ClawHub

scene-analysis

v1.0.0

商业闭环场景分析与评估工具；当用户需要进行Gate0战略红线过滤、Gate1量化评估打分或蓝军审核时使用

⭐ 0· 124·0 current·0 all-time
byYAO@yyf1986

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for yyf1986/scene-analysis.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "scene-analysis" (yyf1986/scene-analysis) from ClawHub.
Skill page: https://clawhub.ai/yyf1986/scene-analysis
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install scene-analysis

ClawHub CLI

Package manager switcher

npx clawhub@latest install scene-analysis
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (场景评估、Gate0/Gate1/蓝军) match the SKILL.md and reference files. There are no unrelated environment variables, binaries, or install steps. All required artifacts are internal docs and the user's scenario input, which is coherent for this purpose.
ℹ
Instruction Scope
Instructions explicitly restrict analysis to user-provided scenario descriptions and the included reference rules, and require evidence-based decisions. They do allow logical deduction when evidence is absent (but require marking '无相关证明材料'), which is reasonable for scoring workflows but could lead to speculative output if users supply little evidence — agents should clearly label inferred conclusions and avoid treating deductions as facts.
✓
Install Mechanism
No install spec and no code files — instruction-only skill. Nothing is written to disk and no external packages or downloads are requested.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. All required inputs are user-provided scenario text and the included reference docs, which is proportionate to the described functionality.
✓
Persistence & Privilege
always:false and default autonomous invocation are present; the skill does not request persistent presence or system configuration changes. It does not modify other skills or access system-wide credentials.
Assessment
This skill appears coherent and limited to evaluating user-provided scenarios using its internal Gate0/Gate1/蓝军 rules. Before installing or invoking it: (1) avoid pasting sensitive secrets or private credentials into the scenario text (the skill expects business evidence only); (2) be aware the agent is allowed to make logical inferences when evidence is missing — request that it label inferred points clearly and flag uncertainty; (3) if you need integration with real contracts, systems, or metrics, prefer providing explicit evidence documents rather than relying on inference. No install or credentials are required, so the main risk is inadvertent disclosure of private data in the scenario input.

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

latestvk978kybhjm0fbpgw21m3stzyk983p7f7
124downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0
YAO@yyf1986
latest
Download

场景分析助手

任务目标

本 Skill 用于：基于商业闭环决策模型，对给定场景进行三阶段评估（Gate0战略红线过滤、Gate1量化评分、蓝军审核） 能力包含：主航道强依赖与核心链路嵌入审查、商业闭环量化评分、风险扣分、评级判定 能力包含：主航道强依赖与核心链路嵌入审查、商业闭环量化评分、风险扣分、评级判定 触发条件：用户需要评估商业场景、进行投资决策评审或获取场景评级报告

前置准备

无额外依赖要求

操作步骤

标准：Gate0战略红线与"去伪存真"过滤器

  1. 接受场景描述

    • 智能体读取用户提供的场景描述文本

  2. 四维度评估（严格按顺序执行）

    • 主航道强依赖：评估是否依赖计费/编排OS/数智本体主航道能力
    • 核心链路嵌入：评估是否嵌入交易/调度/结算核心链路
    • 资产沉淀能力：评估是否形成可复用算法/模块资产
    • 替代性验证：评估市场替代可能性

  3. 评估规则执行

    • 每个维度必须基于用户提供的具体证据材料
    • 无证据时可通过逻辑推导替代，但需标注"无相关证明材料"
    • 任一维度不通过 → 直接判定"C级淘汰"，终止后续流程

  4. 输出Gate0评估结果

    • 列出四维度评估结论（通过/淘汰）
    • 说明判定依据（对应场景描述内容+模型规则）
    • 若全部通过，提示用户可进入Gate1打分环节

标准：Gate1量化评估矩阵

  1. 触发条件

    • Gate0四维度全部通过后
    • 用户确认进入打分环节

  2. 评分执行

    • 按评分矩阵对六个因子打分：
      • A1 必要性（25%）
      • A2 现金窗口真实性（20%）
      • B1 标准化/插座化能力（15%）
      • B2 网络效应（15%）
      • C1 算法不可替代性（15%）
      • C2 生态卡位（10%）
    • 计算总分：(A1×0.25 + A2×0.2 + B1×0.15 + B2×0.15 + C1×0.15 + C2×0.1) × 10
    • 执行风险扣分（如适用）
    • 判定最终评级（S/A+/A/B/C）

本 Skill 用于：基于商业闭环决策模型，对给定场景进行三阶段评估（Gate0战略红线过滤、Gate1量化评分、蓝军审核）

  1. 蓝军评估执行

    • 完全从用户输入的场景描述出发，不受前序评估影响
    • 严格重新评估Gate0四维度（审查要点、核心证据、判定规则）
    • 严格重新评估Gate1六因子（按分档条件判定）
    • 严格执行风险扣分
    • 严格计算总分和评级

  2. 输出蓝军评估结果

    • Gate0审查结果（四维度结论+判定依据）
    • 各维度打分详情（得分+分档依据+权重+加权得分）
    • 风险扣分情况
    • 总分计算过程
    • 等级判定依据
    • 最终评级
    • 完成评估流程，输出最终结果

资源索引

注意事项

  • 严格按"Gate0→Gate1→蓝军"顺序执行，不得跳过任意流程
  • 所有评估必须基于用户提供的具体证据材料，无证据时可通过逻辑推导替代，但需标注
  • 仅在Gate0四维度全部通过后才进入Gate1打分环节
  • 蓝军审核需完全独立判断，不受前序评估影响

使用示例

示例1：完整评估流程

  • 功能说明：从场景描述到蓝军验证结果的完整评估流程
  • 执行方式：智能体按步骤执行Gate0→Gate1→蓝军
  • 关键要点：Gate0通过后进入Gate1打分，Gate1完成后直接进入蓝军审核

示例2：蓝军审核

  • 功能说明：对打分结果进行反向严格验证
  • 执行方式：智能体完全基于场景描述重新评估，不受前序影响
  • 关键要点：从严判定，边界分数按低等级判定

Comments

Loading comments...