agentleFS
magnus919magnus919/agent-skills/spring-ai/SKILL.md

spring-ai

Skill177 starsChanged 4 months agoMITView on GitHub

Diagnose and operate Spring AI projects with version-aware Maven or Gradle checks for ChatClient, advisors, retrieval, conversation memory, tool/MCP boundaries, streaming, configuration, and observability. Use for setup compatibility, local smoke checks, and failure triage; do not use for provider-specific model evaluation, general Java/Spring development, security threat modeling, or production rollout governance.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the checker and retain its JSON output with the project revision.

    line 35
  2. Distinctive:

    Keep prompt/completion logging disabled by default in production.

    line 41
  3. Distinctive:

    Run the project’s own tests/build when dependencies and provider credentials are available.

    line 42
  4. Very specific:

    Stop when the project’s build/config/source facts, findings, owner routes, and limitations are recorded, or when an external dependency …

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Spring AI

Use this operational skill to inspect a real Maven or Gradle Spring AI project before changing it. The included diagnostic CLI is offline and provider-neutral: it reads build files, application configuration, and source to report compatibility clues, unsafe defaults, missing conversation IDs, streaming prerequisites, tool/MCP boundaries, retrieval configuration, and observability risks. It never sends prompts or exposes API-key values.

Entry check

Confirm the project root and whether the task is read-only or will modify configuration/code. Read-only diagnosis can proceed. Before the first state-changing action, confirm the target project, scope, and rollback path (usually a reviewed commit or revert); the CLI itself is read-only.

Run:

python3 spring-ai/scripts/spring_ai_check.py --root /path/to/project --json

The result is stable JSON with status, project, facts, findings, and errors. Exit 0 means no error-severity finding; exit 1 means an error-severity finding or warnings promoted by --strict; exit 2 means an invalid invocation or unreadable project.

Workflow

  1. Run the checker and retain its JSON output with the project revision.
  2. Resolve build compatibility findings against the official Spring AI and Spring Boot documentation in references/source-index.md; do not infer support from a transitive dependency alone.
  3. Inspect ChatClient advisor order and parameters. Every memory-advisor call needs an explicit conversation identifier derived from the application’s authenticated/session boundary; never use a shared default.
  4. For retrieval, verify document ownership/authorization before retrieval context enters a prompt. Test empty retrieval, stale data, provider errors, and latency separately.
  5. For tools and MCP, treat model tool requests as untrusted proposals. The application owns authorization and execution. Bound tool names, arguments, timeout, retry, side effects, and audit fields. Verify MCP transport and schema against the current project dependency.
  6. For streaming, preserve partial output as provisional until completion; test cancellation, timeout, disconnect, and failed completion. Do not treat a partial stream as a committed answer or side effect.
  7. Keep prompt/completion logging disabled by default in production. If enabled temporarily, document redaction, access, retention, and rollback.
  8. Run the project’s own tests/build when dependencies and provider credentials are available. The checker does not prove provider connectivity, model quality, RAG correctness, or production readiness.

Scope and routing

  • ChatClient/advisors, Spring configuration, local diagnostics, and framework troubleshooting belong here.
  • Model quality, evaluator design, statistical comparisons, and trace schemas belong to agent-evals-and-observability.
  • Authority, fallback, disablement, budgets, and rollout belong to agent-production-operations.
  • Threat modeling and security implementation belong to secure-software-engineering.
  • General Java/Spring application design belongs to the relevant engineering skill.

Version posture

The official documentation currently presents Spring AI 2.0.1 as the latest stable line and retains a 1.0 reference (1.0.9). APIs differ across lines: for example, current 2.0 documentation describes ToolCallingAdvisor as the ChatClient tool loop, while 1.x applications may use model-internal tool loops. The checker reports observed versions and flags uncertainty; it does not rewrite dependencies or claim that a version combination is supported without a primary compatibility source. Re-check references/source-index.md and release notes when upgrading.

Completion

Stop when the project’s build/config/source facts, findings, owner routes, and limitations are recorded, or when an external dependency (provider credentials, unavailable build tool, private artifact repository) is explicitly marked blocked. Do not claim a successful live smoke test from static diagnostics.

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.