skill-prompt-convert
- Repo stars 1,503
- Author updated Live
- Author repo best-skills
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @xstongxue · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: skill-prompt-convert
description: 从用户消息或粘贴/附件中获取待转换内容，判断方向： name: skill-name description: 触发场景与功能描述 runs entirely locally. Works w…
category: ai
runtime: no special runtime
---
# skill-prompt-convert output preview
## PART A: Task fit
- Use case: 从用户消息或粘贴/附件中获取待转换内容，判断方向： name: skill-name description: 触发场景与功能描述 runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “使用时机 / Step 1：获取输入并确认方向 / Step 2：执行转换” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “从用户消息或粘贴/附件中获取待转换内容，判断方向： name: skill-name description: 触发场景与功能描述 runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “使用时机 / Step 1：获取输入并确认方向 / Step 2：执行转换” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “使用时机 / Step 1：获取输入并确认方向 / Step 2：执行转换”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: skill-prompt-convert
description: 从用户消息或粘贴/附件中获取待转换内容，判断方向： name: skill-name description: 触发场景与功能描述 runs entirely locally. Works w…
category: ai
source: xstongxue/best-skills
---
# skill-prompt-convert
## When to use
- 从用户消息或粘贴/附件中获取待转换内容，判断方向： name: skill-name description: 触发场景与功能描述 Skill 与 Prompt 互转 用户需要将 Skill 转为可直接复制到聊天框的 Prompt 用户…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “使用时机 / Step 1：获取输入并确认方向 / Step 2：执行转换” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "skill-prompt-convert" {
input -> user goal + target files + boundaries + acceptance criteria
context -> 使用时机 / Step 1：获取输入并确认方向 / Step 2：执行转换
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Skill 与 Prompt 互转
使用时机
- 用户需要将 Skill 转为可直接复制到聊天框的 Prompt
- 用户需要将 Prompt 转为 SKILL.md 格式的 Skill
- 用户提到 Skill 与 Prompt 互转、格式转换
Step 1：获取输入并确认方向
从用户消息或粘贴/附件中获取待转换内容，判断方向：
- A. Skill → Prompt：输入为 SKILL.md 内容，输出聊天框可用的 Prompt
- B. Prompt → Skill：输入为 Prompt 内容（含 ``` 代码块），输出 SKILL.md 格式
Step 2：执行转换
Skill → Prompt 时：将 name、description 融入 # Role 和 # Task；将「使用时机」转化为适用场景；将 Step 1/2... 转化为 # Workflow 或 # Constraints；补充 # Output Format 和 # Input 占位符；输出用 ``` 包裹。
Prompt → Skill 时：从 # Role、# Task 提炼 name（英文小写短横线）和 description；从 # Task 或 # Constraints 提炼「使用时机」；将 # Workflow、# Constraints 拆解为 Step 1、Step 2...；保留 # Output Format 到「注意事项」；输出完整 SKILL.md，必须符合标准 Skill 格式。
Step 3：输出结果
- Part 1 [转换说明]：简要说明映射关系（如：Step 1 映射为 Workflow 第一步）
- Part 2 [转换结果]：完整的转换后内容（可直接粘贴使用）
注意事项
- 信息零丢失：不得删减核心逻辑、步骤、约束条件
- 格式适配：Skill 强调「何时触发」「Agent 如何执行」；Prompt 强调「用户输入什么」「输出什么格式」
- 命名规范：
name必须英文、小写、短横线（如wechat-article-writer）；reference 文件名同理（如outline-review-science.md） - description 质量：需包含「什么时候用」「用来干什么」及关键词
- Skill 正文结构：标题 → 使用时机 → Step 1/2... → 注意事项/示例；多输入任务需补充「触发时的输入方式」
- 标准 Skill 格式：YAML 前置元数据必须用
---开头和结尾闭合，使用name:和description:（严禁## name:），示例：--- name: skill-name description: 触发场景与功能描述 --- # 标题 ...
Decide Fit First
Design Intent
How To Use It
Boundaries And Review