Browser Session Curator
Purpose
Turn an overwhelming set of tabs, bookmarks, and snippets into a structured session digest with tasks, reading queue, and archive plan.
Trigger phrases
- - 整理浏览器标签页
- tab dump
- session digest
- 书签归档
- 浏览器会话整理
Ask for these inputs
- - tab titles/URLs/notes
- session goal
- time budget
- archive rules
- project tags
Workflow
- 1. Cluster tabs by task, reading, waiting, and archive.
- Identify likely duplicates and stale tabs.
- Produce a short execution plan for the next 30–60 minutes.
- Export a digest with tags and follow-up actions.
- Prefer lightweight action over cataloging everything forever.
Output contract
- - session digest
- reading queue
- archive list
- next-hour action plan
Files in this skill
- - Script: INLINECODE0
- Resource: INLINECODE1
Operating rules
- - Be concrete and action-oriented.
- Prefer preview / draft / simulation mode before destructive changes.
- If information is missing, ask only for the minimum needed to proceed.
- Never fabricate metrics, legal certainty, receipts, credentials, or evidence.
- Keep assumptions explicit.
Suggested prompts
- - 整理浏览器标签页
- tab dump
- session digest
Use of script and resources
Use the bundled script when it helps the user produce a structured file, manifest, CSV, or first-pass draft.
Use the resource file as the default schema, checklist, or preset when the user does not provide one.
Boundaries
- - This skill supports planning, structuring, and first-pass artifacts.
- It should not claim that files were modified, messages were sent, or legal/financial decisions were finalized unless the user actually performed those actions.
Compatibility notes
- - Directory-based AgentSkills/OpenClaw skill.
- Runtime dependency declared through
metadata.openclaw.requires. - Helper script is local and auditable:
scripts/session_digest.py. - Bundled resource is local and referenced by the instructions:
resources/session_tags.yaml.
浏览器会话整理器
目的
将杂乱的标签页、书签和片段整理为结构化的会话摘要，包含任务、阅读队列和归档计划。
触发短语
- - 整理浏览器标签页
- tab dump
- session digest
- 书签归档
- 浏览器会话整理
请求以下输入
- - 标签页标题/网址/备注
- 会话目标
- 时间预算
- 归档规则
- 项目标签
工作流程
- 1. 将标签页按任务、阅读、待处理、归档进行聚类。
- 识别可能的重复标签页和过期标签页。
- 生成未来30-60分钟的简短执行计划。
- 导出带有标签和后续行动的摘要。
- 优先轻量级操作，而非永久性全面编目。
输出约定
本技能包含的文件
- - 脚本：{baseDir}/scripts/sessiondigest.py
- 资源：{baseDir}/resources/sessiontags.yaml
操作规则
- - 具体且以行动为导向。
- 在破坏性变更前优先使用预览/草稿/模拟模式。
- 若信息缺失，仅询问推进所需的最少信息。
- 绝不捏造指标、法律确定性、收据、凭证或证据。
- 保持假设明确。
建议提示
- - 整理浏览器标签页
- tab dump
- session digest
脚本与资源的使用
当脚本有助于用户生成结构化文件、清单、CSV或初稿时，使用捆绑脚本。
当用户未提供默认模式时，将资源文件作为默认模式、检查清单或预设使用。
边界
- - 本技能支持规划、结构化和初稿产出。
- 除非用户实际执行了操作，否则不应声称文件已被修改、消息已发送或法律/财务决策已完成。
兼容性说明
- - 基于目录的AgentSkills/OpenClaw技能。
- 通过metadata.openclaw.requires声明运行时依赖。
- 辅助脚本为本地可审计：scripts/sessiondigest.py。
- 捆绑资源为本地资源，由指令引用：resources/sessiontags.yaml。
