2skill
v1.0.0Generate product requirement documents (PRD) with a complete structure for product design and requirement writing. Use when the user asks for PRD, 产品需求文档, 产品...
⭐ 0· 62·0 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/description (PRD writer) match the SKILL.md: it only needs to read the user's prompt, ask clarifying questions, and produce a structured PRD in Chinese. No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
The instructions stay within the PRD-writing scope: extract user-provided product details, ask up to 6 clarifying questions, and generate a full PRD with specific sections and templates. The skill does not instruct the agent to read system files, access external endpoints, or exfiltrate data. It does ask the agent to integrate any user-provided wireframe/screenshot text (which is reasonable) and to mark assumptions as '待确认'.
Install Mechanism
No install spec and no code files are present (instruction-only), so nothing will be written to disk or downloaded. This is the lowest-risk install model.
Credentials
The skill requires no environment variables, no credentials, and no config paths. The declared requirements are proportional and appropriate for a document-generation helper.
Persistence & Privilege
always is false and disable-model-invocation is false (normal). The skill does not request permanent system presence or modify other skills/configs. Autonomous invocation is the platform default and not alone a concern here.
Assessment
This skill is instruction-only and appears internally consistent with its purpose: it asks for user prompts, optionally requests clarifying answers, and generates a complete PRD in Chinese. Before installing or using it, consider: (1) Review generated PRDs carefully — the agent can hallucinate implementation details, technical constraints, or metrics; (2) Do not paste sensitive credentials or internal secrets into prompts; the skill does not need them; (3) If you want the skill to use internal diagrams or screenshots, provide only textual descriptions (it has no file access); (4) Because autonomous invocation is allowed by default, the agent may call this skill when it thinks a PRD is needed — if you prefer manual control, keep it user-invocable and monitor usage. Overall risk is low, but always verify outputs before sharing or acting on them.Like a lobster shell, security has layers — review code before you run it.
latestvk97ctwvs8gd9m830wm9haqfkn583nadm
License
MIT-0
Free to use, modify, and redistribute. No attribution required.