recorder — recorder skill for AI agents recorder, LifeKernel, community, recorder skill for AI agents, ide skills, JSONL recording format, UTF-8 encoding without BOM, unified record management, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for Data Management Agents requiring unified JSONL record-keeping for knowledge, news, lifelog, and task data Recorder is a skill that unifies JSONL recording for various data types, following a strict schema defined in .codex/schema.json.

Features

Unifies records into a single JSONL format
Ensures UTF-8 encoding without BOM
Follows a strict schema defined in .codex/schema.json
Supports CRUD operations for records
Allows for automatic recording and updating of records

# Core Topics

recorder skill for AI agents JSONL recording format UTF-8 encoding without BOM unified record management
Krual-T Krual-T
[0]
[0]
Updated: 3/8/2026

Agent Capability Analysis

The recorder skill by Krual-T is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for recorder skill for AI agents, JSONL recording format, UTF-8 encoding without BOM.

Ideal Agent Persona

Ideal for Data Management Agents requiring unified JSONL record-keeping for knowledge, news, lifelog, and task data

Core Value

Empowers agents to manage records in a standardized JSONL format, ensuring data consistency and ease of management through UTF-8 encoded files without BOM, adhering to a strict schema defined in `.codex/schema.json`

↓ Capabilities Granted for recorder

Unifying knowledge and news records into a single JSONL file
Automating lifelog and task updates with CRUD operations
Ensuring data integrity through schema validation

! Prerequisites & Limits

  • Requires adherence to `.codex/schema.json` schema
  • UTF-8 encoding without BOM necessary
  • JSONL format compatibility required
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

recorder

Install recorder, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

统一 JSONL 记录（knowledge / news / lifelog / agent_kernel_memory / tasks）

概述

将“记录类数据”统一为 JSONLCRUD，并确保 UTF-8 无 BOM。所有记录必须遵循 .codex/schema.json 的强约束 Schema。

适用场景

  • 新增或更新 knowledge、news、lifelog、agent_kernel_memory、tasks 等记录类数据
  • 希望自动化记录并保持结构统一

输入

  • record_type：knowledge | news | lifelog | agent_kernel_memory | tasks | update | delete
  • update：按 id + key + value 查询记录后就地更新（覆盖写入）
  • delete：按 id 查询记录后删除
  • data：记录内容（按各自 schema）
  • related_files：相关文件路径（可选）
  • auto_record：是否自动写入 lifelog（默认：对 knowledge 为 true）

输出

  • 对应 JSONL 文件追加一条记录（append-only）
  • 若开启 auto_record，同时写入一条 lifelog 记录

统一步骤

  1. 确定目标路径
    • knowledge：workspace/records/knowledge/knowledge.jsonl
    • news：workspace/records/news/news.jsonl
    • lifelog：workspace/records/lifelog/YYYY/MM/DD.jsonl
    • agent_kernel_memory：workspace/records/agent_kernel_memory/agent_kernel_memory.jsonl
    • tasks：workspace/records/tasks/tasks.jsonl
  2. 生成记录对象
    • 统一字段必填：id、type、timestamp、source、content
    • 其他字段按 .codex/schema.json 的 record_type 必填/可选项填充
    • id：默认自动生成 UUID（uuid4），如需手动指定需显式传入
    • 业务字段按 record_type schema 补充
  3. UTF-8 无 BOM CRUD
    • CRUD必须符合.codex/schema.json 的强约束 Schema`
  4. 可选：auto record
    • 当 record_type = knowledge 且 auto_record = true 时，追加一条 lifelog
  5. 必要时更新可视化
    • knowledge/lifelog/tasks：workspace/view/index.html
    • news：workspace/view/news.html

更新记录（CRUD）

用于在 JSONL 中“就地更新/删除”记录：先查询目标记录与所在文件，再读取文件并覆盖写回（保留原有非 JSON 行）。 注意：对 agent_kernel_memory 的 delete 为逻辑删除（写入 deleted: true），不进行物理删除。

参数：

  • record_type：update
  • target_type：knowledge | news | lifelog | agent_kernel_memory | tasks
  • id：目标记录 id
  • key：需要更新的字段名
  • value / value_json：更新值（字符串或 JSON）

示例（PowerShell，更新）：

powershell
1python .\\.codex\\skills\\recorder\\scripts\\record_jsonl.py --record-type update --target-type tasks --id "b3e9c6b0-9f5f-47ff-8d62-1f5f8b7f2a1c" --key status --value "done"
powershell
1python .\\.codex\\skills\\recorder\\scripts\\record_jsonl.py --record-type update --target-type knowledge --id "7f5d6f8a-1c3a-4f7e-9e42-2c3e1d6b0e9a" --key tags --value-json "[\"coworker\",\"research\"]"

示例（PowerShell，删除）：

powershell
1python .\\.codex\\skills\\recorder\\scripts\\record_jsonl.py --record-type delete --target-type tasks --id "b3e9c6b0-9f5f-47ff-8d62-1f5f8b7f2a1c"

脚本（推荐）

  • scripts/record_jsonl.py
    • 统一写入 knowledge/lifelog/agent_kernel_memory/tasks
    • knowledge 默认 auto record 到 lifelog

示例：

Windows（PowerShell）：

powershell
1python .\.codex\skills\recorder\scripts\record_jsonl.py --record-type knowledge --title "Live Preview 目录列表返回反斜杠" --solution "对 href 做 decodeURIComponent 并将 \\ 替换为 /" --tags "lifelog,live-preview" --module work --source conversation
powershell
1python .\.codex\skills\recorder\scripts\record_jsonl.py --record-type lifelog --description "整理归档索引" --module work --source conversation --status completed --related-file docs/skills_archive/ARCHIVE_LOG.md

Linux（bash）：

bash
1python ./.codex/skills/recorder/scripts/record_jsonl.py --record-type knowledge --title "Live Preview 目录列表返回反斜杠" --solution "对 href 做 decodeURIComponent 并将 \\ 替换为 /" --tags "lifelog,live-preview" --module work --source conversation
bash
1python ./.codex/skills/recorder/scripts/record_jsonl.py --record-type lifelog --description "整理归档索引" --module work --source conversation --status completed --related-file docs/skills_archive/ARCHIVE_LOG.md

字段规范（通用）

  • id：UUID（uuid4）
  • type：knowledge | news | lifelog | agent_kernel_memory | tasks
  • timestamp：ISO8601
  • source：conversation | from_screenshot
  • content：用于统一检索的正文摘要
  • module：work | personal | learning | health（可选）
  • related_files：workspace 内相关路径数组（可选）

编码规范

  • 所有记录文件必须 UTF-8 无 BOM

自动记录（auto record）

  • 默认策略：对 knowledge 写入时开启
  • auto record 的 lifelog 描述格式：
    • 新增 knowledge：<title/summary>

注意事项

  • JSONL 一行一条记录，不可写多行
  • 不记录 secrets
  • 记录描述使用中文，字段名可保留英文

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is recorder?

Ideal for Data Management Agents requiring unified JSONL record-keeping for knowledge, news, lifelog, and task data Recorder is a skill that unifies JSONL recording for various data types, following a strict schema defined in .codex/schema.json.

How do I install recorder?

Run the command: npx killer-skills add Krual-T/LifeKernel/recorder. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for recorder?

Key use cases include: Unifying knowledge and news records into a single JSONL file, Automating lifelog and task updates with CRUD operations, Ensuring data integrity through schema validation.

Which IDEs are compatible with recorder?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for recorder?

Requires adherence to `.codex/schema.json` schema. UTF-8 encoding without BOM necessary. JSONL format compatibility required.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add Krual-T/LifeKernel/recorder. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use recorder immediately in the current project.

Related Skills

Looking for an alternative to recorder or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

★ 138.4k
⑂ 0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI