← 返回 Skills 市场
151
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install signal-intelligence-pack
功能描述
LLM通用前置grounding技能组。在正式分析、判断、报告或规划之前,将问题拆解为可执行查询、选对来源、洗净证据、标清新鲜度、补上反证。内部固定串联5个独立技能:query-planner → source-router → evidence-cleaner → freshness-judge → count...
安全使用建议
This skill appears coherent for its stated purpose, but before installing check the following: (1) child sub-skills (query-planner, source-router, evidence-cleaner, freshness-judge, counter-evidence-hunter) must exist and be trusted — inspect their SKILL.md files because the orchestration relies on them; (2) confirm how the agent performs web fetches and what connectors (tavily, bailian, web_fetch_direct) are configured — ensure those connectors don't require you to supply credentials you don't want shared and that their endpoints are vetted; (3) verify where pipeline_metadata, pending_actions and any 'local cache' are persisted and who can read them (agent memory, files, or external storage), since they may contain search queries or intermediate evidence; (4) expect this skill to issue potentially many external searches (quota/cost/privacy), so set search budgets or rate limits as needed; (5) because the skill can autonomously invoke sub-skills, review those sub-skills for any broader system access (file, network, credentials). If you cannot inspect the child skills or the connectors, consider treating the package as untrusted or run it in a limited/sandboxed agent profile.
功能分析
Type: OpenClaw Skill
Name: signal-intelligence-pack
Version: 2.1.0
The 'signal-intelligence-pack' is a sophisticated orchestration framework designed to ground LLM responses through a structured 5-step intelligence gathering pipeline (query planning, source routing, evidence cleaning, freshness judging, and counter-evidence hunting). The bundle consists of comprehensive documentation, JSON schemas, and execution instructions (SKILL.md) that define complex logic for feedback loops and search degradation. No evidence of malicious intent, data exfiltration, or unauthorized command execution was found; the capabilities are entirely consistent with the stated purpose of providing high-quality, multi-source grounding for strategic and tactical analysis.
能力评估
Purpose & Capability
Name/description match the instructions: this is a pipeline orchestrator (query-planner → source-router → evidence-cleaner → freshness-judge → counter-evidence-hunter). It requests no binaries, no environment variables, and no install — all proportionate for an instruction-only orchestration skill. Referenced sources (e.g., 'tavily', 'bailian', 'web_search') are plausible search targets for the described use case.
Instruction Scope
SKILL.md strictly limits the skill to orchestration tasks and does not instruct reading arbitrary system files or secrets. It does instruct the agent to call five child sub-skills and to perform searches (including direct web fetchs). The workflow includes fallback chains, dynamic feedback and potential generation of additional queries. This grants the agent broad discretion over external search activity (multiple web sources and 'web_fetch_direct') but does not direct exfiltration of credentials or unrelated system data.
Install Mechanism
Instruction-only (no install spec, no code files). This is the lowest install risk — nothing will be written to disk by an installer step from this package itself.
Credentials
No required environment variables, credentials, or config paths are declared. The skill references third‑party sources but does not request API keys or secrets in its metadata, which is appropriate for a generic orchestration skill.
Persistence & Privilege
always:false and normal autonomous invocation are used. The spec describes writing pipeline_metadata, pending_actions and mentions 'local cache (memory/*_cache.md)' as a fallback — implying the orchestrator may use agent memory or writable cache. That is reasonable for a pipeline but worth reviewing in your environment to confirm where those pending_actions and pipeline_metadata are stored and who/what can read them.
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 signal-intelligence-pack - 安装完成后,直接呼叫该 Skill 的名称或使用
/signal-intelligence-pack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
v2.1.0
V2.1: 信号降级为待办(pending_actions) + pipeline_metadata命名精确化 + 同源矛盾检测集成
v2.0.0
V2.0: LLM前置grounding技能组编排器,feedback_signal回溯+量化评分
v1.0.0
Initial release of signal-intelligence-pack.
- Introduces a 5-step grounding pipeline: query-planner → source-router → evidence-cleaner → freshness-judge → counter-evidence-hunter.
- Transforms vague questions into an enhanced evidence base before any analysis or judgment.
- Implements unified input/output schemas and pipeline execution flow.
- Includes configurable early stopping rules and quality thresholds for each step.
- Designed for scenarios such as strategic analysis, research agents, and “search-before-judge” tasks.
元数据
常见问题
Signal Intelligence Pack 是什么?
LLM通用前置grounding技能组。在正式分析、判断、报告或规划之前,将问题拆解为可执行查询、选对来源、洗净证据、标清新鲜度、补上反证。内部固定串联5个独立技能:query-planner → source-router → evidence-cleaner → freshness-judge → count... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 151 次。
如何安装 Signal Intelligence Pack?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install signal-intelligence-pack」即可一键安装,无需额外配置。
Signal Intelligence Pack 是免费的吗?
是的,Signal Intelligence Pack 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Signal Intelligence Pack 支持哪些平台?
Signal Intelligence Pack 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 Signal Intelligence Pack?
由 z1one0415(@z1one0415)开发并维护,当前版本 v2.1.0。
推荐 Skills