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://autogineer.com/agent-skills/microsoft/foundry-iq/downloadUnzip 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
references/content-fit.md
Content-fit intake for ingestion
Read when File or Blob/ADLS content/answer needs are unknown or a mode conflicts with the goal, even if a processing mode was explicitly named. Honor explicit processing choices only when informed and compatible with the confirmed outcome; reuse known content descriptions and answer needs without asking again. Explain a known mismatch and clarify before planning: never override the choice or silently reduce the requested outcome. Unknown content requires assessment before a recommendation, even if the user already confirmed a technical plan. Neither suffix/MIME nor inventory metadata establishes suitability; service-detected file type remains admission authority.
Text-only can use hybrid; multimodal can use keyword-only.
Explicit choice checks
| Request | Before planning |
|---|---|
| Minimal; unknown PDF content | Assess via consented samples or questions. |
| Minimal; visual answers needed | Clarify supported outcome, no silent omissions/override. |
| Informed text-only reduced outcome | Preserve exclusions/admission checks; do not reask. |
| Use Standard to interpret trends in charts. | Planner verbalization is off: disclose limits; explicit supported reduced outcome or handoff, no flag/model escalation. |
Two routes, not a file-sharing requirement
Offer: "I can inspect a few representative samples you authorize, or you can describe the content."
Primary question: "Are these documents text-only, or do they contain multimodal content such as images, charts, diagrams, tables or meaningful page layout?" Options: text-only / multimodal / mixed-or-unsure. For mixed-or-unsure, offer authorized inspection or questions, never require file sharing. A born-digital/searchable PDF is not synonymous with text-only. Searchable text may coexist with answer-critical visual/layout information.
Only if answer dependence is not already known, ask separately: "Do the answers you need depend on visual or layout information, rather than text alone?" Use answer-dependence labels text alone, OCR + table/layout relationships, or chart/diagram/image interpretation (verbalization off in this planner profile). Reuse informed answers; do not repeat this question. Scans are one example of image-based content, not the primary taxonomy. OCR/searchable-text availability is a secondary conditional follow-up only when needed to resolve extraction suitability, not the opening content question.
Description: a useful answer is sufficient; do not force files or repeat answered questions. Ask only unresolved figure/table answer needs. A searchable PDF can still need visual extraction.
Samples: agree exact local paths, file/page count, byte/output limits, inspection purpose and permitted content exposure first. Use only available, supported local read-only viewers/parsers. Only when document inspection is selected, read bounded document assessment: declared adapters, exact scope/hash, whole-file metadata consent, time/memory limits and counts only; no text viewer on PDF binary. Dependency installation needs separate approval, never ad-hoc tooling. Never execute scripts/macros, extract archives to disk or follow links. Other approved text samples need host-appropriate quoting and byte/output bounds; line count alone is not a byte bound. If no safe supported viewer can inspect the needed structure, use the description route. For Blob/ADLS ask for customer-provided local representative copies; do not download blobs to decide. Never scan/download an entire container or widen the selected root/prefix. Metadata discovery is not content inspection consent. Never upload samples to CU, embeddings or chat-model services just to choose. Do not retain raw sample content in plans, logs or summaries.
Mixed content: cover each relevant content family and answer-critical structure, not just the first/easiest text file. Ask how representative the samples are; describe uninspected portions and uncertainty. A small sample is not corpus-wide extraction proof.
Inspection unavailable, declined or unreadable: ask whether content is text-only / multimodal / mixed-or-unsure, not searchable versus scanned. Only if unknown, ask separately whether answers need text alone, OCR + table/layout relationships, or chart/diagram/image interpretation (verbalization off in this planner profile). Reuse informed answers; no inspection/upload is required. Never infer text-only from failure, refusal or no samples. If content/answer needs remain unknown, leave processing unresolved and pause source planning; no automatic Minimal or forced file sharing.
Recommend, then approve
| Capability | Minimal | Standard: typed File/Blob |
|---|---|---|
| Basic text/existing text captions | Supported text, not image interpretation | Text extraction |
| Layout/tables | Relationships surviving text | CU layout to Markdown; imperfect |
| OCR | Not added | CU-supported; no accuracy guarantee |
| AI-generated image captions | Off | Off; broader CU supports descriptions with ingestion chat |
| Chart/diagram interpretation | Not promised | Not promised; reduced outcome/handoff |
Input profile (text-only/multimodal/unknown) differs from indexed Markdown. Text output cannot prove text-only input; counts do not select a mode.
Recommend Minimal when supported searchable text supplies the needed answers, including ordinary text tables whose relationships survive text extraction. Minimal avoids additional CU cost, dependencies and processing latency; Search/ingestion and selected embeddings still cost.
Recommend Standard (Content Understanding) for answer-critical OCR or
table/layout relationships that the selected operation may support, subject to
supported formats and the source-specific recipe. It already extracts structured
Markdown/text chunks; no generated .md file or perfect table/chart extraction
is promised. Explain billable CU, potentially higher
processing latency, required region/configuration/access, data movement and
retention. Standard is not universally better; images/tables/extensions alone do
not select it. No timing/quality guarantee.
Label Standard: OCR/layout to Markdown; image descriptions off in this planner
profile. These typed planners set disableImageVerbalization: true and omit
chatCompletionModel; this is not
a CU service-wide limitation. Optional image descriptions also yield text, but
need an ingestion chat-model purpose, not necessarily a new deployment.
Source embeddings and KB synthesis chat remain separate. Multimodal input alone
requires neither verbalization nor KB chat. For unsupported visual answer needs,
clarify a supported outcome or handoff; no hidden model calls.
Never automatically enable image verbalization or add/escalate a chat model.
State the observed or customer-described basis, coverage/uncertainty, recommended mode and tradeoff in user terms; retain that rationale with the workflow handoff, not a fabricated helper evidence boolean. Ask only the unresolved mode decision. Cost refusal, denied permissions or unavailable CU blocks that choice; explain limitations and alternatives, but never silently downgrade. A customer may explicitly choose a supported reduced outcome after learning its limitations.
Selection and sample consent are not ingestion/dependency consent. Return to the source owner's concrete-plan approval and applicable CU/data-movement approvals before writes; never auto-provision CU, change local auth, enable preview or widen data boundaries. File standard uses verified MI or approved keys/August preview; Blob CU uses existing keyless dependencies/GA or selected preview, ADLS preview. Do not transplant recipes. Extraction is independent of lexical/vector indexing, KB reasoning/synthesis and agent models; no model calls to make this decision.
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.
Related skills
Claude API
AnthropicOfficial
Comprehensive reference for integrating Anthropic's Claude API, SDKs, and Managed Agents into your applications.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository188.6k
Transformers
K-Dense· Community
Integrate Hugging Face Transformers for model loading, inference, and fine-tuning across NLP, vision, and audio tasks.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITLow riskGitHub stars of the source repository56.4k
Open Notebook
K-Dense· Community
Integrate with the self-hosted Open Notebook platform to automate research ingestion, context-aware chat, and AI-driven analysis.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITLow riskHas scriptsGitHub stars of the source repository56.4k
Vision Sft
Seth Hobson· Community
A structured workflow for supervised fine-tuning of vision-language models, focusing on adapter configuration and silent failure prevention.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository42.3k
LLM Evaluation
Seth Hobson· Community
A comprehensive framework for evaluating LLM application performance using automated metrics, human feedback, and LLM-as-a-judge techniques.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository42.3k
Lora Qlora Recipes
Seth Hobson· Community
Provides configuration recipes and best-practice hyperparameters for LoRA and QLoRA supervised fine-tuning.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository42.3k
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download foundry-iq.zip