RetentaRetenta

Evidence record · captured 2026-10-10

OpenAI Docs

An official-source workflow for current OpenAI API guidance, Codex self-knowledge, model selection, and bounded fallback when documentation does not establish a claim.

Official publisherUnverifiedSource reviewedBehavior not tested
Source review

Editorial assessment

This is a source-only assessment. It does not claim runtime or security testing.

What it does

The source defines a strict evidence route: current OpenAI docs for API questions, a fetched manual for broad Codex questions, schema tools for exact API shapes, and bounded uncertainty instead of unsupported claims.

Best for

  • Current OpenAI API and product guidance
  • Codex setup, customization, skills, plugins, and MCP questions
  • Model-selection or named-model migration planning

Strengths in the source

  • Separates Codex manual evidence, developer docs, API schema, and web fallback by claim type.
  • Preserves explicitly requested model targets instead of silently chasing the newest model.
  • Defines stopping conditions when official sources do not establish private or rollout-specific terminology.

Limitations

  • The workflow is intentionally limited to OpenAI products and official sources.
  • Its Codex path relies on helper scripts, temporary caching, and documentation services that may be unavailable.
  • The long routing logic adds overhead for simple, stable questions.
  • The pinned publisher repository is deprecated in favor of OpenAI's plugins repository, so confirm the current distribution path before adopting it.

When not to use it

  • Generic software work that only happens to mention Codex
  • Cross-provider research that requires non-OpenAI sources

Reviewed by Retenta editorial on 2026-10-10; scope: source only.

Files included in this review
  • skills/.curated/openai-docs/SKILL.md
  • README.md
  • skills/.curated/openai-docs/LICENSE.txt

Evidence and boundaries

Execution · not tested

Retenta reviewed the pinned source but did not install or execute this skill.

Security · not tested

No sandbox run, dependency audit, or independent security assessment is claimed.

Revision
49f948faa9258a0c61caceaf225e179651397431
License evidence
Apache-2.0The pinned skill directory includes an Apache License, Version 2.0 LICENSE.txt.
Last source change
2026-06-17
Independent verification
The source is controlled by OpenAI; Retenta has not independently verified its runtime behavior or security.
Upstream repository
Open publisher repository

Compatibility

Codex

documented

OpenAI's repository documents curated skills for Codex and installation through the built-in skill installer.

Requirements and access

  • OpenAI developer-docs tools or official-domain browsing
  • A writable temporary cache for the preferred Codex manual helper
  • A clearly scoped OpenAI product question

Referenced tools

OpenAI developer docs MCPCodex manual helperOfficial OpenAI web fallback

Install from the source

The pinned README documents name-based installation for curated skills and says to restart Codex. It also marks this repository deprecated in favor of OpenAI's plugins repository, so confirm the current path before adopting it.

Download the pinned SKILL.md Apache-2.0 license text
Verify the publisher's install documentation

More Docs and writing skills →

Codex skill installer

$skill-installer openai-docs

Thyme RAG Capsules

Add OpenAI Docs to a capsule in one click.

Every capsule's dashboard lists this skill. Add it, and it becomes searchable next to your own documents from every agent you connect, with its source and license attached.

Create a capsule with this skillUnderstand the evidence labels