agentleFS
Sign inStart free
1tomany1tomany/agent-skills/symfony-ai/SKILL.md

symfony-ai

Skill0 starsChanged 35 days agoMITView on GitHub

Use when working with Symfony AI documentation or implementing integrations with LLM providers such as OpenAI, Anthropic, or Google Gemini embeddings, structured output, tool calling, streaming, multimodal input, or AI Bundle platform/agent configuration.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for Symfony AI provider work.

    line 11
  2. Very specific:

    Read references/docs.md to pick the relevant official Symfony AI docs.

    line 13
  3. Very specific:

    Prefer Symfony AI Bundle configuration in config/packages/ai.yaml for Symfony apps.

    line 16
  4. Distinctive:

    Keep provider secrets in the Symfony Secrets component.

    line 17
  5. Distinctive:

    Add tests with fake/in-memory platforms or mocked clients where practical.

    line 18
  6. Very specific:

    Use ai.platform.<provider> service IDs from the AI Bundle when wiring agents, vectorizers, or stores.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Symfony AI

Workflow

Use this skill for Symfony AI provider work. Treat Symfony AI as fast-moving: verify current official docs before changing code or giving definitive configuration advice.

  1. Read references/docs.md to pick the relevant official Symfony AI docs.
  2. Browse the selected official docs pages before implementing provider-specific behavior.
  3. Inspect the local project for existing Symfony AI, Gemini, LLM, HTTP client, env var, and service configuration patterns.
  4. Prefer Symfony AI Bundle configuration in config/packages/ai.yaml for Symfony apps. Use the standalone Platform component only when the project already uses it directly or the task explicitly asks for component-level code.
  5. Keep provider secrets in the Symfony Secrets component. DO NOT hard-code API keys, model names tied to private deployments, tenant IDs, or endpoints.
  6. Add tests with fake/in-memory platforms or mocked clients where practical. Avoid tests that call live LLM APIs unless the user explicitly asks for integration testing.

Implementation notes

  • Use ai.platform.<provider> service IDs from the AI Bundle when wiring agents, vectorizers, or stores.
  • For Google Gemini, start from ai.platform.gemini configuration and GEMINI_API_KEY unless existing project conventions say otherwise.
  • For tool calling, read the Agent and AI Bundle tool sections; register application tools with #[AsTool] and restrict injected tools per agent when broad access is not intended.
  • For structured extraction, prefer Symfony AI structured output support when the provider/model supports it, and still validate returned data in application code. Additionally, use PHP DTO classes to define structured output schemas:
  • For RAG or embeddings, read Platform embeddings, Store, Vectorizer, and Indexer docs together; the provider config alone is not enough.

Project fit

In this repository, respect the RICH module pattern and existing Symfony conventions. Place business behavior in module handlers/services instead of controllers, use immutable DTOs where data crosses boundaries, and run the project’s normal validation command when code changes are made.

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.

Check your setup, free