agentleFS
Sign inStart free
FullFranFullFran/Agent-skills-POC/.agents/skills/ai-orchestration-patterns/SKILL.md

ai-orchestration-patterns

Skill1 starsChanged 10 months agoMITView on GitHub

Apply AI orchestration patterns (routing, tool use, ReAct, fallbacks) to design reliable agent flows.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Prefer explicit tool schemas and clear system instructions.

    line 19
  2. Distinctive:

    Add guardrails: timeouts, max steps, and safe fallbacks.

    line 20
  3. Distinctive:

    Keep tool routing in services (not endpoints).

    line 24
  4. Distinctive:

    Add conservative fallbacks when tool support is missing.

    line 26

≈ “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

AI Orchestration Patterns

When to use

  • Designing agent flows, tool calling, or multi-step reasoning.
  • Adding fallbacks, routing, or safety checks for LLM behavior.
  • Improving observability and determinism of agent outcomes.

Core guidance

  • Separate decisioning from execution (planner vs. tool runner).
  • Prefer explicit tool schemas and clear system instructions.
  • Add guardrails: timeouts, max steps, and safe fallbacks.
  • Log decisions with enough context for debugging.

Do

  • Keep tool routing in services (not endpoints).
  • Define tool schemas close to the agent logic in src/services/.
  • Add conservative fallbacks when tool support is missing.

Don't

  • Let LLMs call tools without validation of arguments.
  • Mix orchestration logic into src/endpoints/.
  • Skip logging of tool calls, queries, and chosen paths.

Anti-patterns seen

  • Hidden state in scratchpads without logging.
  • Tool selection coupled to provider-specific formats.
  • Unlimited loops without max_steps or timeouts.

Repo anchors

  • src/services/agent_service.py
  • src/services/rag_service.py
  • src/services/context_builder.py

References

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