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/knowledge_base_retrieve.py

from __future__ import annotations

import argparse
import json
import shutil
import subprocess
import sys
from pathlib import Path
from typing import Any
from urllib.parse import quote

try:
    from ._common import (
        SEARCH_AUDIENCE, HelperFailure, HttpResult, TokenProvider, Transport,
        azure_cli_token, blocked_result, emit_result, http_request,
        reject_secrets, require_allowed_fields, validate_search_endpoint,
    )
except ImportError:
    from _common import (  # type: ignore[no-redef]
        SEARCH_AUDIENCE, HelperFailure, HttpResult, TokenProvider, Transport,
        azure_cli_token, blocked_result, emit_result, http_request,
        reject_secrets, require_allowed_fields, validate_search_endpoint,
    )


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


def _invalid(message: str) -> HelperFailure:
    return HelperFailure("input-schema-invalid", message, blocked_at="input-resolution")


def _target(endpoint: Any, name: Any, api_version: Any) -> str:
    if not isinstance(api_version, str) or api_version not in API_VERSIONS:
        raise _invalid("Unsupported API version.")
    if not isinstance(name, str) or not name.strip() or any(ord(c) < 32 for c in name):
        raise _invalid("An exact nonempty resource name is required.")
    try:
        return validate_search_endpoint(endpoint)
    except ValueError as exc:
        raise _invalid("Invalid Search endpoint.") from exc


def retrieval_request(
    endpoint: str, name: str, api_version: str, effort: str, query: str,
) -> tuple[str, str, dict[str, Any]]:
    base = _target(endpoint, name, api_version) + "/knowledgebases"
    if not isinstance(effort, str) or effort not in {"minimal", "low", "medium"}:
        raise _invalid("Unsupported reasoning effort.")
    if api_version == "2026-04-01" and effort != "minimal":
        raise _invalid("GA requires minimal retrieval.")
    if not isinstance(query, str) or not query.strip():
        raise _invalid("A nonempty query is required.")
    definition_url = base + "('" + quote(name.replace("'", "''"), safe="") + "')"
    retrieve_url = base + "/" + quote(name, safe="") + "/retrieve"
    suffix = "?api-version=" + api_version
    body = (
        {"intents": [{"type": "semantic", "search": query}]}
        if effort == "minimal" else
        {"messages": [{"role": "user", "content": [{"type": "text", "text": query}]}]}
    )
    return definition_url + suffix, retrieve_url + suffix, body


def read_json(
    method: str, url: str, body: dict[str, Any] | None = None,
    forward_permissions: bool = False, *,
    token_provider: TokenProvider = azure_cli_token,
    transport: Transport = http_request,
) -> HttpResult:
    token = token_provider(SEARCH_AUDIENCE)
    headers = {"Content-Type": "application/json"}
    if forward_permissions:
        headers["x-ms-query-source-authorization"] = token
    result = transport(
        method, url, token,
        body=json.dumps(body).encode("utf-8") if body is not None else None,
        headers=headers, follow_redirects=False, max_response_bytes=5 * 1024 * 1024,
    )
    if result.status != 200 or not isinstance(result.body, dict):
        raise HelperFailure(
            "retrieval-incomplete", "Expected complete JSON response.",
            blocked_at="verification", status=result.status, request_id=result.request_id,
        )
    return result


def _verify_signed_in_user() -> None:
    executable = shutil.which("az")
    if executable is None:
        raise HelperFailure(
            "azure-cli-unavailable", "Azure CLI is required for keyless authentication.",
            blocked_at="execution",
        )
    try:
        result = subprocess.run(
            [executable, "account", "show", "--query", "user.type", "--output", "tsv"],
            check=True, capture_output=True, text=True, timeout=60,
        )
    except (OSError, subprocess.CalledProcessError, subprocess.TimeoutExpired) as exc:
        raise HelperFailure(
            "permission-forwarding-unavailable", "Could not verify the signed-in user.",
            blocked_at="input-resolution",
        ) from exc
    if result.stdout.strip().casefold() != "user":
        raise HelperFailure(
            "permission-forwarding-unavailable", "Permission forwarding requires a signed-in user.",
            blocked_at="input-resolution",
        )


def execute(
    document: Any, *, token_provider: TokenProvider = azure_cli_token,
    transport: Transport = http_request,
) -> dict[str, Any]:
    if not isinstance(document, dict):
        raise _invalid("Input must be a JSON object.")
    reject_secrets(document)
    operation = document.get("operation")
    if not isinstance(operation, str) or operation not in {
        "get-knowledge-base", "get-knowledge-source", "retrieve",
    }:
        raise _invalid("Choose get-knowledge-base, get-knowledge-source, or retrieve.")
    fields = {"operation", "endpoint", "name", "api_version"}
    if operation == "retrieve":
        fields |= {"effort", "query", "forward_permissions"}
    require_allowed_fields(document, fields, label="read-only request")
    endpoint = _target(document.get("endpoint"), document.get("name"), document.get("api_version"))
    name, api_version = document["name"], document["api_version"]
    body = None
    forwarding = False
    if operation == "retrieve":
        forwarding = document.get("forward_permissions")
        if type(forwarding) is not bool:
            raise _invalid("Explicit forward_permissions true or false is required.")
        _, url, body = retrieval_request(
            endpoint, name, api_version, document.get("effort"), document.get("query"),
        )
        if forwarding:
            _verify_signed_in_user()
        method = "POST"
    else:
        collection = "knowledgebases" if operation == "get-knowledge-base" else "knowledgesources"
        url = endpoint + "/" + collection + "('" + quote(name.replace("'", "''"), safe="") + "')"
        url += "?api-version=" + api_version
        method = "GET"
    result = read_json(
        method, url, body, forwarding, token_provider=token_provider, transport=transport,
    )
    return {
        "status": "response-received", "operation": operation, "mutation": "none",
        "writes_performed": [], "http_status": result.status, "request_id": result.request_id,
        "response_body": result.body, "verification": "not-performed", "cleanup": "not-applicable",
    }


def main(argv: list[str] | None = None) -> int:
    parser = argparse.ArgumentParser(description="Read Search KB/source definitions or retrieve from one KB.")
    parser.add_argument("--input", required=True, type=Path)
    args = parser.parse_args(argv)
    try:
        try:
            document = json.loads(args.input.read_text(encoding="utf-8"))
        except OSError as exc:
            raise HelperFailure("input-unreadable", "Input file cannot be read.", blocked_at="input-resolution") from exc
        except (UnicodeError, json.JSONDecodeError) as exc:
            raise HelperFailure("input-invalid-json", "Input must be UTF-8 JSON.", blocked_at="input-resolution") from exc
        result = execute(document)
    except HelperFailure as failure:
        # POST retrieve is read-only even when the generic transport marks it ambiguous.
        readonly_failure = HelperFailure(
            failure.code, failure.message, blocked_at=failure.blocked_at,
            status=failure.http_status, request_id=failure.request_id,
        )
        result = blocked_result(readonly_failure, outcome="knowledge-base-retrieval", fingerprint=None)
        result.update(
            mutation="none", cleanup="not-applicable",
            safe_next_decision="Resolve the first blocker before repeating this read-only request.",
        )
        emit_result(result)
        return 2
    emit_result(result)
    return 0


if __name__ == "__main__":
    sys.exit(main())

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