PRD to Prototype
v1.0.0从产品需求到可交互原型的完整工作流。当用户表达产品想法（如'我想做一个...'、'帮我设计...'）时触发。支持：1) 零提问直出PRD 2) 平台选择确认 3) 生成Awwwards级别的高保真HTML/Tailwind原型（移动端/PC端）。端到端产品设计流程。
⭐ 1· 593·2 current·2 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description (PRD → prototype) align with instructions: the SKILL.md mandates generating a PRD, writing it to /workspace/docs/prd.md, and producing HTML/Tailwind prototype files under /workspace/prototype/. No unrelated credentials, binaries, or installs are requested.
Instruction Scope
Instructions are explicit and confined to the workspace and external public CDNs/Unsplash for assets. Two notable behavioral choices: (1) a strict '禁止提问' rule forces the agent to invent missing details rather than ask clarifying questions — this is a design decision (not a secret-access behavior) but can lead to inaccurate or invented content; (2) the skill may attempt to 'deploy' if a deploy tool is available (unspecified), which could cause the agent to call external tooling or APIs if present. The SKILL.md does not direct reading of other system files, environment variables, or secrets.
Install Mechanism
There is no install spec and no code files — the skill is instruction-only, so nothing is written to disk by an installer and no third-party packages are pulled in. This is low risk from an install perspective.
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. The external resources referenced (Tailwind CDN, FontAwesome CDN, Unsplash) are appropriate for generating prototypes and do not require secrets.
Persistence & Privilege
always is false and the skill does not request persistent or elevated privileges. It writes output only to /workspace/ locations (expected for a generator) and does not modify other skills or system configs.
Assessment
This skill is coherent with its purpose and does not request credentials or installs, but review these points before installing/using it: 1) It enforces 'no-questions' behavior and will invent missing details — if you need precise requirements, the agent will not ask and may hallucinate specifics, so carefully review and correct the generated PRD. 2) The skill will write files to /workspace/docs and /workspace/prototype; inspect these outputs before publishing or deploying. 3) It fetches assets from public CDNs and Unsplash — if you have outbound-network restrictions or privacy concerns, be aware the agent will make external requests to load images and style resources. 4) The SKILL.md may call a deploy tool 'if available' — confirm what deployment integrations your agent environment exposes to avoid unintended publishes. If any of these behaviors are unacceptable (especially automatic deployment or invention of sensitive details), do not enable the skill or restrict its network/deploy permissions.Like a lobster shell, security has layers — review code before you run it.
latestvk973p4wqrj96rf1e145ykqgss983efkh
License
MIT-0
Free to use, modify, and redistribute. No attribution required.