by 安全扫描
OpenClaw
安全
high confidenceThe skill's requirements and runtime instructions match its stated purpose (optimizing prompts); it is instruction-only, requests no credentials, and its web- and codebase-research behaviors are coherent with the documented modifiers.
评估建议
This skill appears coherent and does what it says: optimize prompts, ask clarifying questions, read project files when you request +deep, and search the web when you request +web. Before installing or using it, consider: (1) If you use +deep, confirm the agent's file-access scope so it doesn't read unrelated system files or secrets in the repo. (2) Web search and WebFetch will contact external sites — avoid including sensitive data in prompts that will be sent externally. (3) The skill copies op...详细分析 ▾
✓ 用途与能力
Name/description (prompt optimization) align with declared behavior: clarifier, codebase research, and web research sub-agents are appropriate for improving prompts that reference projects, require clarification, or need current best practices. No unrelated credentials, binaries, or config paths are requested.
ℹ 指令范围
SKILL.md and agent docs instruct the agent to read project files (Glob/Grep/Read) when +deep is used and to perform web searches/fetches when +web is used. This is consistent with purpose, but +deep implies file-system reads of the codebase — ensure the agent's file access is scoped to the intended project directory and that users avoid including secrets in prompts.
✓ 安装机制
No install spec and no code files — instruction-only skill (lowest install risk). README suggests typical install commands for external platforms but the skill package itself contains only docs.
✓ 凭证需求
The skill requires no environment variables or credentials. The documented tools (AskUserQuestion, WebSearch, WebFetch, Glob/Grep/Read) are proportional to the described functions; no unexplained secret access is requested.
✓ 持久化与权限
always:false and no special persistence requested. disable-model-invocation:false (agent may invoke autonomously) is the platform default and acceptable here — not combined with broad credentials or persistent system changes.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv3.1.02026/1/30
**Changelog for promptify 3.1.0** - Simplified prompt optimization instructions for improved clarity and brevity. - Consolidated and clarified modifier and trigger sections, focusing on key agent dispatch logic. - Streamlined the contract checklist and process steps for faster, more consistent prompt upgrades. - Moved from detailed markdown tables to concise lists and summary tables where possible. - Added standalone command documentation in commands/promptify.md.
● 可疑
安装命令 点击复制
官方npx clawhub@latest install promptify
镜像加速npx clawhub@latest install promptify --registry https://cn.clawhub-mirror.com
技能文档
Transform prompts into clear, effective ones. Model-agnostic.
Modifiers (parse from ARGUMENTS)
- +ask → Force clarifying questions
- +deep → Force codebase exploration
- +web → Force web search
No modifiers? Auto-detect what's needed.
Auto-Detection Triggers
| Trigger | Signals |
|---|---|
| codebase-researcher | "this project", "our API", specific files/functions, "integrate", "extend", "refactor" |
| clarifier | Ambiguous ("make it better"), multiple interpretations, missing constraints, vague pronouns |
| web-researcher | "best practices", "latest", external APIs/libraries, framework patterns, year references |
Agent Dispatch
When agents needed:
- Announce which and why
- Run in parallel via Task tool (agents/ directory)
- Synthesize findings
- Optimize with gathered context
Core Contract (every prompt needs all four)
| Element | If Missing |
|---|---|
| Role | Add persona with expertise |
| Task | Make action specific |
| Constraints | Infer from context |
| Output | Specify format/structure |
Process
- If image: Analyze, incorporate context
- Detect type: coding/writing/analysis/creative/data
- Convert output→process: "Write X" → "Analyze → Plan → Implement → Validate"
- Strip fluff: "please", "I want you to", filler, apologies
- Apply contract: Verify all 4 elements
- Add structure: XML tags for complex prompts
Type Focus
- Coding: Specs, edge cases, framework
- Writing: Tone, audience, length
- Analysis: Criteria, depth
- Creative: Constraints, novelty
- Data: I/O format, edge cases
Output
- Optimized prompt in code block
echo 'PROMPT' | pbcopy- 2-3 sentence explanation
数据来源：ClawHub ↗ · 中文优化：龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制
免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制