← 返回 Skills 市场
457
总下载
0
收藏
5
当前安装
1
版本数
在 OpenClaw 中安装
/install project
功能描述
The AI project manager that never forgets, never drops a task, and never lets a deadline sneak up on anyone. Break any goal into phases, tasks, and milestone...
安全使用建议
This skill's description says it will read chats, detect blockers, escalate, and generate reports from ‘actual work data’, but the package metadata lists no integrations, credentials, or install steps. Before installing or enabling it, ask the publisher (or the platform) for specifics: which systems it will read/write (Slack, Teams, email, calendar, GitHub, Jira, etc.); what credentials/tokens are required; where data and reports are stored; how long data is retained; and what user consent/opt-out controls exist. If the skill needs access to chat or email, treat that as sensitive: verify least-privilege tokens, audit logs of actions, and the ability to revoke access. If the full SKILL.md contains concrete API calls or endpoints, share that so the manifest can be re-evaluated — the current mismatch is the reason for caution.
功能分析
Type: OpenClaw Skill
Name: project
Version: 1.0.0
The skill bundle contains only metadata and a descriptive markdown file (skill.md) outlining the persona and functions of an AI project manager. There is no executable code, no network requests, and no instructions that would lead to data exfiltration or unauthorized access.
能力评估
Purpose & Capability
The description promises automated tracking across people, teams, chats and external work data (escalations, status reports, updates from conversation). Yet the registry metadata declares no required environment variables, config paths, or install steps for integrating with chat systems, email, calendars, or PM tools. Either the skill relies on platform-provided connectors (not documented here) or the manifest omits necessary capabilities.
Instruction Scope
The SKILL.md explicitly says the skill updates trackers 'when you mention in a chat', logs blockers from team messages, escalates when owners don't respond, and generates status reports from 'actual work data'. Those behaviors imply reading and writing conversational and cross‑system data. The instructions as shown do not document what data sources will be read, where data is stored, or what endpoints messages/notifications are sent to.
Install Mechanism
This is an instruction‑only skill with no install spec and no code files, so there is nothing being downloaded or written to disk by the skill package itself — that is the lowest technical install risk. However, runtime integrations (connectors/APIs) would introduce risk if they exist but are undocumented.
Credentials
No environment variables or credentials are declared, yet the skill's behavior implies it will need access to chat systems, email/calendars, or PM tools. That mismatch is proportionally concerning because access to those services would require tokens/permissions and could expose sensitive data if not clearly specified and limited.
Persistence & Privilege
The skill is not marked always:true and does not request persistent installation behavior in the manifest. Autonomous invocation is allowed (platform default), which increases impact if the skill is later granted broad data access, but that alone is not an immediate coherence issue.
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 project - 安装完成后，直接呼叫该 Skill 的名称或使用
/project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
Initial release
元数据
常见问题
Project 是什么？
The AI project manager that never forgets, never drops a task, and never lets a deadline sneak up on anyone. Break any goal into phases, tasks, and milestone... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 457 次。
如何安装 Project？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install project」即可一键安装，无需额外配置。
Project 是免费的吗？
是的，Project 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Project 支持哪些平台？
Project 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 Project？
由 Duclawbot（@duclawbot）开发并维护，当前版本 v1.0.0。
推荐 Skills