foundry-iq skill
✓ OfficialscriptsCreate, diagnose, and connect knowledge bases to agents using local files, Blob storage, or multi-source configurations.
- GitHub stars
- 1,636
- Files
- 85
- Last commit
- Nov 11, 2026
- License
- MIT
- Allowed tools
- —
What does the foundry-iq skill do?
foundry-iq is an agent skill. Create, diagnose, and connect knowledge bases to agents using local files, Blob storage, or multi-source configurations.
Summary generated from the skill's SKILL.md.
About the foundry-iq skill
Developers building intelligent agents can use this skill to manage knowledge bases by making local files or Blob storage documents searchable. It allows for the creation, diagnosis, and connection of knowledge bases to agents, supporting multi-source configurations and the setup of search services. When an agent needs to retrieve information with citations, it uses these tools to access existing knowledge bases.
An agent should load this skill when it needs to create a new knowledge base, connect an existing one to an agent, or troubleshoot unsupported connectors. The skill provides specific tools like File for local knowledge sources, Blob for Azure Blob or ADLS sources, and Query for retrieving information from established knowledge bases. It distinguishes between simple connections and complex reconfigurations, using the Diagnose tool to handle unsupported provisioning or multi-source setup requests instead of attempting silent execution.
What an agent can do with it
- 1Make local files searchableAn agent can transform a collection of local documents into a searchable knowledge source.
- 2Connect existing knowledge to agentsA developer can instruct an agent to link a previously established knowledge base to a new agent.
- 3Troubleshoot configuration errorsWhen a multi-source knowledge base creation fails or a connector is unsupported, the agent uses diagnostic tools to find the boundary.
- 4Retrieve information with citationsAn agent can pull specific data from a knowledge base while providing the necessary citations.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the foundry-iq skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the foundry-iq skill in Plugin
/plugin marketplace add microsoft/azure-skills /plugin install foundry-iq-skills@azure-skills
Install the foundry-iq skill in Claude Code
~/.claude/skills/foundry-iq/SKILL.md
$ npx degit microsoft/azure-skills/.github/plugins/foundry-iq-skills/skills/foundry-iq ~/.claude/skills/foundry-iqInstall the foundry-iq skill in Claude Code (project)
.claude/skills/foundry-iq/SKILL.md
$ npx degit microsoft/azure-skills/.github/plugins/foundry-iq-skills/skills/foundry-iq .claude/skills/foundry-iqInstall the foundry-iq skill in Codex
~/.agents/skills/foundry-iq/SKILL.md
$ npx degit microsoft/azure-skills/.github/plugins/foundry-iq-skills/skills/foundry-iq ~/.agents/skills/foundry-iqInstall the foundry-iq skill in Gemini CLI
~/.gemini/skills/foundry-iq/SKILL.md
$ npx degit microsoft/azure-skills/.github/plugins/foundry-iq-skills/skills/foundry-iq ~/.gemini/skills/foundry-iqInstall the foundry-iq skill in Claude.ai
npx degit microsoft/azure-skills/.github/plugins/foundry-iq-skills/skills/foundry-iq foundry-iq && zip -r foundry-iq.zip foundry-iq # claude.ai → Customize → Skills → + → Create skill → Upload a skill → foundry-iq.zip
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A skill needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablemicrosoft/azure-skills/.github/plugins/foundry-iq-skills/skills/foundry-iq is public and reachablegithub.com/microsoft/azure-skills/tree/HEAD/.github/plugins/ ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/microsoft/azure-skills/commits ↗Pass
- No download-and-run or credential theft in scripts5 of 40 scripts read; none of them downloads and runs code, the rest were not readFinding
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/microsoft/azure-skills/blob/HEAD/.github/plugins/ ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/microsoft/azure-skills/blob/HEAD/.github/plugins/ ↗Pass
- SKILL.md follows the Agent Skills formatthe description does not say when to use the skillgithub.com/microsoft/azure-skills/blob/HEAD/.github/plugins/ ↗Finding
SKILL.md
View on GitHubFoundry 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 in this skill
85foundry-iq skill questions
How do I install the foundry-iq skill in Claude Code?
Run npx degit microsoft/azure-skills/.github/plugins/foundry-iq-skills/skills/foundry-iq ~/.claude/skills/foundry-iq. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the foundry-iq skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What should I do if I need to reconfigure a multi-source knowledge base or use an unsupported connector?
You should use the Diagnose procedure to identify boundaries and receive documentation pointers.
How do I connect an existing knowledge base to an agent without changing the KB?
Use the Connect operation to link an existing knowledge base with two or more sources to an agent.