Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Build Personal Project Management System

ASecurity

Build a personal project management system that scales from simple lists to structured planning.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgo

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill build-personal-project-management-system --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Build Personal Project Management System?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Build Personal Project Management System
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-build-personal-project-management-system/badge)](https://www.skillsdirectory.com/skills/rondoflow-build-personal-project-management-system)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: build-personal-project-management-system
description: "Build a personal project management system that scales from simple lists to structured planning."
category: "Community"
author: community
version: "1.0.0"
icon: puzzle
---

## Core Behavior
- User mentions a project → help define scope, create folder
- User adds tasks → capture in project context
- Regular review prompts → surface stalled projects
- Create `~/projects/` as workspace

## First Question
- "What does done look like?" — define success before starting
- Scope creep is the project killer — clear boundaries from day one
- If they can't define done, the project isn't ready to start

## Project Types to Recognize
- One-time goal: clear end state, then archive (move apartments, plan trip)
- Ongoing area: never truly done, maintain indefinitely (health, career)
- Client work: external deadline, deliverables, often paid
- Learning: skill acquisition, may spawn other projects
- Creative: writing, art, building — process matters as much as output

## Minimal Project Structure
- Folder with project name: `~/projects/kitchen-renovation/`
- README.md: what, why, done criteria, deadline if any
- tasks.md: simple checklist, add as discovered
- notes.md: decisions made, research, reference material

## When User Starts a Project
- Ask: "What's the one sentence description?"
- Ask: "When does this need to be done?" (or "no deadline")
- Ask: "What's the very next physical action?"
- Create folder with README containing answers

## Task Capture
- Quick capture: "Add to kitchen project: call contractor"
- Tasks are concrete actions, not vague goals
- "Research options" is a task, "figure out renovation" is not
- Estimate size if useful: small/medium/large or hours

## When Projects Grow
- More than 15 tasks → consider grouping into phases
- Multiple workstreams → split into areas within project
- Dependencies emerging → note which tasks block others
- Collaborators involved → note who owns what

## Phase/Milestone Structure
For larger projects:
```
~/projects/kitchen-renovation/
├── README.md
├── phase-1-planning/
│   ├── tasks.md
│   └── notes.md
├── phase-2-demo/
├── phase-3-install/
└── archive/
```

## Active Project Limits
- Suggest maximum 3-5 active projects — more means nothing progresses
- Distinguish active (working this week) from someday (parked intentionally)
- Parked projects go in `~/projects/_someday/`
- Review someday quarterly — activate, archive, or delete

## Weekly Project Review
- What progressed this week?
- What's the next action for each active project?
- Any projects stalled more than 2 weeks?
- Any someday projects ready to activate?

## Stalled Project Detection
- No task completions in 2+ weeks → surface in review
- Ask: "Is this still a priority? Block or drop?"
- Options: push forward, park to someday, kill it
- Killing projects is healthy — better than zombie projects

## Project Completion
- Define done checklist in README from start
- When complete: review what went well, what didn't
- Archive to `~/projects/_archive/year/`
- Celebrate completion — don't just move to next thing

## Client/Work Projects
- Add: deadline, contact info, rate if applicable
- Track time if billing: simple log in project folder
- Deliverables list with status
- Communication log: key decisions and approvals

## What NOT To Suggest
- Complex project management app until files fail
- Rigid methodology (Agile, GTD, etc.) — adapt to user
- Gantt charts for personal projects — overkill
- Time tracking for non-billable work — adds friction

## Project Templates
Offer to create templates for recurring project types:
- "You start client projects often — want a template?"
- Template: folder structure, README prompts, standard tasks
- Keep templates minimal — adapt per project

## Integration Points
- Calendar: deadlines, milestones
- Contacts: collaborators, stakeholders
- Invoices: if client project with billing
- Goals: projects often serve larger goals

## Someday/Maybe List
- Ideas not ready for commitment
- Review monthly — promote, delete, or keep parking
- No guilt about long lists — it's a holding pen
- "This would be cool but not now" is valid

## Project Metrics (When Asked)
- How long did similar projects take?
- Completion rate: started vs finished
- Average project duration
- Don't track obsessively — only if user finds it useful

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →