to-prompt-opus
Use when preparing or rewriting prompts for Claude Opus 4.8, Anthropic API agents, XML-structured prompts, long-context document work, coding agents, research synthesis, frontend/design tasks, or model-specific prompt optimization. Do not use for GPT/OpenAI prompts or raw context packaging without Opus-specific tuning.
- License 许可
- MIT
- 最近更新
- 2026-07-16
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- to-prompt-opus
- description
- Use when preparing or rewriting prompts for Claude Opus 4.8, Anthropic API agents, XML-structured prompts, long-context document work, coding agents, research synthesis, frontend/design tasks, or model-specific prompt optimization. Do not use for GPT/OpenAI prompts or raw context packaging without Opus-specific tuning.
02 资源文件 3
- 参考文档agents/openai.yaml205 B
- 参考文档references/opus-4.8-guidance.md4.7 KB
- 参考文档references/output-template.md1.8 KB
03 SKILL.md 正文
To Prompt Opus
Transform a user request, rough context, or existing prompt into a Claude Opus 4.8-ready prompt.
Required Reading Router
Match the task to every applicable row. Read the listed files in full before producing output. They are load-bearing; inline guidance is only a router.
| Task | MUST read |
|---|---|
| Any Claude Opus 4.8 prompt rewrite | references/opus-4.8-guidance.md + references/output-template.md |
| Raw, incomplete, or issue-like context | Apply to-prompt behavior first, then read references/opus-4.8-guidance.md + references/output-template.md |
| XML, long-context, coding, frontend/design, tool, subagent, or runtime prompt | references/opus-4.8-guidance.md |
| Missing critical context | references/output-template.md |
Reference Index
references/opus-4.8-guidance.md: Claude Opus 4.8-specific prompt-shaping rules from Anthropic guidance.references/output-template.md: Final prompt template and missing-context question format.
Operating Procedure
-
Classify the input as raw context, structured prompt, or blocked by missing context.
- Raw context includes bugs, issues, repo notes, scattered requirements, logs, or code snippets.
- Structured prompts already contain goal, context, constraints, and output requirements.
- Blocked requests lack the target task, audience, source material, or success criteria.
STOP. Read
references/output-template.mdin full before deciding whether to ask questions or produce the final prompt. The bullets above are tripwires, not the output contract.
-
For raw context, first apply
to-promptbehavior without force-loading it: gather problem, current state, requirements, constraints, evidence, files, logs, tests, and success criteria. Do not add implementation advice unless the user explicitly asks the receiving model to propose an implementation. -
Refine for Claude Opus 4.8.
- State scope literally and explicitly.
- Use XML tags for complex context, documents, examples, or output contracts when helpful.
- Add tool, subagent, frontend/design, effort, adaptive-thinking, or long-context guidance only when relevant to the target task.
STOP. Read
references/opus-4.8-guidance.mdin full before writing the final Opus prompt. These bullets are tripwires, not the source of truth.
-
Produce only the final artifact.
- If context is sufficient, output the prompt and no commentary.
- If context is insufficient, output concise questions and no speculative prompt.
- Preserve the user's language unless the user asks for another language.
STOP. Read
references/output-template.mdin full before formatting the final answer. The template file is the contract.
Error Handling
- If the user asks for GPT, OpenAI, Responses, or GPT-specific prompting, stop and use
to-prompt-gptinstead. - If the request only asks for neutral context packaging, use
to-promptinstead. - If official model guidance is needed and may have changed, verify the current Anthropic documentation before relying on cached rules.
04 同仓库更多 Skills
to-prompt-gpt
Use when preparing or rewriting prompts for GPT-5.5, OpenAI API agents, Responses workflows, coding agents, research synthesis, support assistants, or model-specific prompt optimization. Do not use for Claude/Opus prompts or raw context packaging without GPT-specific tuning.
plan-refactor-qa
Plans and runs qa-report before executing Compozy refactor tasks. Use when the user provides a refactor or issue slug and wants Codex to inspect the matching .compozy/tasks directory, related PRD/TechSpec/ADR/task artifacts, affected code, and existing tests, then invoke $qa-report with a repository-grounded prompt. Do not use to run tests, execute qa-execution, implement code, or perform post-refactor verification.
multi-tool-branch-review
Orchestrates a multi-tool branch review of the current git branch against a base branch. By default it runs two independent thermo-nuclear maintainability audits, one on Codex GPT-5.5 xhigh and one on Claude Opus xhigh, then consolidates the findings into a single remediation plan via writing-plans. If the user explicitly asks for native reviews, it can add the Claude native review pass, the Codex native review pass, or both. Use when the user wants a deep cross-model review of a branch or PR before merge, or asks to review this branch with multiple tools or models. Encodes known infra failure modes and their fixes (missing Claude ACP adapter, Codex MCP auth hangs, false-positive report files, long jobs orphaned inside subagents). Do not use for reviewing a single uncommitted snippet, for non-git work, for running only one reviewer, or when the user only wants a quick lint or test run.
create-pr-with-template
Create a GitHub Pull Request with gh CLI and prefer repository PR templates automatically. Use this whenever the user asks to open/create a PR, especially when template compliance is needed. If multiple templates exist, ask the user which template to use.
ui-craft
Provides guardrails for user-facing UI work: usability heuristics, accessibility floors, design-system discipline, component states, microcopy, motion, dark mode, responsive behavior, and human-AI UX. Use when designing, generating, reviewing, or refactoring visible product surfaces such as components, pages, dashboards, forms, dialogs, loading/empty/error states, or AI interfaces. Do not use for backend-only work, infrastructure, CLI/TUI design, or pure documentation editing.
typescript-advanced
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects. Don't use for plain JavaScript, runtime validation libraries (Zod, Yup), or basic TypeScript syntax questions.