Product Monster Feature List
v1.0.0用于在产品立项或版本规划阶段，梳理并输出标准化的 Feature List（功能清单）。严格遵循多级模块划分、用户故事表述及软硬件依赖分析。
⭐ 0· 101·0 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
Name/description claim: produce standardized Feature List. What it actually does: read user-provided background, parse the included ./examples/standard_featurelist.csv header as a template, and output a Markdown table matching those headers. No unrelated credentials, binaries, or installs are requested — proportional to purpose.
Instruction Scope
Runtime instructions are focused: read user-provided context and the included example CSV to align headers and granularity, then emit a Markdown table matching the CSV headers. The only file the skill explicitly reads is the included example CSV in the same directory. There are no instructions to read other system files, environment variables, or to transmit data externally.
Install Mechanism
No install spec and no code files beyond SKILL.md and an example CSV — lowest-risk model. Nothing will be written to disk or downloaded during install because there is no installer.
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md does not reference secrets or other environment variables. Requested access is minimal and appropriate for the stated function.
Persistence & Privilege
always:false and the skill does not request persistent presence or modify other skills/system settings. Model invocation is allowed (platform default) which is expected for an agent skill and is not by itself a concern here.
Assessment
This is an instruction-only skill that reads the example CSV in its directory and user-supplied requirements to produce a standardized Feature List. Before installing or invoking it: (1) inspect the included example CSV and SKILL.md yourself to confirm no sensitive data is present; (2) avoid pasting secrets or credentials into prompts you give the skill (it will include whatever you provide in outputs); and (3) remember the agent may read files you place in the same directory — don't put private files there. Overall risk is low and the skill appears coherent with its stated purpose.Like a lobster shell, security has layers — review code before you run it.
latestvk974g06m1rw9yd832pyrm01va183k49p
License
MIT-0
Free to use, modify, and redistribute. No attribution required.