PRD-review

v1.0.2

自动化审查商业化产品需求文档的逻辑准确性与闭环性,提取界面/功能/商业化设计要点并划分高-中-低优先级,输出设计师友好的标准化梳理文档;当用户需要审查PRD、梳理设计要点、划分设计优先级或快速对接开发时使用

0· 145·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description describe PRD review and design-point extraction; included doc_parser.py and the review checklist directly support that purpose. There are no unrelated binaries, credentials, or config-path requirements.
Instruction Scope
SKILL.md confines behavior to parsing user-provided documents (upload, paste, or downloaded-and-uploaded). Runtime steps instruct running scripts/doc_parser.py to extract text and then performing local analysis. There are no instructions to read system files, environment variables, or to transmit data to external endpoints.
Install Mechanism
This is an instruction-only skill with no install spec. The SKILL.md declares Python dependencies (python-docx, PyPDF2) but does not provide an automated install step; users must ensure those packages are present. No remote downloads, obscure URLs, or archive extraction are used.
Credentials
The skill requires no environment variables, credentials, or special config paths. The parser operates on local files provided by the user. There are no requests for tokens/keys or unrelated secrets.
Persistence & Privilege
always is false and autonomous invocation is allowed by default. The skill does not request persistent system presence, modify other skills, or alter system-wide agent settings.
Assessment
This skill appears coherent and limited to parsing user-supplied PRDs and producing review output. Before installing/running: (1) review and be comfortable with running the included Python script (scripts/doc_parser.py) locally; (2) install the declared Python packages (python-docx, PyPDF2) in a controlled environment (virtualenv/container); (3) avoid uploading sensitive documents unless you trust the environment where the script runs—the code reads files you provide but does not attempt network access or exfiltration; (4) if you want extra assurance, run the script in a sandbox and inspect the code yourself (it is short and only reads files and prints extracted text).

Like a lobster shell, security has layers — review code before you run it.

latestvk978whxyq2x3a0bc0xzqw38qfh83feh9

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments