Agent skill
openai-agent-tools
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/openai-agent-tools
SKILL.md
Skill: OpenAI Agent Tools
Purpose
Define reusable function tools for OpenAI Agents using the
OpenAI Agents SDK function_tool interface.
These tools expose external capabilities (RAG, databases, selection-based answering) to the agent without embedding reasoning logic.
Responsibilities
- Define tools using @function_tool
- Enforce strict input/output contracts
- Provide deterministic, side-effect-aware behavior
- Support Retrieval-Augmented Generation (RAG)
What This Skill Covers
- function_tool decorator usage
- Tool input schema design
- Tool output structure
- Tool naming conventions
What This Skill Does NOT Cover
- Agent reasoning or planning
- Prompt engineering
- UI concerns
Constraints
- Tools must not call LLMs
- Tools must not hallucinate
- Tools must return factual data only
Used By
- openai_agent_runtime
- RAG Orchestrator Agent
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?