plan_file":"source-execution.json","vector_field":"vector","content_field":"content","citation_field":"citation","expected_citation":"guide.txt","expected_text":"Example local data","query":"Where are examples?","mode":"vector","k":3,"not_before":null}

mode: vector/hybrid; k: 1–10. Query/citation/text: nonempty, at most 4096 characters. Three distinct simple field names; use actual schema and corpus provenance, not illustrative names. No credentials/tokens. Blob/ADLS not_before: explicit UTC synchronization start lower bound for this ingestion, never an arbitrary old success. Redacted Storage bindings need paired reuse_input_file/reuse_result_file creation receipts per the Blob proof contract, loaded only when needed.

Checks: artifact/source/index identities/ETags, dimensions/profile/algorithm/vectorizer, endpoint/deployment/model/auth, retrievable content/citation/key. Unknown/redacted/ duplicate/conflicting metadata blocks. Permission sources/indexes require KB retrieval.

File: complete matching IDs/markers, no reported errors; uploads are synchronous. Blob/ADLS: bounded complete Storage/ACL observations; relevant completed nonempty cycle, zero failures/skips, no current cycle. Never start indexers. Zero-work: required proof. Stale/missing readiness blocks. Reread source/index; snapshots are not locks.

Exit 0: planned, configuration/ingestion observations, retrieval unverified, unapproved execution_input, query/model/cost summary. Retain referenced artifacts; keep private paths/fingerprints machine-only, never ask users to repeat hashes.

Separately approved query

Save execution_input; explicitly approve query text, model calls/cost and content transfer, then:

python helpers/source_vector.py --input approved-vector-query.json

Reobserve source, inventories/readiness and index; drift blocks before POST. One vector-only request to the source-owned index: POST /indexes('<index>')/docs/search.post.search?api-version=<source-api>, vectorQueries: [{kind: text, text: <query>, fields: <vector-field>, k: <k>}], top: k, minimumCoverage: 100, selected key/content/citation fields. Hybrid additionally sends search, searchFields, queryType: simple in a second request only after independent vector-only success. Never fall back to lexical retrieval. No KB/chat/semantic answers.

Require HTTP 200/request ID, full coverage, nonempty bounded unique hits, finite scores, matching expected citation and content. Partial/error/continuation/ malformed/mismatched responses block. Reobserve afterward and reject drift. retrieval-verified: this runtime probe passed, not corpus-wide quality. Evidence: request IDs/digests/counts, not raw documents/citations. Tests/mocks are never cloud evidence.

Blocked queries: exit 2, zero resource writes, attempted count/possible billing; no ambiguous-query retries. Source writes retain partial/separate cleanup. After definition/model/identity/policy/data drift, rerun source/verification --plan, replace artifacts and discard consent.

Bounds: each observation uses existing File limits (200 pages/records, 60-second listing budget, 1 MiB/page) or the source artifact's complete Blob/ADLS discovery limits. It adds four Search definition/index GETs and, for Blob, one status GET. One planning observation; two bracket approved queries. At most two query POSTs, each capped at 8 MiB and a 60-second body-read budget; added GETs use the same caps. Overflow blocks. No redirects or unbounded background work. Body budgets are not hard DNS/connect/header/scheduling deadlines.

Schemas

Authorities: failure/conflict/uncertainty only.

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