foundry-iq
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.
- License 许可
- MIT
- 所属仓库
- microsoft/skills
- 最近更新
- 2026-11-14
- Stars
- ★ 3.2k
- Forks
- 368
01 前言 Front Matter
- name
- foundry-iq
- license
- MIT
- metadata
- { "author": "Microsoft", "version": "0.2.3" }
- description
- 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.
- compatibility
- Azure
02 资源文件 84
- 参考文档agents/connect-hosted-toolbox.md7.8 KB
- 参考文档agents/connect-hosted.md7.8 KB
- 参考文档agents/connect-prompt-sdk-fallback.md7.8 KB
- 参考文档agents/connect.md7.8 KB
- 参考文档agents/create-missing-agent.md7.8 KB
- 脚本helpers/_blob_observation.py4.4 KB
- 脚本helpers/_blob_source_read.py39.5 KB
- 脚本helpers/_bootstrap_io.py30.1 KB
- 脚本helpers/_cleanup_dependencies.py27.5 KB
- 脚本helpers/_cleanup_receipts.py13.5 KB
- 脚本helpers/_common.py36.2 KB
- 脚本helpers/_document_adapters.py15.0 KB
- 脚本helpers/_document_limits.py3.9 KB
- 脚本helpers/_embedding.py7.0 KB
- 脚本helpers/_file_inventory.py24.4 KB
- 脚本helpers/_file_source_config.py15.6 KB
- 脚本helpers/_indexer_observation.py7.1 KB
- 脚本helpers/_initial_prompt.py12.5 KB
- 脚本helpers/_private_json.py2.4 KB
- 脚本helpers/_progress.py12.1 KB
- 脚本helpers/_prompt_read.py17.7 KB
- 脚本helpers/_search_read.py6.0 KB
- 脚本helpers/_source_readback.py1.6 KB
- 脚本helpers/blob_inventory.py17.1 KB
- 脚本helpers/blob_recheck.py64.6 KB
- 脚本helpers/blob_source.py35.8 KB
- 参考文档helpers/blob-contracts.md7.8 KB
- 参考文档helpers/blob-cu-contracts.md7.8 KB
- 脚本helpers/bootstrap_azure.py41.5 KB
- 参考文档helpers/bootstrap-contracts.md7.8 KB
- 脚本helpers/cleanup_plan.py41.4 KB
- 参考文档helpers/contracts.md7.8 KB
- 脚本helpers/cu_ingestion_auth.py12.5 KB
- 脚本helpers/document_assess.py14.0 KB
- 参考文档helpers/document-assessment.md7.8 KB
- 脚本helpers/file_cu_canary.py32.7 KB
- 脚本helpers/file_cu_mi.py9.6 KB
- 脚本helpers/file_ingest.py15.4 KB
- 脚本helpers/file_source.py31.7 KB
- 脚本helpers/file_upload.py53.7 KB
- 参考文档helpers/file-upload-recovery.md7.8 KB
- 脚本helpers/hosted_connect.py30.8 KB
- 参考文档helpers/kb-contracts.md7.8 KB
- 脚本helpers/knowledge_base_retrieve.py7.7 KB
- 脚本helpers/model_discovery.py23.7 KB
- 参考文档helpers/model-discovery-contracts.md7.8 KB
- 参考文档helpers/model-discovery-scopes.md7.8 KB
- 脚本helpers/private_artifacts.py4.8 KB
- 参考文档helpers/private-artifacts.md7.2 KB
- 脚本helpers/prompt_cleanup.py22.0 KB
- 脚本helpers/prompt_connect.py62.3 KB
- 参考文档helpers/requirements-assessment.txt103 B
- 脚本helpers/retrieval_verify.py19.6 KB
- 参考文档helpers/retrieval-verification-contracts.md7.8 KB
- 脚本helpers/search_intake.py18.4 KB
- 脚本helpers/search_reconcile.py59.7 KB
- 参考文档helpers/search-intake-contracts.md7.6 KB
- 脚本helpers/source_vector.py33.2 KB
- 参考文档helpers/throttle-recovery.md5.0 KB
- 参考文档helpers/vector-contracts.md7.8 KB
- 参考文档knowledge-bases/create.md8.1 KB
- 参考文档knowledge-bases/retrieve.md7.8 KB
- 参考文档knowledge-sources/create-azure-blob.md7.8 KB
- 参考文档knowledge-sources/create-file.md7.8 KB
- 参考文档lifecycle/cleanup.md7.8 KB
- 参考文档references/abstention.md1.0 KB
- 参考文档references/blob-binding-evidence.md7.8 KB
- 参考文档references/blob-indexer-observation.md7.7 KB
- 参考文档references/blob-ingestion-progress.md6.5 KB
- 参考文档references/blob-readiness-recheck.md7.8 KB
- 参考文档references/blob-vector-readiness.md2.6 KB
- 参考文档references/bootstrap-azure.md7.8 KB
- 参考文档references/content-fit.md7.8 KB
- 参考文档references/cu-ingestion.md7.8 KB
- 参考文档references/file-cu-canary.md7.8 KB
- 参考文档references/intent-routing.md7.7 KB
- 参考文档references/owner.md2.1 KB
- 参考文档references/platform-contracts.md7.7 KB
- 参考文档references/platform-interfaces.md7.8 KB
- 参考文档references/resource-intake.md7.8 KB
- 参考文档references/search-substrate.md7.8 KB
- 参考文档references/standard-cu.md7.8 KB
- 参考文档search-services/create.md7.8 KB
- 参考文档troubleshooting/diagnose.md8.7 KB
03 SKILL.md 正文
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.
04 同仓库更多 Skills
azure-advisor-cost-optimization
Analyze Azure Advisor Cost/IdleResources findings and prevalidate deletion safety, including Service Groups. WHEN: "find unused Azure resources", "what resources am I paying for but no longer using", "idle-resource savings", "historical idle-resource savings", "are these idle resources safe to delete". Generic Cost, other subcategories, and cross-category requests use azure-advisor.
skill-creator
Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.
podcast-generation
Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.
microsoft-docs
Understand Microsoft technologies by querying official documentation. Use whenever the user asks how something works, wants tutorials, needs configuration options, limits, quotas, or best practices for any Microsoft technology (Azure, .NET, M365, Windows, Power Platform, etc.)—even if they don't mention "docs." If the question is about understanding a concept rather than writing code, this is the right skill.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP), Node/TypeScript (MCP SDK), or C#/.NET (Microsoft MCP SDK).
kql
KQL language expertise for writing correct, efficient Kusto Query Language queries. Covers syntax gotchas, join patterns, dynamic types, datetime pitfalls, regex patterns, serialization, memory management, result-size discipline, and advanced functions (geo, vector, graph). USE THIS SKILL whenever writing, debugging, or reviewing KQL queries — even simple ones — because the gotchas section prevents the most common errors that waste tool calls and cause expensive retry cascades. Trigger on: KQL, Kusto, ADX, Azure Data Explorer, Fabric Real-Time Intelligence, EventHouse, Log Analytics, log analysis, data exploration, time series, anomaly detection, summarize, where clause, join, extend, project, let statement, parse operator, extract function, any mention of pipe-forward query syntax.