agentleFS
MicrosoftKnown publishermicrosoft/bobsql/.github/skills/sqlserver2025/SKILL.md

sqlserver2025

Skill1 starsChanged 12 days agoMITView on GitHub

Select SQL Server 2025 demos for AI embeddings/vector search, JSON, regex, REST, optimized locking, tempdb Resource Governor, ABORT_QUERY_EXECUTION, or ZavaHospital with NVIDIA NIM. Use when working with examples/sqlserver2025.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the collection README and the chosen feature's local instructions.

    line 10
  2. Distinctive:

    Verify SQL Server 2025 build/edition, compatibility level, sample database, and feature prerequisites.

    line 13
  3. Distinctive:

    Follow the selected script/session sequence.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

SQL Server 2025 demonstration collection

Procedure

  1. Read the collection README and the chosen feature's local instructions. For AI, select the intended provider: Azure AI, OpenAI-compatible endpoints, Ollama, or ONNX.
  2. Verify SQL Server 2025 build/edition, compatibility level, sample database, and feature prerequisites. Inspect current source for actual model names, endpoint contracts, and dimensions rather than assuming old prose is current.
  3. Review changes and obtain approval before database writes, configuration changes, model deployment/download, credential setup, stress workloads, or cloud spending. Keep API keys and master-key secrets outside source.
  4. Follow the selected script/session sequence. Validate the specific feature: query hints, JSON/regex behavior, locking evidence, resource limits, vector index/search results, or REST/model responses.
  5. For ZavaHospital, complete NIM/GPU deployment, readiness, DNS/TLS, and SQL endpoint tests first. Then run database build stages before presentation scripts. Use synthetic data only; generated responses are not clinical advice.
  6. Report observed outputs and failures. Follow the selected cleanup with approval; do not remove shared databases, model services, or AKS resources.

AI providers have different network/privacy and runtime requirements. Do not claim offline behavior or data locality without checking the actual execution path. Follow secret checks.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.