← 返回 Skills 市场
519
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install percept-summarize
功能描述
Generates AI summaries of conversations after silence, extracting entities, action items, and relationships for searchable meeting notes and context retrieval.
安全使用建议
This skill's goal (summarize meetings) is plausible but the instructions leave important questions unanswered. Before installing or enabling it, consider:
- Confirm where 'OpenClaw' runs: is it a local CLI that stays on your machine or a remote service? Transcripts sent to an external service can expose sensitive meeting content.
- Verify percept-listen: this skill depends on another listener to capture audio/transcripts; only enable if you trust that component and know how it captures audio (microphone access, file reads).
- Ask for a complete dependency list and install steps (binaries, versions, whether LanceDB is used and where it runs). The metadata currently lists no dependencies but the SKILL.md references several.
- Check data storage details: where is the SQLite DB stored, who can access it, and can retention settings (speaker profiles never expire) be changed? Consider limiting retention for sensitive data.
- Confirm the dashboard binding: ensure the web UI listens on localhost only (not 0.0.0.0) and is access-controlled if you will run it.
- If you need stronger assurances, request source or an install spec from the author (or avoid enabling the skill). Because the skill can autonomously collect and persist conversation transcripts, only enable it in trusted environments and after clarifying the above points.
功能分析
Type: OpenClaw Skill
Name: percept-summarize
Version: 1.0.0
The provided skill bundle, consisting of `_meta.json` and `SKILL.md`, describes a conversation summarization and entity extraction skill. The `SKILL.md` documentation outlines the skill's purpose, functionality, and requirements, including interaction with the OpenClaw agent via CLI for LLM summarization and local storage of data in SQLite. There are no explicit instructions for the AI agent to perform unauthorized actions, exfiltrate data, or hide activities. No malicious prompt injection attempts, suspicious code, or indicators of compromise were found within the analyzed files.
能力评估
Purpose & Capability
The stated purpose (summarize conversations, extract entities, store searchable notes) aligns with the steps in SKILL.md. However the instructions depend on other components (percept-listen, an 'OpenClaw agent' CLI, LanceDB) that are not declared in the skill metadata (no required binaries, env vars, or install steps). That mismatch is unexpected: a skill that relies on a local CLI and vector DB should declare those dependencies.
Instruction Scope
SKILL.md instructs the agent to watch for 60s silence, build speaker-tagged transcripts, send transcripts to an 'OpenClaw' CLI for LLM summarization, run entity resolution (including LanceDB vector search), write results to SQLite (FTS5), and host a dashboard on port 8960. Those actions allow the agent to collect, persist, and serve conversation content and to invoke an external LLM via a CLI — none of which are constrained or fully specified in the instructions, creating scope creep and potential for sensitive data exposure.
Install Mechanism
This is an instruction-only skill with no install spec or code files, which minimizes direct supply-chain risk. However because it assumes external components (OpenClaw CLI, LanceDB, percept-listen) are present, lack of an install spec means it's unclear how or whether those components will be installed or configured, and whether they'll be invoked locally or remotely.
Credentials
The skill declares no required environment variables or credentials, yet it instructs sending transcripts to an 'OpenClaw agent' via CLI and using LanceDB for semantic search. Those operations often require tokens, endpoints, or binaries; their absence from metadata is a proportionality mismatch. Also, speaker profiles are set to 'never expire'—a retention policy that may be disproportionate for many users without explicit consent or access controls.
Persistence & Privilege
The skill does not request always:true and is user-invocable (normal). Still, it instructs the agent to persist conversational data locally (SQLite) and expose a dashboard on port 8960. Autonomous invocation combined with persistent storage and an HTTP dashboard increases the practical blast radius if the skill is misconfigured, but the skill does not explicitly request elevated system privileges.
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 percept-summarize - 安装完成后，直接呼叫该 Skill 的名称或使用
/percept-summarize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
v1.0.0
percept-summarize 1.0.0
- Initial release of percept-summarize skill for automated conversation summarization.
- Generates AI-powered summaries with entity extraction (people, companies, topics), relationship mapping, and action items.
- Summaries and entities stored locally in SQLite with full-text search.
- Entity resolution uses a 5-stage cascade, including fuzzy and semantic matching.
- Requires percept-listen skill and OpenClaw agent for AI processing.
- Searchable summaries via dashboard (port 8960) or directly in SQLite.
元数据
常见问题
Percept Summarize 是什么？
Generates AI summaries of conversations after silence, extracting entities, action items, and relationships for searchable meeting notes and context retrieval. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 519 次。
如何安装 Percept Summarize？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install percept-summarize」即可一键安装，无需额外配置。
Percept Summarize 是免费的吗？
是的，Percept Summarize 完全免费（开源免费），可自由下载、安装和使用。
Percept Summarize 支持哪些平台？
Percept Summarize 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 Percept Summarize？
由 jarvis563（@jarvis563）开发并维护，当前版本 v1.0.0。
推荐 Skills