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/_cleanup_receipts.py

"""Filtered, immutable creation evidence; never a credentialized callback surface."""
from __future__ import annotations

import copy
import uuid
from datetime import datetime
from pathlib import Path

try:
    from . import _bootstrap_io as private_io, _search_read
    from ._common import (
        HelperFailure, digest, load_approved_input, reject_secrets, odata_name, validate_search_endpoint,
    )
except ImportError:
    import _bootstrap_io as private_io
    import _search_read
    from _common import (
        HelperFailure, digest, load_approved_input, reject_secrets, odata_name, validate_search_endpoint,
    )


def fail(code, message):
    return HelperFailure(code, message, blocked_at="cleanup-provenance")


def version_identity(value):
    get = value.get if isinstance(value, dict) else lambda key: getattr(value, key, None)
    identifier, created = get("id"), get("created_at")
    if isinstance(created, datetime):
        created = int(created.timestamp()) if created.tzinfo is not None else None
    if not isinstance(identifier, str) or not identifier.strip() or type(created) is not int or created <= 0:
        return None
    return {"id": identifier, "created_at": created}


def add_argument(parser):
    parser.add_argument("--cleanup-receipt-dir", type=Path,
                        help="Existing absolute private directory for filtered original-create evidence.")


class Capture:
    def __init__(self, directory, document):
        self.directory = private_io.private_directory(str(directory))
        self.plan_digest = digest(document["plan"])
        self.owner = document["plan"].get("owner")
        self.records = {}
        self.summaries = []

    def start(self, target, acknowledgement):
        acknowledgement.setdefault("version_identity", None)
        record = {
            "schema_version": "1.0", "kind": "cleanup-creation-receipt",
            "plan_digest": self.plan_digest, "owner": self.owner, "target": target,
            "state": "acknowledged", "acknowledgement": acknowledgement, "snapshot": None,
        }
        key = digest(target)
        self.records[key] = record
        self._persist(record)

    def finish(self, target, snapshot):
        record = copy.deepcopy(self.records[digest(target)])
        ack = record["acknowledgement"]
        snapshot.setdefault("version_identity", None)
        if (snapshot["version_identity"] != ack["version_identity"]
                or (target["type"] == "prompt-agent-version" and ack["version_identity"] is None)):
            raise fail("creation-version-unproven", "Native version identity/creation time must match the original acknowledgement.")
        if not isinstance(ack["request_id"], str) or not ack["request_id"].strip():
            raise fail("creation-request-id-unavailable", "Original native acknowledgement lacks a request ID.")
        if snapshot["definition_digest"] != ack["definition_digest"]:
            raise fail("definition-drift", "Readback differs from the acknowledged original creation.")
        record.update(state="verified", snapshot=snapshot)
        self._persist(record)

    def _persist(self, record):
        reject_secrets(record)
        value = {**record, "integrity": digest(record)}
        try:
            path = private_io.private_file(self.directory, uuid.uuid4().hex + ".cleanup.json", value)
        except OSError as exc:
            raise fail("cleanup-receipt-persistence-failed", "Acknowledged creation evidence could not be retained privately.") from exc
        self.summaries.append({"target": record["target"], "state": record["state"],
                               "receipt_file": str(path), "evidence_digest": value["integrity"]})


def search_target(plan):
    return {"type": plan["resource_type"], "endpoint": validate_search_endpoint(plan["endpoint"]),
            **{key: plan[key] for key in ("name", "api_version")}}


def search_ack(capture, plan, response):
    try:
        from . import _cleanup_dependencies as dependencies
    except ImportError:
        import _cleanup_dependencies as dependencies
    generated = None
    if plan["resource_type"] == "knowledge-source":
        try:
            generated = dependencies.generated(response.body) if isinstance(response.body, dict) else None
        except HelperFailure as error:
            if error.code not in {"source-cleanup-kind-unsupported", "generated-ownership-unproven", "name-invalid"}:
                raise
            # Retain the ACK before search_finish rejects incomplete ownership evidence.
            generated = None
    capture.start(search_target(plan), {
        "operation": "search-create", "status": response.status, "request_id": response.request_id,
        "definition_digest": digest(_search_read._definition(plan["desired"])),
        "etag_evidence": _search_read.response_etags(response), "generated": generated, "version": None,
    })


def search_finish(capture, plan, current, token, transport):
    try:
        from . import _cleanup_dependencies as dependencies
    except ImportError:
        import _cleanup_dependencies as dependencies
    target = search_target(plan)
    ack = capture.records[digest(target)]["acknowledgement"]
    etag = _search_read.resolve_etag(ack["etag_evidence"], ack["request_id"])
    if ack["status"] != 201 or not etag or current is None or current.get("@odata.etag") != etag:
        raise fail("creation-version-unproven", "Require original HTTP 201 and the unchanged acknowledged ETag, not a later GET version.")
    children = []
    if plan["resource_type"] == "knowledge-source":
        if ack["generated"] is None or dependencies.generated(current) != ack["generated"]:
            raise fail("generated-creation-evidence-unavailable", "The original create response did not identify this exact generated cascade.")
        for kind, name in sorted(ack["generated"].items()):
            url = f"{plan['endpoint'].rstrip('/')}/{dependencies.COLLECTIONS[kind]}('{odata_name(name)}')?api-version={plan['api_version']}"
            child, _ = _search_read.read_resource(url, token, transport=transport)
            if child is None or child.get("name") != name or not child.get("@odata.etag"):
                raise fail("generated-version-unavailable", "An original generated child lacks exact version readback.")
            children.append({"type": kind, "name": name, "etag": child["@odata.etag"], "definition_digest": digest(child)})
        refreshed, _ = _search_read.read_resource(_search_read.resource_url(plan), token, transport=transport)
        if (refreshed is None or refreshed.get("@odata.etag") != etag
                or _search_read._definition(refreshed) != _search_read._definition(current)
                or dependencies.generated(refreshed) != ack["generated"]):
            raise fail("definition-drift", "Source changed during original generated-child capture.")
    capture.finish(target, {"definition_digest": digest(_search_read._definition(current)), "etag": etag, "generated": children})


def project_target(plan, kind, *, name=None, version=None):
    target = {"type": kind, "project_resource_id": plan["project_resource_id"].casefold(),
              "project_endpoint": plan["project_endpoint"].rstrip("/"),
              "name": name or plan["connection"]["name"]}
    if version is not None:
        target["version"] = version
    return target


def connection_ack(capture, plan, response):
    body = response.body if isinstance(response.body, dict) else {}
    capture.start(project_target(plan, "project-connection"), {
        "operation": "project-connection-create", "status": response.status, "request_id": response.request_id,
        "definition_digest": digest(body), "version": None, "generated": None,
        "etag_evidence": {"body": body.get("etag") or body.get("@odata.etag"),
                          "headers": [v for k, v in response.headers.items() if k.casefold() == "etag"]},
    })


def connection_finish(capture, plan, body):
    target = project_target(plan, "project-connection")
    ack = capture.records[digest(target)]["acknowledgement"]
    etag = _search_read.resolve_etag(ack["etag_evidence"], ack["request_id"])
    if ack["status"] != 201 or not etag or etag != (body.get("etag") or body.get("@odata.etag")):
        raise fail("creation-version-unproven", "Connection readback must retain its original HTTP 201 ETag.")
    capture.finish(target, {"definition_digest": digest(body), "etag": etag, "generated": []})


def sdk_response_hook(metadata):
    def capture(response):
        native = response.http_response
        metadata["request_id"] = next((v for k, v in native.headers.items()
                                       if k.casefold() in ("request-id", "x-request-id", "x-ms-request-id", "apim-request-id")), None)
        metadata["status"] = native.status_code
    return capture


def agent_ack(capture, plan, created, metadata):
    target = project_target(plan, "prompt-agent-version", name=created.name, version=str(created.version))
    capture.start(target, {
        "operation": "agents.create_version", "status": metadata.get("status"), "request_id": metadata.get("request_id"),
        "definition_digest": digest(created.definition.as_dict()), "version": str(created.version),
        "etag_evidence": None, "generated": None,
        "version_identity": version_identity(created),
    })
    if (metadata.get("status") not in (200, 201) or created.name != plan["agent"]["name"]
            or str(created.version) == plan["agent"]["version"] or version_identity(created) is None):
        raise fail("ownership-unproven", "The original SDK return must identify a newly created version in the approved agent.")
    return target


def load(input_path, receipt_path, target):
    try:
        from . import _private_json
    except ImportError:
        import _private_json
    _, plan, fingerprint = load_approved_input(input_path)
    record = _private_json.read_private(receipt_path)
    reject_secrets(record)
    fields = {"schema_version", "kind", "plan_digest", "owner", "target", "state", "acknowledgement", "snapshot", "integrity"}
    if (not isinstance(record, dict) or set(record) != fields or record["schema_version"] != "1.0"
            or record["kind"] != "cleanup-creation-receipt" or record["state"] != "verified"
            or record["plan_digest"] != fingerprint or record["owner"] != plan.get("owner")
            or record["target"] != target
            or record["integrity"] != digest({k: v for k, v in record.items() if k != "integrity"})):
        raise fail("ownership-unproven", "Require the exact original verified producer receipt and original approval; ACK/recovery/reuse cannot substitute.")
    ack, snapshot = record["acknowledgement"], record["snapshot"]
    if (not isinstance(ack, dict) or set(ack) != {"operation", "status", "request_id", "definition_digest", "etag_evidence", "generated", "version", "version_identity"}
            or not isinstance(snapshot, dict) or set(snapshot) != {"definition_digest", "etag", "generated", "version_identity"}
            or not isinstance(ack["request_id"], str) or not ack["request_id"].strip()
            or snapshot["definition_digest"] != ack["definition_digest"]
            or not isinstance(snapshot["definition_digest"], str) or not _search_read.SHA256.fullmatch(snapshot["definition_digest"])
            or not isinstance(snapshot["generated"], list)):
        raise fail("ownership-unproven", "Producer receipt lacks complete acknowledged version evidence.")
    if (snapshot["version_identity"] != ack["version_identity"]
            or (target["type"] == "prompt-agent-version" and (
                not isinstance(snapshot["version_identity"], dict)
                or set(snapshot["version_identity"]) != {"id", "created_at"}
                or version_identity(snapshot["version_identity"]) != snapshot["version_identity"]))):
        raise fail("ownership-unproven", "Native version birth identity is missing or changed.")
    if target["type"] != "prompt-agent-version" and (
        not isinstance(ack["etag_evidence"], dict) or set(ack["etag_evidence"]) != {"body", "headers"}
        or not isinstance(ack["etag_evidence"]["headers"], list)
    ):
        raise fail("ownership-unproven", "Native ETag evidence must be complete.")
    if target["type"] in ("knowledge-base", "knowledge-source"):
        if (ack["operation"] != "search-create" or ack["status"] != 201
                or _search_read.resolve_etag(ack["etag_evidence"], ack["request_id"]) != snapshot["etag"]
                or not isinstance(snapshot["etag"], str) or not snapshot["etag"].strip()):
            raise fail("creation-version-unproven", "Original Search create acknowledgement and snapshot versions disagree.")
    elif target["type"] == "project-connection":
        if (ack["operation"] != "project-connection-create" or ack["status"] != 201
                or _search_read.resolve_etag(ack["etag_evidence"], ack["request_id"]) != snapshot["etag"]
                or not snapshot["etag"] or snapshot["generated"]):
            raise fail("creation-version-unproven", "Original connection acknowledgement and readback versions disagree.")
    elif target["type"] == "prompt-agent-version":
        if (ack["operation"] not in ("agents.create_version", "agents.create") or ack["status"] not in (200, 201)
                or (ack["operation"] == "agents.create" and ack["status"] != 200)
                or ack["version"] != target["version"] or snapshot["etag"] is not None or snapshot["generated"]):
            raise fail("ownership-unproven", "Require original SDK version-create return and its exact readback.")
    else:
        raise fail("cleanup-kind-unsupported", "No producer receipt contract supports this target.")
    return plan, record

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

From the author

AutoGineer summary

What it does

When to use it

Advantages

Usage examples

Install

Documentation by Microsoft

Foundry IQ

Files

helpers/_cleanup_receipts.py

Requirements and compatibility

Security

Attribution and licence

Related skills

Claude API

Transformers

Open Notebook

Vision Sft

LLM Evaluation

Lora Qlora Recipes

Download ZIP