openai-responses
Build agentic AI with OpenAI Responses API - stateful conversations with preserved reasoning, built-in tools (Code Interpreter, File Search, Web Search), and MCP integration. Prevents 11 documented errors. Use when: building agents with persistent reasoning, using server-side tools, or migrating from Chat Completions/Assistants for better multi-turn performance.
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill openai-responses75
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
N/ABased on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
Something went wrong
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, production-ready skill with excellent actionability - nearly every concept has executable TypeScript code. The progressive disclosure is well-handled with clear references to external resources. Main weaknesses are some verbosity (comparison tables, visual analogies) and missing explicit validation workflows for multi-step operations like migration or MCP setup.
Suggestions
Condense the comparison tables - the Chat Completions vs Responses table appears twice with overlapping information
Add explicit validation steps to the migration workflow (e.g., 'Verify conversation created successfully before proceeding')
Remove the 'Visual Analogy' section for reasoning preservation - Claude doesn't need metaphors to understand the concept
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary explanations (e.g., 'Visual Analogy' section, extensive comparison tables that could be condensed). The 'What Is the Responses API?' section explains concepts Claude likely knows. However, most content is information-dense and specific to this API. | 2 / 3 |
Actionability | Excellent executable code examples throughout - Quick Start, stateful conversations, MCP integration, migration examples are all copy-paste ready with specific imports, error handling patterns, and real TypeScript code. Known issues include specific error messages and working workarounds. | 3 / 3 |
Workflow Clarity | Multi-step processes like background mode polling and MCP approval handling are present but lack explicit validation checkpoints. The migration sections show before/after but don't provide a step-by-step migration workflow with verification steps. The 'Critical Patterns' section provides good guardrails but isn't structured as a workflow. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections, tables for quick reference, and explicit references to external resources (templates/, references/ files, official docs, GitHub issues). Content is appropriately split between overview and detailed sections. Navigation is easy with clear headings. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
68%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (548 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 11 / 16 Passed | |
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.