Lofy Projects

Project management for the Lofy AI assistant — tracks multiple projects with milestones, priority scoring engine (urgency × job relevance × momentum × energy match), meeting prep automation, time logging, stale project alerts, and work session recommendations. Use when managing projects, prioritizing work, preparing for meetings, or tracking milestones and deadlines.

Security Scan

The skill's requirements and instructions are internally consistent for a local project-management helper, but a few runtime behaviors (meeting detection and proactive sending) are vague and could cause the agent to access external calendars or messaging channels if not constrained.

Purpose & Capability

Name/description (project management, prioritization, meeting prep, time logging) match the instructions: read/update a projects JSON, compute priority scores, flag stale projects, and provide meeting prep. The skill does not request unrelated binaries, credentials, or config paths.

Instruction Scope

Most instructions are confined to reading/updating data/projects.json and producing recommendations. However, 'When a meeting is detected' and 'Send prep 2 hours before' are underspecified: they imply detecting external events (calendar/meeting system) and sending messages but do not declare how or where. That ambiguity could lead the agent to access calendars, email, or messaging integrations without explicit declared access.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk. Nothing is downloaded or written by an installer.

Credentials

The skill declares no required environment variables, credentials, or config paths. Its stated operations (local JSON read/write) are proportionate to the purpose. There is no unexplained request for secrets or external credentials.

Persistence & Privilege

always:false and default autonomous invocation are appropriate. That said, the instruction to 'proactively send prep 2 hours before' implies ongoing monitoring or scheduled triggers; achieving that behavior would require either external scheduler/cron or background invocation and possibly access to calendar/messaging — the skill does not request persistent presence explicitly.

Assessment

This skill appears coherent for local project tracking: it wants to read and update a projects JSON file and produce prioritization and meeting-prep text. Before installing, confirm two things: (1) where meeting detection and 'send prep' actions will read/write (calendar, email, chat), and ensure you are comfortable granting access to only those specific services; (2) that the agent's file-write permissions are limited to the intended data/projects.json location (backup your files if needed). If you need the skill to send messages or access calendars, prefer explicit, auditable connectors (e.g., a calendar API token you supply with clear scopes) rather than letting the agent guess how to detect meetings. If you cannot get clarification from the author, treat proactive scheduling/sending as an operational risk and disable autonomous/background invocation for this skill.

Project Pilot — Project & Academic Manager

Keeps projects, coursework, and research organized. Tracks status, deadlines, blockers, and helps prioritize work time.

Data File: data/projects.json

{
  "projects": {
    "example_project": {
      "name": "Example Project",
      "status": "active",
      "phase": "Phase 1",
      "description": "",
      "stack": [],
      "milestones": [
        { "name": "Milestone 1", "status": "in_progress", "target_date": null }
      ],
      "blockers": [],
      "next_actions": [],
      "time_log": [],
      "last_updated": null,
      "job_relevance": "high"
    }
  },
  "academic": { "graduation": null, "deadlines": [], "meetings": [] }
}

Priority Engine

When user asks "what should I work on?":

Priority = (Urgency × 3) + (Job_Relevance × 2) + (Momentum × 1) + (Energy_Match × 1)

Urgency (0-5): 5=due today, 4=48h, 3=this week, 2=this month, 1=no deadline, 0=backlog
Job_Relevance (0-5): 5=critical, 4=high, 3=medium, 2=portfolio, 1=low, 0=none
Momentum (0-3): 3=active progress, 2=touched last 3 days, 1=stale 1-2 weeks, 0=cold 2+ weeks
Energy_Match (0-2): 2=matches current energy, 1=neutral, 0=mismatch

Time-Based Recommendations

• < 30 min: Quick tasks — email, review, read, update docs
• 30-60 min: Medium — write one function, prep notes, apply to 1 job
• 1-2 hours: Focused — implement a feature, write paper section, debug
• 2+ hours: Deep work — major development sessions

Meeting Prep

When a meeting is detected:

1. Identify related project
2. Pull recent time_log entries since last meeting
3. List current blockers
4. Generate 2-3 questions to ask
5. Suggest what to demo/present
6. Send prep 2 hours before

Status Updates via Natural Language

• "Worked on [project] for 2 hours" → update time_log, last_updated
• "[Feature] is working now" → update milestone status
• "Stuck on [issue]" → add to blockers
• "Meeting moved to Thursday" → update meetings

Instructions

1. Always read data/projects.json before responding about projects
2. Update JSON after any project conversation
3. For "what should I work on?" — ONE clear recommendation + one alternative
4. Flag stale projects: "[Project] hasn't been touched in X days"
5. Before meetings, proactively send prep
6. Prioritize job-critical projects unless there's a deadline override