← 返回 Skills 市场
619
总下载
0
收藏
3
当前安装
3
版本数
在 OpenClaw 中安装
/install sentiment-priority-scorer
功能描述
Score normalized real-estate leads using sentiment, urgency, intent, recency, and record type to produce deterministic priority rankings and P1-P3 buckets. U...
安全使用建议
This skill appears coherent and limited to scoring leads. Before installing, confirm how the agent will compute sentiment_score (ensure it does not call an external API or a third-party endpoint you don't control). Verify the upstream chain (e.g., india-location-normalizer) for any additional permissions or env requirements. Test with synthetic or redacted data to ensure no PII is leaked in logs or evidence strings, and confirm your Supervisor routing and enforcement actually blocks writes/sends as the SKILL.md requires.
功能分析
Type: OpenClaw Skill
Name: sentiment-priority-scorer
Version: 1.0.2
The skill bundle is benign. The `SKILL.md` clearly defines the purpose of scoring real-estate leads and, critically, includes an 'Enforce Boundaries' section that explicitly prohibits writing to files/databases, sending messages, triggering outbound channels, creating reminders, or executing actions. These instructions act as strong guardrails against data exfiltration, persistence, or unauthorized actions, indicating a clear intent to operate within a safe, read-only computational scope. All other files (metadata, agent configuration, and JSON schemas) support this stated, non-malicious functionality without introducing any risky behaviors or prompt injection attempts.
能力评估
Purpose & Capability
Name/description match the instructions: the skill is an instruction-only scorer for leads and requests no binaries, env vars, or installs. All required inputs (lead fields) are appropriate for lead prioritization.
Instruction Scope
SKILL.md confines behavior to validating input, computing deterministic scores from provided fields and raw_text, producing evidence, and validating output. It explicitly forbids writes, sends, creating reminders, or bypassing Supervisor. The scoring formula and keyword boosts are narrowly scoped to lead text and metadata. Note: the skill does not prescribe a specific algorithm for deriving sentiment_score from raw_text (left to the agent), which is a functional detail rather than a security mismatch.
Install Mechanism
No install spec or code files — instruction-only skill (lowest installation risk). Nothing is downloaded or written to disk by the skill itself.
Credentials
No required environment variables, no credentials, and no config paths are declared. The requested input fields are limited to lead-related data and align with the stated purpose.
Persistence & Privilege
always:false and no elevated privileges requested. The skill also instructs not to write or send outbound data. Default autonomous invocation (disable-model-invocation:false) is allowed but not combined with other risky signals.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install sentiment-priority-scorer - 安装完成后，直接呼叫该 Skill 的名称或使用
/sentiment-priority-scorer触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.2
Align broker-group contracts: dataset_mode, record_type, and expanded summary/prioritization schemas.
v1.0.1
Added intent boost cues for immediate action listing language
v1.0.0
Sentiment Priority Scorer v1.0.0
- Introduced a deterministic scoring system for real-estate leads based on sentiment, urgency, intent, and recency.
- Normalizes leads into P1/P2/P3 priority buckets with transparent, plain-language evidence.
- Enforces strict boundaries: read-only, no outbound messaging, state mutation, or unsanctioned actions.
- Validates input and output schemas, and provides clear error handling for invalid or incomplete records.
- Recommended chain: india-location-normalizer → sentiment-priority-scorer → summary-generator.
元数据
常见问题
Sentiment Priority Scorer 是什么？
Score normalized real-estate leads using sentiment, urgency, intent, recency, and record type to produce deterministic priority rankings and P1-P3 buckets. U... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 619 次。
如何安装 Sentiment Priority Scorer？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install sentiment-priority-scorer」即可一键安装，无需额外配置。
Sentiment Priority Scorer 是免费的吗？
是的，Sentiment Priority Scorer 完全免费（开源免费），可自由下载、安装和使用。
Sentiment Priority Scorer 支持哪些平台？
Sentiment Priority Scorer 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Sentiment Priority Scorer？
由 Vishal（@vishalgojha）开发并维护，当前版本 v1.0.2。
推荐 Skills