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

helpers/bootstrap-contracts.md

Search bootstrap

New Basic/standard Search in an existing group. Other prerequisites/cleanup: native bootstrap.

Progress: stderr; --no-progress disables.

Choices

Python 3.12+, signed-in CLI on Windows/POSIX; no login/install/context switch. No preflight policy reads. Prerequisites: owner-verified references, not helper-verified. 1–256 printable characters; punctuation allowed. Errors omit values.

Creation: search/create. Existing operations: intake; legacy reuse stays strict, never hardens. New locations fold ASCII case/whitespace (East US → eastus); Not availability proof; bodies/hashes stay unchanged. Basic: 1–3 replicas/one partition; standard: 1–12 replicas/1/2/3/4/6/12 partitions. Fixed SystemAssigned, keyless auth and public networking; no role changes. Non-secret tags; creation adds operation/owner tags.

{"schema_version":"2.0","resource_kind":"search","action":"create",
"subscription_id":"00000000-0000-0000-0000-000000000001","tenant_id":"00000000-0000-0000-0000-000000000002",
"resource_group":"rg1","name":"mysearchservice","location":"westus","sku":"basic","replicas":1,"partitions":1,
"public_network_access":"Enabled","tags":{"project":"knowledge"},"owner":"operator",
"prerequisites":{"quota":"checked; enough","pricing":"approved","network":"approved public","requirements":"settings","exclusive_name_authority":"exclusive name"},
"limits":{"command_seconds":5,"wait_seconds":10,"wait_interval_seconds":1},"receipt_dir":"<absolute-private-directory>"}

Replace examples/limits. Reuse: exclusive_name_authority: null; required tags match; no ownership transfer.

Region scope (closed):

{"schema_version":"2.0","subscription_id":"<guid>","tenant_id":"<guid>","receipt_dir":"<private-dir>","limits":{"command_seconds":5}}

No RG/name/SKU: account check plus one az rest GET: /subscriptions/<sub>/providers/Microsoft.Search?api-version=2021-04-01. searchServices.locations supplies canonical available_locations (1–256). Exit 0: discovered, no approval/artifact. Create plan/apply: one fresh region GET each, including retained artifacts; no cache. Unknown: bootstrap-region-unsupported plus choices; denied/malformed: blocked. Reuse skips catalogs. Not SKU/quota/capacity/model/residency proof.

python "<skill-root>/helpers/bootstrap_azure.py" --regions scope.json
python "<skill-root>/helpers/bootstrap_azure.py" --plan choices.json
python "<skill-root>/helpers/bootstrap_azure.py" --apply "<private-directory>/<artifact_id>.plan.json" --approve

--plan uses Azure reads/local private writes: <artifact_id>.plan.json body, before-state, choices, time, unapproved envelope. Stdout: artifact_id/approval_summary, no paths/errors/hashes. Labels: caller attestation, not helper verification; exact references stay private. Show resource/network/capacity/tags/cost/limits; --approve consents once. No cached consent or user checksums.

15-minute expiry; submission markers prevent retries. On drift/failure/expiry/changed choices, rerun --plan; discard consent. Reconcile uncertainty; no suffix-create/body/hash edits. Schema 1.0: regenerate (bootstrap-contract-version). Removed inputs max_polls/poll_seconds/poll_interval_seconds are rejected.

Execution

Argv: az account show --subscription, az group show --name --subscription, Search ARM GET/PUT API 2025-05-01. PUT uses --body then one "@" + str(body_path) argument, Content-Type/client-request-ID headers. POSIX runs az directly; Windows MSI/ZIP uses bundled python.exe -IBm azure.cli. Other Windows layouts block.

Only normally returned target ResourceNotFound proves absence. Fresh principal/tenant/subscription/group/exact-name absence precede one PUT. GET/PUT is not atomic: require exclusive name authority. Mandatory atomicity: bootstrap-concurrency-unresolved, no invented conditionals.

Reuse: two fresh material readbacks, required configuration/tags, keyless identity/principal/tenant, endpoint, provisioning succeeded/status running. reused: no mutation approval/executor or ownership adoption. Wait uses the same identity; existence is not readiness.

After PUT: az resource wait --ids <id> --api-version 2025-05-01 --custom <generated-condition> --interval <wait_interval_seconds> --timeout <wait_seconds>. Fixed properties: succeeded/running or terminal states, lower/title/uppercase. No caller expressions/custom polling. Final raw GET establishes material match/ownership before readiness. Wait failure remains primary even with ready GET; provider evidence is secondary.

Limits: command 1–60 seconds, wait 1–900, interval 1–30. Wait/final GET: separate wait_seconds/command_seconds; sum is not an end-to-end deadline. subprocess.run: argv, shell=False, best-effort timeout/cleanup. CLI/OS/filesystems prevent hard time/process-tree/request-count guarantees. No PID or confirmed-cleanup claim. Captured output is rejected after capture above 1 MiB per stream: not a streaming cap or memory bound. Input/body/receipt limits remain 1 MiB. Timeout/execution/receipt failure after attempted PUT is partial.

Checks: target, principal/tenant, capacity/SKU, auth/network, identity, required tags, ARM readiness. Metadata/ordering/unrelated tags, ID/enum casing, equivalent optional defaults do not need another approval. Never default missing material fields or return extra tags. Material conflict, unknown ownership or failed readiness blocks/returns partial.

Evidence and failure

Existing absolute private directory outside the plugin. No symlinks/reparse paths. POSIX: directory-FD creation, identity/owner/private-mode rechecks; exclusive safe leaves, mode 0600. POSIX semantics required; later pathname uses are not pinned. Windows checks owner/DACL (owner, SYSTEM, Administrators), not handle-relative creation; chmod does not establish Windows privacy. No ACL changes. Same-user/admin tampering is possible; unprovable privacy blocks. Mocked/DrvFS is not native-filesystem or Azure evidence.

Flushed receipts: operation/target/body/argv, client-request ID, readbacks/digests, first error code/status/request ID, ownership. No raw errors/output/policy values/tokens/documents. Message digest/message_withheld; secret-free labels/tags. CLI file logging/dynamic installation: process-disabled.

Creation-only policy diagnostics: RequestDisallowedByPolicy, supported policy IDs or policy-violation details. Provider error/statusDetails, never tags/configuration. A bare 403/RBAC/network/quota failure triggers no policy calls. Preserve first failure; diagnostic/receipt errors are secondary warnings. At most eight referenced assignments/selected-subscription definitions within 60 seconds: az policy assignment show --name --scope and az policy definition show --name --subscription. No lists or global scans. Built-ins/management groups/initiatives/exemptions/missing references need the policy owner. No compliance/applicability proof, policy changes, write retries or correction approval.

Exit 0: planned/fresh reused/applied completed (ARM only). Data-plane access/ingestion/retrieval stay unverified. Exit 2: blocked, no confirmed/ambiguous Azure writes. Exit 3: partial, first_failure, attempted_writes, resources_remaining; unproven ownership is unverified, never run-owned. Receipt failure: block before submission, partial handoff afterward. No automatic rollback/deletion. Cleanup always needs separate consent and fresh ownership/configuration/children/scoped-role evidence.

Authorities: failure/conflict/uncertainty only.

Native wait; location metadata; provider GET.

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