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/blob-contracts.md

Blob/ADLS contract

Blob progress: --no-progress disables stderr.

Planning

python helpers/blob_source.py --plan intent.json

Intent:

{"schema_version":"1.0","endpoint":"https://svc.search.windows.net","name":"manuals","owner":"[email protected]","storage_id":"/subscriptions/00000000-0000-0000-0000-000000000000/resourceGroups/Example/providers/Microsoft.Storage/storageAccounts/example","container":"documents","prefix":"Reports/","is_adls":false,"api_version":"2026-04-01","processing":"minimal-lexical","network_access":"public","identity":"system-assigned","permission_options":[],"ingestion_schedule":null,"description":null,"rbac":{"assignments":[{"id":"<observed-assignment>","principalId":"<observed-principal>"}]},"network":{"posture":"public","evidence":"<fresh-readback-reference>"},"inventory_limits":{"max_pages":100,"max_objects":10000,"max_requests":25000,"deadline_seconds":600},"poll":{"deadline_seconds":600,"max_requests":120,"interval_seconds":5}}

Content fit (no default): minimal-lexical=minimal/no vectors, minimal-vector=minimal/vectors, standard-cu=standard/optional vectors; not KB reasoning. Public/system-assigned; no schedule settings/permission ingestion. Blob: 2026-04-01 or 2026-08-01-preview; ADLS: preview, is_adls: true, directory prefix without trailing /. Root: explicit prefix: "", no widening. Description: text/null; other modes: planning-processing-unsupported.

No writes/auth changes/installs/polling/cleanup. Verify access/cost/data preapproval.

Two exact Search GETs bracket two-pass Storage observation. Reuse requires matching definition/ETag, Storage binding and four generated identities. reuse_input_file/reuse_result_file: retained approved input/successful creation result. Validate pairing/types before auth; load only for redacted binding. Required fingerprints/boundaries/source ETags/definitions/generated identities must match fresh readback. Unproven binding: source-binding-unverified. Old consent/readiness never authorizes new work.

Exit 0: status: planned, plan_fingerprint, execution_input, approval_summary, request IDs and writes_performed: []. Save only execution_input; its approval is false and the executor rejects it until actual unchanged-plan approval. Private artifacts preserve ResourceId connection strings/fingerprints; ordinary result redaction is unchanged. Summaries omit paths/ACLs/hashes; no readiness. Exact reuse sets execution_required and mutation_approval_required false: no executor or approval needed. Drift: rerun --plan, replace the artifact, discard consent; never hand-edit nested plans/hashes. Cleanup stays separate and run-owned-only.

For standard-cu, read CU choices/wire. content_understanding binds CU; optional embedding selects source vectors.

Discovery

python helpers/blob_source.py --discover <boundary.json> accepts this closed JSON (no approval):

{"boundary":{"storage_id":"<ARM-account-ID>","container":"<container-or-filesystem>","prefix":"Reports/","is_adls":false},"inventory_limits":{"max_pages":100,"max_objects":10000,"max_requests":25000,"deadline_seconds":600}}

Arbitrary partial-name prefixes: boundary-ambiguous. Public cloud/private DNS.

Read all pages twice including empty continuations. Exit 0 returns status: discovered, mutation: none, writes_performed: [], boundary/account, sorted objects (URL/path/size/ETag/version), ADLS path/property digests, request IDs, inventory_digest; not approval/ingestion. Incomplete/duplicate/out-of-scope/unreadable/unstable evidence blocks. ADLS HEADs path/ancestor ACLs; no raw ACL/content. Operator access is not Search access. Every path has an ACL HEAD; every non-root path also has a properties HEAD for type and matching ETag. Root has no type header. Preserve ancestors and normalize quoted/unquoted Blob/DFS ETags only for comparison; never skip required reads.

Inventory bounds apply per discovery: pages/objects per pass; requests/time across both passes, including empty pages and all HEADs. Maximum accepted limits are 1000 pages, 100000 objects, 200000 requests and 3600 seconds; exceeding any bound blocks, never truncates. Planning adds at most two Search GETs and shares its time budget with discovery. Bodies are capped at 8 MiB plus one overflow probe byte. Socket watchdog interrupts body reads; DNS/connect/header acquisition and scheduling are not hard wall-clock bounded. Redirects and unsupported deadline readers block. Limits are safety bounds, not spending consent.

Apply

python helpers/blob_source.py --input <approved.json> uses:

{"schema_version":"1.0","plan":{},"approval":{"confirmed":true,"fingerprint":"sha256:<canonical-plan-digest>"}}

Canonical JSON: UTF-8, sorted keys, ASCII-escaped/compact. operation: reconcile-and-monitor, owner, cleanup_approved: false, discovered boundary, inventory_digest, inventory_limits, source, poll: {"deadline_seconds":600,"max_requests":120,"interval_seconds":5}. Planner reuse: expected_generated, four typed/name/service-managed identities, checked before writes; legacy artifacts remain valid. Planner creation sets expected_source_absent: true; an intervening source blocks. Redacted GET requires the PUT ETag (body/header); conflicts block. ambiguous unproven ownership remains partial, never adopted or cleaned up.

source: operation: reconcile, resource_type: knowledge-source, exact endpoint/name/api_version, action: create or reuse, matching owner, cleanup_approved: false, approved desired, and source_evidence with verified: true and the same inventory_digest. ADLS also requires path_verified: true, acl_verified: true attest metadata, not effective Search permissions.

desired: matching name, kind: azureBlob; azureBlobParameters: connectionString: ResourceId=<exact-storage-resource-id>, containerName, exact folderPath (null for explicit root), boolean isADLSGen2, ingestionParameters. Optional shared controls. No keys/SAS/updates/credential environments or supplied createdResources/assetStore.

Recompute approval/evidence; block drift. Create conditionally/reuse zero-write; supplied ETag must match. Poll GET knowledgesources('{name}')/status within bounds. Only 408/429/500/502/503/504/transport-ambiguous reads retry; 403/404 block. Watch expiry pauses; it does not fail ingestion. Backoff and explicit GET-only continuation/compact output: recheck.

Require completed start/end times at or after the pre-write cutoff, nonnegative integer itemsUpdatesProcessed, itemsUpdatesFailed, and itemsSkipped, zero failures, no observed relevant errors or active cycle. Missing counts are not zero. Completed status may be absent; reject partialSuccess/failure/malformed/unknown. Never trigger indexers/edit schedules; stale success cannot pass. Reuse also excludes the first observed completion.

Results

--receipt-dir: PUT acknowledgement before GET. Binding/recovery: redaction, recovery, reuse; never reconstruct cutoffs. Timing differences: indexer checks.

Exit 0: completed; unverified zero-write reuse is exit 2, blocked with reconciliation: completed. After a write, exit 3 / partial retains approval/first failure/resources_remaining.run_owned. Conflicting children aren't owned. Return generated identities/readiness/digests/ warnings/cleanup; errors retain status/request ID, not sensitive text. No rollback/source writes/child edits.

Owner handles RBAC/private links. CLI Entra: ARM/Storage/Search audiences. Probes: ARM GET 2025-06-01, Storage 2025-05-05 listing, ADLS HEAD action=getAccessControl&upn=false.

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