← 返回 Skills 市场
83
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install prompt-optimizer-v3
功能描述
自动将模糊需求优化成结构化、精确可执行的AI指令，支持多任务类型和多格式输出。
安全使用建议
This package appears coherent and implements a local CLI/library for optimizing prompts. Before installing: 1) inspect the remainder of prompt_optimizer.py (truncated in the package summary) to confirm there are no network calls, subprocess.exec/eval, or hidden endpoints; 2) be aware the install step copies Python files into your OpenClaw workspace (they will run locally); 3) if you enable the llm section in config.yaml (llm.enabled: true) you may need to provide provider credentials (e.g., OpenAI API key) — only enable that if you trust the code and author; 4) the metadata file contains a GitHub homepage URL while the registry summary showed no homepage — if provenance matters, review that repo or contact the author. Overall the skill looks consistent with its stated purpose.
能力评估
Purpose & Capability
Name/description (prompt optimizer) align with the provided code and SKILL.md. The files implement pattern matching, formatting detection, caching, and CLI behavior that match the stated functionality. No unrelated cloud credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs local installation (copy into skills directory) and running the included Python CLI. The instructions and code operate on user-supplied prompts, optional config files, and an internal cache; they do not instruct the agent to read unrelated system files, environment variables, or send data to external endpoints in the visible code.
Install Mechanism
There is no formal install spec (instruction-only install via copying files). That keeps risk low, but the skill includes multiple Python files which will be written into the user's workspace when installed. No network downloads or archive extraction are used by the skill itself.
Credentials
The skill declares no required env vars or credentials. The code optionally supports loading a YAML config that can enable an LLM provider (llm.enabled), but default config has llm.enabled=false. If a user enables LLM usage, they would need to supply provider credentials externally — this is configurable and not required by default.
Persistence & Privilege
Skill does not request 'always: true' and is user‑invocable only. It does write cache state into its own in-memory LRU cache; there is no evidence it modifies other skills or global agent settings.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install prompt-optimizer-v3 - 安装完成后，直接呼叫该 Skill 的名称或使用
/prompt-optimizer-v3触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v3.2.0
**prompt-optimizer-v3 3.2.0 Changelog**
- 新增 7 种任务类型支持，包括写测试用例、代码调试、性能优化、安全检查、API设计、数据结构设计等
- 支持多种输出格式（Markdown、JSON、YAML、XML、表格、PlantUML 等）
- 优化目标受众识别，自动适应技术人员、产品经理、管理者等 7 类用户需求
- 新增风格识别、字数/条数等约束条件支持
- 所有 57 个测试用例全部通过
元数据
常见问题
Prompt Optimizer 是什么？
自动将模糊需求优化成结构化、精确可执行的AI指令，支持多任务类型和多格式输出。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 83 次。
如何安装 Prompt Optimizer？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install prompt-optimizer-v3」即可一键安装，无需额外配置。
Prompt Optimizer 是免费的吗？
是的，Prompt Optimizer 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Prompt Optimizer 支持哪些平台？
Prompt Optimizer 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Prompt Optimizer？
由 ntaffffff（@ntaffffff）开发并维护，当前版本 v3.2.0。
推荐 Skills