Prompt Engineer
v1.0.0将用户模糊简单的需求，转化为逻辑严密、结构清晰的专家级结构化Prompt，适配Gemini/GPT/Claude/Qwen等大模型最佳实践
⭐ 0· 353·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description ('Prompt Engineer') match the SKILL.md instructions (an agent persona that transforms fuzzy user requests into structured prompts for LLMs). There are no unrelated required binaries, env vars, or config paths listed.
Instruction Scope
The SKILL.md stays within prompt-engineering tasks (analyze input, build modular prompt, explain design). It does allow the agent to make 'reasonable default assumptions' when information is missing, which grants some discretionary behavior but is consistent with the skill's purpose. The instructions do not ask the agent to read files, environment variables, or send data to external endpoints.
Install Mechanism
No install spec and no code files are present (instruction-only). This minimizes disk writes and external installation risks.
Credentials
The skill requests no environment variables, credentials, or config paths. The level of access requested is proportionate to a prompt-engineering utility.
Persistence & Privilege
always:false and no special privileges are requested. The skill can be invoked autonomously (platform default), which is expected for a user-invocable skill; there is no persistent or cross-skill configuration modification.
Assessment
This skill appears coherent and low-risk because it is instruction-only and asks for no credentials or installs. Before installing or using it: (1) avoid pasting secrets or private data into prompts you ask it to transform; (2) review any 'reasonable defaults' the skill invents to ensure they don't expose or assume sensitive details; (3) if you do not want the agent to invoke this skill autonomously, restrict its usage in your agent settings. Overall it is appropriate for generating structured prompts, but treat outputs like any automatically generated text and verify them before use.Like a lobster shell, security has layers — review code before you run it.
latestvk977xy6phew2mhs66x1vnjgews82tza9
License
MIT-0
Free to use, modify, and redistribute. No attribution required.