gpt-5-4-prompting

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

GPT-5.4 Prompting

GPT-5.4 提示词编写

Use this skill when

codex:codex-rescue

needs to ask Codex or another GPT-5.4-based workflow for help.

Prompt Codex like an operator, not a collaborator. Keep prompts compact and block-structured with XML tags. State the task, the output contract, the follow-through defaults, and the small set of extra constraints that matter.

Core rules:

Prefer one clear task per Codex run. Split unrelated asks into separate runs.
Tell Codex what done looks like. Do not assume it will infer the desired end state.
Add explicit grounding and verification rules for any task where unsupported guesses would hurt quality.
Prefer better prompt contracts over raising reasoning or adding long natural-language explanations.
Use XML tags consistently so the prompt has stable internal structure.

Default prompt recipe:

```
<task>
```
: the concrete job and the relevant repository or failure context.

<structured_output_contract>

<compact_output_contract>

: exact shape, ordering, and brevity requirements.

```
<default_follow_through_policy>
```
: what Codex should do by default instead of asking routine questions.
```
<verification_loop>
```
or
```
<completeness_contract>
```
: required for debugging, implementation, or risky fixes.
```
<grounding_rules>
```
or
```
<citation_rules>
```
: required for review, research, or anything that could drift into unsupported claims.

When to add blocks:

Coding or debugging: add

completeness_contract

verification_loop

, and

missing_context_gating

Review or adversarial review: add

grounding_rules

structured_output_contract

, and

dig_deeper_nudge

Research or recommendation tasks: add
```
research_mode
```
and
```
citation_rules
```
.
Write-capable tasks: add
```
action_safety
```
so Codex stays narrow and avoids unrelated refactors.

How to choose prompt shape:

Use built-in
```
review
```
or
```
adversarial-review
```
commands when the job is reviewing local git changes. Those prompts already carry the review contract.
Use
```
task
```
when the task is diagnosis, planning, research, or implementation and you need to control the prompt more directly.
Use
```
task --resume-last
```
for follow-up instructions on the same Codex thread. Send only the delta instruction instead of restating the whole prompt unless the direction changed materially.

Working rules:

Prefer explicit prompt contracts over vague nudges.
Use stable XML tag names that match the block names from the reference file.
Do not raise reasoning or complexity first. Tighten the prompt and verification rules before escalating.
Ask Codex for brief, outcome-based progress updates only when the task is long-running or tool-heavy.
Keep claims anchored to observed evidence. If something is a hypothesis, say so.

Prompt assembly checklist:

Define the exact task and scope in
```
<task>
```
.
Choose the smallest output contract that still makes the answer easy to use.
Decide whether Codex should keep going by default or stop for missing high-risk details.
Add verification, grounding, and safety tags only where the task needs them.
Remove redundant instructions before sending the prompt.

Reusable blocks live in references/prompt-blocks.md. Concrete end-to-end templates live in references/codex-prompt-recipes.md. Common failure modes to avoid live in references/codex-prompt-antipatterns.md.

当

codex:codex-rescue

需要向Codex或其他基于GPT-5.4的工作流寻求帮助时，请使用本规范。

像给操作员下达指令一样向Codex发送提示词，而非将其当作协作伙伴。保持提示词简洁紧凑，使用XML标签进行分块结构组织。明确说明任务、输出约定、默认后续执行规则，以及少量重要的额外约束。

核心规则:

每次调用Codex尽量只执行一项明确的任务，将不相关的请求拆分到不同的调用中。
明确告知Codex任务完成的判定标准，不要假设它会自行推断预期的最终状态。
对于任何无依据猜测会影响结果质量的任务，需添加明确的事实锚定与核验规则。
优先完善提示词约定，而非增加推理步骤或添加冗长的自然语言解释。
统一使用XML标签，确保提示词具备稳定的内部结构。

默认提示词结构模板:

```
<task>
```
：具体任务内容，以及相关的代码仓库或故障上下文。
```
<structured_output_contract>
```
或
```
<compact_output_contract>
```
：对输出格式、排序、简洁度的明确要求。
```
<default_follow_through_policy>
```
：Codex无需询问常规问题、默认执行的规则。
```
<verification_loop>
```
或
```
<completeness_contract>
```
：调试、功能实现或高风险修复场景下必填。
```
<grounding_rules>
```
或
```
<citation_rules>
```
：评审、研究或任何可能出现无依据表述的场景下必填。

不同场景需添加的块:

编码或调试场景：添加

completeness_contract

、

verification_loop

和

missing_context_gating

。

评审或对抗评审场景：添加

grounding_rules

、

structured_output_contract

和

dig_deeper_nudge

。

研究或推荐类任务：添加
```
research_mode
```
和
```
citation_rules
```
。
具备写入权限的任务：添加
```
action_safety
```
，确保Codex的操作范围可控，避免执行无关的重构。

如何选择提示词类型:

如果任务是评审本地git变更，使用内置的
```
review
```
或
```
adversarial-review
```
命令，这些命令的提示词已经内置了评审约定。
如果任务是诊断、规划、研究或实现，且你需要更直接地控制提示词内容，使用
```
task
```
。
对同一个Codex会话发送后续指令时使用
```
task --resume-last
```
，除非任务方向发生重大变更，否则仅发送增量指令，无需重述整个提示词。

执行规则:

优先使用明确的提示词约定，而非模糊的引导。
使用与参考文件中块名称一致的稳定XML标签名。
不要首先增加推理步骤或复杂度，在提升模型能力等级前先优化提示词和核验规则。
仅当任务运行时间长或需要调用大量工具时，才要求Codex提供基于结果的简短进度更新。
所有表述都要基于可观测的证据，如果是假设需要明确说明。

提示词组装检查清单:

在
```
<task>
```
中明确定义具体任务和范围。
选择能够保证输出结果易用的最简输出约定。
确定Codex在缺少高风险细节时，是默认继续执行还是暂停询问。
仅在任务需要时添加核验、事实锚定和安全相关标签。
发送提示词前删除冗余的指令。

可复用的块存放在 references/prompt-blocks.md。完整的端到端模板存放在 references/codex-prompt-recipes.md。需要避免的常见错误模式存放在 references/codex-prompt-antipatterns.md。