Project Management Guru (ADHD)

Expert project manager for ADHD engineers managing multiple concurrent projects. Specializes in hyperfocus management, context-switching minimization, and parakeet-style gentle reminders.

This skill reads like a design + implementation guide for an automated reminder/monitoring system, but the package declares no credentials or install steps — that's a mismatch. Before installing or enabling it: - Ask the publisher for the source repository and a security/privacy description (what APIs it will call, exactly which tokens are required, and why). - Do not provide broad tokens (full workspace/admin). If you must supply credentials, use least-privilege service accounts (Slack bot scoped only to sending DMs, calendar read-only where possible). - Inspect SKILL.md for hidden unicode/control characters (the scan found them); view the raw file to ensure there are no obfuscated instructions. - Confirm how 'send_slack_dm', 'schedule_task', webhooks, and 'prompt_user' are implemented in your environment — these are referenced but not provided. - If you plan to let the skill run autonomously, test it in a sandboxed account/workspace first and audit outgoing messages and scheduled actions. If the owner cannot explain the missing integration configuration or provide a canonical source repo, treat the skill as untrusted and do not grant credentials or enable autonomous invocation.

Type: OpenClaw Skill Name: project-management-guru-adhd Version: 1.0.0 The skill bundle provides instructions and Python code for an AI agent to act as a project manager for ADHD engineers. All files, including the SKILL.md instructions, are aligned with this stated purpose. The Python code implements features like context-switching tracking, hyperfocus monitoring, parakeet-style reminders, and task chunking. While the code implies interaction with external systems like Slack (`send_slack_dm`) and a calendar API (`calendar_api.get_events`), these are plausible and necessary functionalities for a project management skill and are used for benign purposes (e.g., sending reminders, scheduling breaks). There is no evidence of data exfiltration, malicious execution, persistence mechanisms, prompt injection with harmful objectives, or obfuscation. The `prompt_user` function is used for legitimate user interaction regarding workflow management.