机票产品需求评审
v1.0.0机票产品需求评审 Agent。对前端、后端、运营类机票需求文档进行结构化评审打分，含独立的流程图治理评审（去If化、卫语句、决策表、FSM、泳道图、分层建模）。输入需求文档（markdown/图片/HTML），输出分项评分、评语和改进建议。使用场景：用户说"评审需求"、"审需求文档"、"给需求打分"、"需求评审"...
⭐ 0· 77·0 current·0 all-time
by@arisefx
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the provided SKILL.md, example outputs, and templates. All included files are documentation and review templates that are appropriate for a requirements-review agent. There are no declared binaries, env vars, or config paths that would be out-of-scope for a document-review tool.
Instruction Scope
Runtime instructions ask the agent to read Markdown, view images, and parse HTML to produce structured scores/reports, which is consistent with the stated purpose. Note: the SKILL.md assumes the agent environment can process images/HTML (OCR/HTML parsing); this is an operational dependency (not a security misalignment). The instructions do not ask to read unrelated system files, access credentials, or transmit data to unexpected external endpoints.
Install Mechanism
No install spec or code is present (instruction-only). This is low-risk: nothing will be downloaded or written by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested. The skill does not require any secret or external-service tokens, matching its stated function of offline document evaluation.
Persistence & Privilege
always:false and normal autonomous invocation settings. The skill does not request permanent presence or modify other skills' configuration. No elevated privileges are requested.
Assessment
This skill appears internally consistent and low-risk from a technical footprint perspective, but consider these points before installing: 1) It will process any document, image, or HTML you give it — do not upload sensitive PII, credentials, or confidential business secrets unless you trust the agent logging/retention policy. 2) The SKILL.md assumes the platform/agent can parse images (OCR) and HTML; test with non-sensitive examples to confirm expected behavior in your environment. 3) Because the skill is instruction-only, there is no hidden code download, but outputs and user-provided inputs may be stored in conversation logs — check your platform's data retention and privacy settings. 4) If you need stricter data handling, avoid sending regulated data or sanitize documents before use. Overall, the skill is coherent with its stated purpose.Like a lobster shell, security has layers — review code before you run it.
latestvk97a9ya2tgy1t2fgmqj0bs50vn83pszt
License
MIT-0
Free to use, modify, and redistribute. No attribution required.