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://mp-staging.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

knowledge-bases/retrieve.md

Retrieve from a knowledge base

When to use

One KB query; opt-in offline/agent audits.

Do not use

No creation/repair/sync/connection/RBAC/effort changes or cleanup. Failures/drift: Diagnose. Never return credentials.

Inputs and discovery order

Standalone: Search REST retrieve with Entra auth, no MCP/agent required. Check CLI/sign-in; preserve azure-authentication-failed or azure-cli-unavailable. Never install/switch identity implicitly. Capture privately: az account show --output json; for a user, az ad signed-in-user show --query id --output tsv (no subscription flag).

Never request tokens/credentials/keys in chat. Missing verified host auth blocks; pasted tokens aren't a remedy.

Resolve prompt/session/workspace/exact Azure readback; one focused question. Label evidence. Discovery needs no approval; run only authorized queries. Retrieval can invoke models/cost/data movement. Silence never selects identity/permissions/extra queries.

Input	Why needed	Required?	Discovery order	Safe default	If missing or unanswered	Reconfirmation trigger
Search/base ID/endpoint	Target	Yes	Prompt/session/GET	None	Ask ambiguity	No writes
API/definition/mode	Shape	Yes	Creation/GET	None	Ask/block	None
Query	Retrieval	Yes	Prompt	None	Ask	None
Caller	Access	Yes	Identity GET	None	Block	None
Forwarding	Access	If needed	Source/base GET	None	Block	None
Original identity	Citations	Opt-in audit	Inventory	None	Unverifiable	None
Unrelated question	Abstention	Opt-in audit	Authorized evidence	None	Not tested	None
Agent/tool identity	Tool proof	Audit	GET	None	Block	None

Decisions

GET base/source definitions; connection binding is not definition evidence. Use the API from creation evidence or ask before GET; it isn't a returned field. GA 2026-04-01 is extractive. Preview minimal can synthesize with a configured KB chat model; still use intents. Preserve observed output/effort.

KB/model changes: KB setup selects chat model and separately approved deployment/configuration. No retrieval-time mutation or fallback to minimal.

Inspect source ingestionPermissionOptions in ingestion parameters; unknown posture blocks. Permission-enabled retrieval requires per-request x-ms-query-source-authorization, audience https://search.azure.com/.default, separate from service auth. Forward only the verified same signed-in user's token; otherwise permission-forwarding-unavailable. Never persist/log tokens; do not pass the caller token as a CLI argument. Never query unfiltered as fallback.

Proposed plan

State target/API/mode, caller/query/forwarding, citation identity and optional audit; mutation: none.

Confirmation

No mutation approval gate. Confirm acceptance questions not already authorized; do not auto-run queries. Writes need the owner's separate plan and confirmation.

Mutation

None; never retry through another resource.

Standalone: use selected endpoint/name/API and observed effort. Query is JSON data, never shell text. GA/preview minimal use intents; preview low/medium uses messages. Never override mode/effort/models/source selection.

Invoke by loaded skill path, not customer project; never read/copy source or replace:

python "<skill-dir>/helpers/knowledge_base_retrieve.py" --input "<request.json>"

Definition GET, UTF-8 JSON:

{"operation":"get-knowledge-base","endpoint":"https://<service>.search.windows.net","name":"<kb>","api_version":"2026-08-01-preview"}

Read selected sources with operation: get-knowledge-source and exact name. Helper escapes OData; do not pre-encode. Inspect definitions/permissions; use observed effort and explicit forwarding:

{"operation":"retrieve","endpoint":"https://<service>.search.windows.net","name":"<kb>","api_version":"2026-08-01-preview","effort":"minimal","query":"<question>","forward_permissions":false}

Use the selected API. Closed inputs: no approval envelope/fingerprint/credentials. Set forward_permissions: true only for the verified same signed-in user when the source requires forwarding. The helper additionally checks CLI user type, then acquires the token in memory. It never accepts a caller token as input.

Helper retains HTTP status/request ID, disables redirects, bounds bytes, never retries. Exit 0: status: response-received, http_status, request_id, response_body; not grounding/end-to-end proof. Exit 2: status: blocked, first code/status/request ID, no writes/ownership/cleanup, even for ambiguous POST. No tokens/raw diagnostics.

REST results contain response, references, and optional activity; they are not MCP result.content[]. Parse all returned text blocks and reference IDs. Activity errors or missing grounding are incomplete, not success. HTTP 206 is rejected even with valid-looking content. No-support is valid; never fill gaps from general knowledge.

Requested agent audits: invoke supported host; verify native per-KB knowledge_base_retrieve call. Missing connection: knowledge-base-mcp-endpoint-unavailable; do not substitute REST as agent proof. Never substitute a generic index query or the generic Azure MCP Server search_* tool group for either path.

Verification

For ordinary retrieval, check the requested answer, native references and activity; missing grounding/errors remain incomplete. No extra questions or retained bundle.

Offline audit is opt-in; default audit_status: not-requested. No hand-authored Q&A required. Propose title/content questions only from authorized content, not structural assessment. Approve proposed queries before execution; never derive ground truth from audited answers. No samples/questions: defer audit. After opt-in, follow the paired audit contract: python "<skill-dir>/helpers/retrieval_verify.py" --input "<private-bundle>/audit.json". No custom parsing/raw dumps/reretrieval; exit 0 isn't acceptance. Skipping is not a pass.

Audit original File path plus file ID or Blob/ADLS URL/path plus ETag/version; native docName/blobUrl lack File ID/ETag: report unverified, not chunk-ID proof. For synthesis audits, apply the shared semantic abstention criteria, honoring any explicit exact-output contract. GA/preview extractive audits require no supporting extracts: do not invent a synthesized I don't know. Structural absence isn't semantic abstention. Recheck identities; require before_after_snapshot_equal: true.

Failure and partial completion

Denial is inaccessible, not absence. Diagnose empty/wrong/stale output without mutation. No fabricated citations/success; failures create no ownership.

Cleanup

Not applicable. No resources or cleanup approval.

Return contract

Verified: status: completed, outcome: knowledge-base-retrieval, mutation: none, KB/source IDs/endpoint/API/mode, preview: true|false, caller/forwarding, requested answer/citations, activity/tool evidence, warnings/latency, audit_status, abstention tested/evidence and before/after equality when audited. Otherwise return status: blocked, blocked_at, first status/message/request ID, missing/conflicting input, safe next decision, writes_performed: [], no new ownership and cleanup: not-applicable. Never report unavailable evidence as verified or include credentials/raw diagnostics.

References

Abstention criteria: required for synthesis audits.
Optional audit schema and versions; not required normal-path reads.

Authorities: failure/conflict/uncertainty only.

Retrieve using a knowledge base

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

2026-11-08

AutoGineer is not affiliated with or endorsed by Microsoft.

Download ZIP

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