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://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/_search_read.py

"""Search definition, version evidence and read-only resource access."""
from __future__ import annotations

import re
from typing import Any
from urllib.parse import urlencode

try:
    from ._common import (
        HelperFailure, HttpResult, ReadRecovery, Transport, odata_name, validate_search_endpoint,
    )
except ImportError:
    from _common import (
        HelperFailure, HttpResult, ReadRecovery, Transport, odata_name, validate_search_endpoint,
    )


SUPPORTED_API_VERSIONS = {"2026-04-01", "2026-08-01-preview"}


RESOURCE_SEGMENTS = {
    "knowledge-source": "knowledgesources",
    "knowledge-base": "knowledgebases",
}


DYNAMIC_FIELDS = {
    "@odata.context",
    "@odata.etag",
    "currentSynchronizationState",
    "lastSynchronizationState",
    "synchronizationStatus",
    "apiKey",
    "createdResources",
    # Azure Search always returns "<redacted>" for connectionString on GET
    # (secret redaction), never the submitted value, so it can never be
    # compared for exact equality against a desired definition.
    "connectionString",
}


# Search normalizes these endpoint fields inconsistently on readback.
URI_FIELDS = {"resourceUri", "uri"}


SHA256 = re.compile(r"^sha256:[a-f0-9]{64}$")


def _odata_name(name: Any) -> str:
    return odata_name(name)


def _resource_url(plan: dict[str, Any]) -> str:
    endpoint = validate_search_endpoint(plan.get("endpoint"))
    resource_type = plan.get("resource_type")
    segment = RESOURCE_SEGMENTS.get(resource_type)
    if segment is None:
        raise HelperFailure(
            "resource-type-invalid",
            "resource_type must be knowledge-source or knowledge-base.",
            blocked_at="input-resolution",
        )
    api_version = plan.get("api_version")
    if api_version not in SUPPORTED_API_VERSIONS:
        raise HelperFailure(
            "api-version-invalid",
            "API version must be 2026-04-01 or 2026-08-01-preview.",
            blocked_at="input-resolution",
        )
    return (
        f"{endpoint}/{segment}('{_odata_name(plan.get('name'))}')?"
        + urlencode({"api-version": api_version})
    )


def _definition(value: Any, *, key: str | None = None) -> Any:
    if isinstance(value, dict):
        result = {
            child_key: _definition(child, key=child_key)
            for child_key, child in sorted(value.items())
            if child_key not in DYNAMIC_FIELDS and child is not None
        }
        # Preview returns this documented default even when omitted on creation.
        if value.get("kind") == "azureBlob" and result.get("resultsProcessing") == "rerank":
            result.pop("resultsProcessing")
        return {
            child_key: child
            for child_key, child in result.items()
            if child not in ({}, [])
        }
    if isinstance(value, list):
        return [_definition(child) for child in value]
    # Azure Search silently strips a single trailing slash from
    # azureOpenAIParameters.resourceUri on readback (while preserving it
    # verbatim on aiServices.uri), so a byte-exact comparison would
    # false-negative on functionally identical endpoints that differ only
    # by a trailing slash. Normalize both known endpoint-URI field names.
    if (
        key in URI_FIELDS
        and isinstance(value, str)
        and value.endswith("/")
        and len(value) > 1
    ):
        # Remove only one trailing slash; preserve intentional extra
        # slashes (e.g. "https://example.com//") for exact comparison.
        return value[:-1]
    return value


def response_etags(result: HttpResult) -> dict[str, Any]:
    return {
        "body": result.body.get("@odata.etag") if isinstance(result.body, dict) else None,
        "headers": list(result.etag_values) if result.etag_values is not None else [
            value for name, value in result.headers.items() if name.lower() == "etag"
        ],
    }


def resolve_etag(evidence: dict[str, Any], request_id: str | None = None) -> str | None:
    values = [*evidence["headers"]]
    if evidence["body"] is not None:
        values.append(evidence["body"])
    if any(not isinstance(value, str) or not value.strip() for value in values):
        raise HelperFailure("etag-invalid", "Search returned malformed version evidence.",
                            blocked_at="verification", request_id=request_id)
    if len(set(values)) > 1:
        raise HelperFailure("etag-conflict", "Search response header/body ETags conflict.",
                            blocked_at="verification", request_id=request_id)
    return values[0] if values else None


def _get(
    url: str,
    token: str,
    *,
    transport: Transport,
    recovery: ReadRecovery | None = None,
) -> tuple[dict[str, Any] | None, str | None]:
    try:
        result = (recovery.get(url, token, transport=transport) if recovery is not None
                  else transport("GET", url, token))
    except HelperFailure as failure:
        if failure.http_status == 404 and failure.blocked_at != "local-persistence":
            return None, failure.request_id
        raise
    if result.status != 200 or not isinstance(result.body, dict):
        raise HelperFailure(
            "readback-invalid",
            "Search resource readback did not return one JSON object.",
            blocked_at="reconciliation",
            request_id=result.request_id,
            status=result.status,
        )
    etag = resolve_etag(response_etags(result), result.request_id)
    body = {**result.body, "@odata.etag": etag} if etag is not None else result.body
    return body, result.request_id


def resource_url(plan: dict[str, Any]) -> str:
    """Validate and address the exact selected Search resource."""
    return _resource_url(plan)


def read_resource(
    url: str, token: str, *, transport: Transport
) -> tuple[dict[str, Any] | None, str | None]:
    """Read one identity; only a definitive 404 means absent."""
    return _get(url, token, transport=transport)


def definitions_match(desired: dict[str, Any], current: dict[str, Any]) -> bool:
    return _definition(desired) == _definition(current)

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 or Microsoft.

Download ZIP

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