← 返回 Skills 市场
Memory Tasks
作者
Paul Hernandez
· GitHub ↗
· v0.1.0
· MIT-0
235
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install memory-tasks
功能描述
Task management via Basic Memory schemas: create, track, and resume structured tasks that survive context compaction. Uses BM's schema system for uniform not...
安全使用建议
This skill is coherent and appears safe to install from an internal-consistency standpoint. Before using: confirm your agent/platform exposes the referenced Basic Memory APIs (write_note, search_notes, schema_validate), and be mindful of what you write into task 'context' (avoid pasting secrets, credentials, or sensitive file contents). Periodically run schema_validate and review stored task notes or access controls to ensure sensitive information isn't persisted unintentionally. If you want higher assurance, provide platform docs or confirm the exact API surface for the Basic Memory functions referenced.
功能分析
Type: OpenClaw Skill
Name: memory-tasks
Version: 0.1.0
The memory-tasks skill bundle provides a structured framework for an AI agent to manage its own task list and maintain state across context window resets using a 'Basic Memory' system. The SKILL.md file defines a schema for tasks and provides clear instructions for creating, updating, and querying task notes using standard API calls like write_note and search_notes. No evidence of malicious intent, data exfiltration, or unauthorized execution was found.
能力评估
Purpose & Capability
The name/description (task management using Basic Memory schemas) matches the SKILL.md: it documents a Task schema, how to create/search/update tasks, and how to flush before compaction. Nothing requested (no env vars, no installs) is unnecessary for that purpose.
Instruction Scope
All runtime instructions are limited to note operations (write_note, search_notes, schema_validate, schema_diff) and managing task content. The skill does not instruct reading unrelated system files or sending data to external endpoints. It does encourage including file paths and context in task notes, but it does not instruct the agent to read or exfiltrate those files.
Install Mechanism
No install spec and no code files — instruction-only. This is the lowest-risk install profile and is appropriate for the described behavior.
Credentials
The skill declares no required environment variables, credentials, or config paths. That is proportionate to an instruction-only skill that relies on built-in Basic Memory note APIs.
Persistence & Privilege
always is false and model invocation is allowed (platform default). The skill does not request forced inclusion or modification of other skills or system-wide settings.
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 memory-tasks - 安装完成后，直接呼叫该 Skill 的名称或使用
/memory-tasks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
v0.1.0
- Initial release of memory-tasks skill for managing and resuming structured tasks using Basic Memory schemas.
- Supports creation, tracking, and updating of tasks that persist across context compaction via schema-driven notes.
- Task schema includes fields for description, status, steps, context, assignment, blockers, parent tasks, and more.
- Integrates with knowledge graph and supports full querying and validation with BM’s schema system.
- Provides guidelines for creating, updating, and completing tasks to maintain work continuity.
元数据
常见问题
Memory Tasks 是什么？
Task management via Basic Memory schemas: create, track, and resume structured tasks that survive context compaction. Uses BM's schema system for uniform not... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 235 次。
如何安装 Memory Tasks？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install memory-tasks」即可一键安装，无需额外配置。
Memory Tasks 是免费的吗？
是的，Memory Tasks 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Memory Tasks 支持哪些平台？
Memory Tasks 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 Memory Tasks？
由 Paul Hernandez（@phernandez）开发并维护，当前版本 v0.1.0。
推荐 Skills