Generated banner for Foundry Iq
Generated logo for Foundry Iq

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

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/microsoft/foundry-iq/download
  2. 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.

OutcomeRead
CleanupPlan cleanup
Failure/driftDiagnose
Unsupported connector provisioning / multi-source KB creation or reconfigurationDiagnose
ConnectConnect
Read KBQuery
Search onlySearch
File KS onlyFile
Blob/ADLS KS onlyBlob
Searchable/KBKB

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

helpers/file_cu_mi.py

"""File Standard system-MI binding; implementation evidence is not rollout proof."""
from __future__ import annotations

import copy
import re

try:
    from . import cu_ingestion_auth, _search_read
    from ._common import MANAGEMENT_AUDIENCE, HelperFailure, require_allowed_fields
except ImportError:
    import cu_ingestion_auth
    import _search_read
    from _common import MANAGEMENT_AUDIENCE, HelperFailure, require_allowed_fields


SEARCH_API = "2025-05-01"
ROLE_API = "2022-04-01"
CU_ROLE = "a97b65f3-24c7-4388-baec-2e87135dc908"
SEARCH_ID = re.compile(
    r"/subscriptions/[0-9a-fA-F-]{36}/resourceGroups/[A-Za-z0-9_.()-]{1,90}"
    r"/providers/Microsoft\.Search/searchServices/(?=.{2,60}$)((?a:[a-z0-9][a-z0-9]+(?:-[a-z0-9]+)*))", re.I,
)
REDACTED = (None, "", "<redacted>", "***")


def fail(code, message, *, request_id=None, status=None):
    return HelperFailure(code, message, blocked_at="cu-managed-identity", request_id=request_id, status=status)


def validate_choice(value, resource_id):
    if not isinstance(value, dict):
        raise fail("cu-mi-prerequisite-missing", "Resolve existing Search resource ID and exact CU-scoped Cognitive Services User assignment. Missing identity/role changes need packaged bootstrap plans and explicit approval.")
    require_allowed_fields(value, {"search_resource_id", "role_assignment_id"}, label="File CU managed identity")
    search = value.get("search_resource_id")
    role = value.get("role_assignment_id")
    prefix = resource_id + "/providers/Microsoft.Authorization/roleAssignments/"
    if (
        not isinstance(search, str) or SEARCH_ID.fullmatch(search) is None
        or not isinstance(role, str) or not role.casefold().startswith(prefix.casefold())
        or cu_ingestion_auth.UUID.fullmatch(role[len(prefix):]) is None
    ):
        raise fail("cu-mi-binding-invalid", "Select exact Search and CU-account-scoped role assignment IDs; no inferred account, inherited/custom role or user-assigned identity.")
    return copy.deepcopy(value)


def read_binding(choice, endpoint, *, token_provider, transport):
    selected = validate_choice(choice.get("managed_identity"), choice["resource_id"])
    match = SEARCH_ID.fullmatch(selected["search_resource_id"])
    if endpoint.rstrip("/").casefold() != f"https://{match.group(1)}.search.windows.net".casefold():
        raise fail("cu-mi-search-mismatch", "Search resource ID must match the exact approved Search endpoint.")
    ids = []

    def get(resource, version):
        response = transport(
            "GET", f"{MANAGEMENT_AUDIENCE}{resource}?api-version={version}",
            token_provider(MANAGEMENT_AUDIENCE), follow_redirects=False, max_response_bytes=65536,
        )
        if response.status != 200 or not isinstance(response.body, dict):
            raise fail("cu-mi-prerequisite-unavailable", "Cannot GET the exact Search identity or scoped CU role. Have its owner resolve read access or plan missing setup; no key fallback or permission changes.",
                       request_id=response.request_id, status=response.status)
        if str(response.body.get("id", "")).casefold() != resource.casefold():
            raise fail("cu-mi-resource-mismatch", "ARM returned another resource or scope; refresh the selected bindings.", request_id=response.request_id)
        if response.request_id:
            ids.append(response.request_id)
        return response.body

    search = get(selected["search_resource_id"], SEARCH_API)
    identity, props = search.get("identity"), search.get("properties")
    if (
        not isinstance(identity, dict) or not isinstance(props, dict)
        or "SystemAssigned" not in str(identity.get("type", "")).replace(" ", "").split(",")
        or any(not isinstance(identity.get(k), str) or cu_ingestion_auth.UUID.fullmatch(identity[k]) is None
               for k in ("principalId", "tenantId"))
        or str(props.get("provisioningState", "")).casefold() != "succeeded"
        or str(props.get("status", "")).casefold() != "running"
        or str(props.get("endpoint", "")).rstrip("/").casefold() not in (
            endpoint.rstrip("/").casefold(), endpoint.rstrip("/").casefold().removeprefix("https://"),
        )
    ):
        raise fail("cu-mi-identity-unverified", "Require ready Search system-assigned principal/tenant and endpoint readback; resolve missing identity with a separately approved bootstrap plan.")
    role = get(selected["role_assignment_id"], ROLE_API)
    rp = role.get("properties")
    expected_role = re.compile(r"/subscriptions/[0-9a-fA-F-]{36}/providers/Microsoft.Authorization/roleDefinitions/" + CU_ROLE, re.I)
    if (
        not isinstance(rp, dict)
        or str(rp.get("principalId", "")).casefold() != identity["principalId"].casefold()
        or rp.get("principalType") != "ServicePrincipal"
        or str(rp.get("scope", "")).casefold() != choice["resource_id"].casefold()
        or expected_role.fullmatch(str(rp.get("roleDefinitionId", ""))) is None
        or rp.get("condition") not in (None, "")
    ):
        raise fail("cu-mi-role-unverified", "Require the selected Search principal's unconditional Cognitive Services User assignment on this CU account. Plan a missing scoped role explicitly; no self-grant or key fallback.")
    return {
        **selected, "search_endpoint": endpoint.rstrip("/"),
        "principal_id": identity["principalId"], "tenant_id": identity["tenantId"],
        "identity_type": identity["type"], "search_api_version": SEARCH_API, "role_api_version": ROLE_API,
        "role_definition_id": rp["roleDefinitionId"], "cu_resource_id": choice["resource_id"],
        "search_network": {k: copy.deepcopy(props.get(k)) for k in ("publicNetworkAccess", "networkRuleSet")},
    }, ids


def validate_state(state, choice, endpoint):
    if not isinstance(state, dict):
        raise fail("cu-mi-prerequisite-missing", "Retain the planner's verified Search identity/role binding.")
    fields = {"search_resource_id", "role_assignment_id", "search_endpoint", "principal_id", "tenant_id",
              "identity_type", "search_api_version", "role_api_version", "role_definition_id",
              "cu_resource_id", "search_network"}
    require_allowed_fields(state, fields, label="File CU identity state")
    selected = validate_choice(choice["managed_identity"], choice["resource_id"])
    if (
        set(state) != fields or any(state.get(k) != v for k, v in selected.items())
        or state["search_endpoint"] != endpoint.rstrip("/")
        or state["cu_resource_id"] != choice["resource_id"]
        or state["search_api_version"] != SEARCH_API or state["role_api_version"] != ROLE_API
        or not isinstance(state["search_network"], dict)
        or any(not isinstance(state[k], str) or cu_ingestion_auth.UUID.fullmatch(state[k]) is None
               for k in ("principal_id", "tenant_id"))
        or "SystemAssigned" not in str(state["identity_type"]).replace(" ", "").split(",")
        or not str(state["role_definition_id"]).casefold().endswith("/roledefinitions/" + CU_ROLE)
    ):
        raise fail("cu-mi-binding-invalid", "Retain complete, unchanged identity, role, API and account bindings.")


def guard_create(plan, transport, recheck, checkpoint=None):
    """An expected-absent MI plan must not adopt another actor's redacted source."""
    url = _search_read.resource_url(plan["source"])
    acknowledged = False
    created_etag = None

    def on_created(**evidence):
        nonlocal created_etag
        # The reconciler calls this after ACK, outside ambiguous transport recovery.
        if checkpoint is not None:
            try:
                checkpoint(**evidence)
            except HelperFailure:
                raise
            except Exception:
                raise fail("cu-mi-checkpoint-failed", "Acknowledged MI creation checkpoint failed; private details withheld.") from None
        try:
            response = evidence["response"]
            created_etag = _search_read.resolve_etag(_search_read.response_etags(response), response.request_id)
        except HelperFailure:
            raise fail("cu-mi-ack-version-unverified", "MI creation was acknowledged, but its version evidence is invalid. Retain ownership; do not replay.") from None
        if created_etag is None:
            raise fail("cu-mi-ack-version-unverified", "MI creation was acknowledged without an ETag; redacted auth cannot be bound to a created version. Retain ownership; do not replay.")

    def guarded(method, target, token, **kwargs):
        nonlocal acknowledged, created_etag
        if method == "PUT" and target == url:
            recheck()
        result = transport(method, target, token, **kwargs)
        if target == url:
            if method == "PUT" and result.status in (200, 201):
                acknowledged = True
            if method == "GET" and result.status == 200 and plan["source"]["action"] == "create" and not acknowledged:
                raise fail("cu-mi-source-drift", "Expected source absence changed before creation; do not infer MI from redacted readback. Refresh discovery and provenance.")
            if method == "GET" and result.status == 200 and acknowledged:
                try:
                    observed_etag = _search_read.resolve_etag(_search_read.response_etags(result), result.request_id)
                except HelperFailure:
                    raise fail("cu-mi-readback-version-unverified", "Created MI source readback has invalid version evidence.") from None
                if observed_etag != created_etag:
                    raise fail("cu-mi-source-drift", "Source version changed after acknowledged MI creation; redacted auth is unproven. Inspect ownership before cleanup.")
        return result

    return guarded, on_created

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

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