← 返回 Skills 市场
xiaoke-bot

Daily to Goal AI Coach

作者 Xiao Ke · GitHub ↗ · v0.1.1 · MIT-0
cross-platform ⚠ suspicious
116
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install daily-to-goal-ai-coach
功能描述
Daily to Goal AI Coach — 在 ClawHub / OpenClaw 中一键安装,自动开通 Daily to Goal 工作空间,通过对话完成目标管理、任务追踪、贡献记录、每日摘要与团队周报的完整闭环。支持个人模式与团队模式,安装全程在 IM 渠道(Telegram 等)对话内完成,无需跳转网页。
使用说明 (SKILL.md)

Daily to Goal AI Coach

Daily to Goal 的一键式 AI Skill。安装后自动开通工作空间,通过对话完成目标与任务闭环管理。

功能

  • 对话式目标创建,引导补齐 SMART 要素
  • 任务创建时自动检测目标关联并建议绑定
  • 任务完成后追问贡献结果并回写目标进展
  • 工作日每日摘要(09:00 自动推送)
  • 每周周报草稿生成
  • 团队风险提醒

安装引导

安装全程在 IM 渠道对话内完成,无需打开电脑或跳转网页:

  • 新用户:Bot 引导完成工作空间创建,通过 IM 身份直接绑定账号
  • 已有账号:支持 API Token 绑定或邮箱验证码绑定

环境变量

参见 .env.example

安全使用建议
Do not install or provide secrets yet. The package is missing the server code that skill.json and the README refer to — it expects hosted endpoints (/api/skill-gateway/*) and sensitive environment variables (DATABASE_URL, CLAWHUB_INSTALLATION_SECRET, SKILL_GATEWAY_BASE_URL, WEB_ORIGIN). Before proceeding, ask the publisher for: (1) full source code for the backend that implements the /api/skill-gateway endpoints; (2) a trustworthy homepage or repository and release artifacts; (3) clear deployment instructions showing where data will be stored and who operates the service; and (4) privacy/data-flow details (what user/IM data is stored or sent elsewhere). If you must test, do so in an isolated environment (no production DB credentials) and never hand over real DB URLs or shared secrets to an unverified/opaque service. Providing those to an unknown backend could expose your data and permit privilege escalation.
功能分析
Type: OpenClaw Skill Name: daily-to-goal-ai-coach Version: 0.1.1 The skill bundle describes a productivity tool called 'Daily to Goal AI Coach' for task and goal management. The provided files (SKILL.md, skill.json, README.md) define standard integration components, including API endpoints for installation and automation triggers like daily digests and weekly reports. While it requires a DATABASE_URL environment variable, this is consistent with the stated purpose of managing a workspace, and there is no evidence of malicious intent, data exfiltration, or prompt injection.
能力评估
Purpose & Capability
The skill description promises a hosted workspace, automated daily/weekly triggers, and IM-based installation. That functionality legitimately requires a backend service (web endpoints, a database, and secrets). However the published package is instruction-only with no server code or install spec, while skill.json declares an entrypoint (/api/skill-gateway) and installation endpoints. This is internally inconsistent: either the skill is just documentation for a separate service, or the package is incomplete.
Instruction Scope
SKILL.md describes an IM-only install flow and refers to a '.env.example', but does not give concrete deployment steps. README explicitly requires calling /api/skill-gateway/installations/start and /complete and lists required env vars (DATABASE_URL, SKILL_GATEWAY_BASE_URL, CLAWHUB_INSTALLATION_SECRET, WEB_ORIGIN). The instructions therefore implicitly expect the agent/user to host accessible HTTP endpoints and provide database credentials — none of which are provided or automated by this package. That scope creep (needing hosted endpoints and secrets) is not surfaced in the registry metadata.
Install Mechanism
There is no install spec (instruction-only), so nothing is written to disk by the platform. That reduces immediate supply-chain risk. However because runtime behavior requires a separately hosted service, the real install risk depends entirely on where the user will host the service and what code they deploy (which is not included here).
Credentials
Registry metadata lists no required env vars, but README documents several sensitive variables: DATABASE_URL (Postgres connection), CLAWHUB_INSTALLATION_SECRET (shared secret), SKILL_GATEWAY_BASE_URL and WEB_ORIGIN. Those are plausible for a web-backed workspace/automation service, but the mismatch between declared requirements (none) and README is a red flag. Users should not supply database credentials or shared secrets to an opaque/incomplete package without knowing who runs the service and reviewing the code.
Persistence & Privilege
always is false (normal) and the skill is user-invocable. Autonomous invocation is allowed (default) but there is no shipped code to act on that. The main persistence/privilege concern is that the skill's operation would require long-lived credentials (DB URL and an installation secret). Granting those to an unknown or unreviewed backend would be high-risk.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install daily-to-goal-ai-coach
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /daily-to-goal-ai-coach 触发
  4. 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
v0.1.1
补充对话内引导流程设计:新增全程在 IM 渠道完成的安装引导,覆盖新用户注册和已有账号绑定两个场景
元数据
Slug daily-to-goal-ai-coach
版本 0.1.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Daily to Goal AI Coach 是什么?

Daily to Goal AI Coach — 在 ClawHub / OpenClaw 中一键安装,自动开通 Daily to Goal 工作空间,通过对话完成目标管理、任务追踪、贡献记录、每日摘要与团队周报的完整闭环。支持个人模式与团队模式,安装全程在 IM 渠道(Telegram 等)对话内完成,无需跳转网页。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 116 次。

如何安装 Daily to Goal AI Coach?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install daily-to-goal-ai-coach」即可一键安装,无需额外配置。

Daily to Goal AI Coach 是免费的吗?

是的,Daily to Goal AI Coach 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Daily to Goal AI Coach 支持哪些平台?

Daily to Goal AI Coach 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 Daily to Goal AI Coach?

由 Xiao Ke(@xiaoke-bot)开发并维护,当前版本 v0.1.1。

💬 留言讨论