gpt-5-4-prompting
gpt-5-4-prompting is a Prompt design & optimisation skill for AI agents, published by openai in the codex-plugin-cc repository on GitHub. Skillspace rates gpt-5-4-prompting C (72/100) and it passed the safety scan; a judge model has also reviewed it.
Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin
- Grade
- C
- Quality
- 72 / 100
- Safety
- Passed
- GitHub stars
- 28,823
Placed #2 of 6 in the judged category final for Prompt design & optimisation.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 96 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Apache-2.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Vendor-specific: built around one product. Prompting Codex/GPT-5.4, a public product, from its plugin repo
Judge review
Placed #2 of 6 in the judged category final for Prompt design & optimisation.
- Trigger
72 72 - Instructions
88 88 - Specificity
88 88 - Safety
85 85 - Disclosure
90 90 - Maintenance
78 78
A tight, principled prompt-composition guide with a genuine tag-based contract system and an exemplary three-way reference split into blocks, recipes, and antipatterns.
Not checked yet
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.