skills/planning/SKILL.md
Structured planning and project breakdown using proven methodologies for goals, projects, and strategic initiatives. Use when users need to create plans, break down complex projects, set milestones, estimate timelines, identify dependencies, or develop action plans. Triggers include 'help me plan,' 'create a roadmap for,' 'break down this project,' 'what are the steps to,' or 'how should I approach.'
npx skillsauth add Hongyu-yu/matsci-ai-skills planningInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Guide users through structured, realistic planning for projects, goals, and strategic initiatives using proven project management frameworks.
When a planning request arrives, follow this systematic approach:
Activate for requests involving:
Before planning, gather essential information:
Goal & Scope:
Constraints:
Context:
Don't skip this: 5 minutes of clarification saves hours later.
Choose methodology based on project characteristics:
Use when: Large, complex projects; scope unclear; need comprehensive task inventory
Process: Top-down decomposition (Project → Phases → Deliverables → Tasks)
Best for: Construction, IT projects, events, product launches
Use when: Fixed deadline; event planning; goal clear but path uncertain
Process: Start from end goal, work backwards identifying prerequisites
Best for: Event planning, product launches, campaigns, deadline-driven work
Use when: Uncertain requirements; need flexibility; can deliver incrementally
Process: Plan in short iterations (sprints), adapt based on learning
Best for: Software development, research, new product development
Use when: Long project (3+ months); need checkpoints; staged delivery
Process: Divide into phases with gates, plan phase-by-phase
Best for: Research, construction, strategic initiatives, transformation
Combine methods: WBS for decomposition + Agile for execution, etc.
See references/frameworks-detailed.md for detailed guides on each methodology.
Hierarchical decomposition of work:
Levels: Project → Phases (3-7) → Deliverables → Tasks (1-3 days each) → Sub-tasks (if needed)
100% Rule: Each level represents 100% of parent's work
Tips:
Process:
Key: Be thorough with prerequisites - missing steps are common
Identify longest sequence of dependent tasks (determines minimum duration):
Concepts:
Use: Focus management attention on critical path tasks
Use scripts/critical_path.py for calculation.
Methods:
Key Principles:
Avoid: Planning fallacy (underestimating), optimism bias
See references/estimation-techniques.md for detailed methods.
Good Milestones:
Types: Deliverable completion, decision point, event, phase completion
Spacing: Weekly (short projects), bi-weekly/monthly (medium), monthly/quarterly (long)
Structure: 1 Objective + 3-5 Key Results
Objective: Qualitative, aspirational goal (what to achieve)
Key Results: Quantitative measures (how to measure success)
Example:
Use for: Strategic planning, not tactical tasks
Specific - Measurable - Achievable - Relevant - Time-bound
Example: "Increase NPS from 30 to 50 by Q4 end through improved onboarding"
Use for: Individual goals, small initiatives
Finish-to-Start (most common): B starts when A finishes
Start-to-Start: B starts when A starts
Finish-to-Finish: B finishes when A finishes
Ask for each task:
Categories: Mandatory (technical), Discretionary (preference), External (outside control), Internal (team control)
Look for:
Benefit: Shorter duration, better resource use
Caution: Don't over-parallelize (coordination overhead)
Common categories: Schedule, Technical, Resource, External, Scope, Quality
Ask: "What could go wrong?" Review past issues. Use pre-mortems.
For each risk: Probability (1-5) × Impact (1-5) = Risk Score
Prioritize: High-score risks for mitigation
See references/frameworks-detailed.md for risk register template.
People: Roles, skills, time commitment, availability
Tools: Software, hardware, procurement time
Budget: Personnel, tools, contingency (10-20%)
Other: Space, materials, information access
Responsible (does work) - Accountable (ultimately accountable) - Consulted (provides input) - Informed (kept in loop)
See references/templates.md for RACI template.
Strategic (Annual/Quarterly): Goals, themes, major initiatives. Tools: OKRs, roadmaps. Review quarterly.
Tactical (Monthly/Sprint): Deliverables, projects. Tools: WBS, sprint planning. Review weekly.
Operational (Weekly/Daily): Immediate tasks. Tools: Task lists, kanban. Review daily.
Principle: Plan detail should match certainty - detailed near-term, high-level long-term.
Tips: Keep iterations short (1-2 weeks). Don't skip retrospectives. Protect from disruptions.
See references/templates.md for sprint planning template.
Schedule: 20-30% for uncertain work, more for novel/complex
Resource: 10-20% budget contingency, backup personnel
Scope: Prioritize features (must-have vs nice-to-have), have cut list
For critical paths, ask:
Document: Trigger points, alternatives, decision makers
Track: Compare actual vs planned, identify variances early
Re-plan when: Assumptions wrong, scope changes, resource changes, risks occur
Remember: Plans are tools, not contracts. Adapt when reality differs.
High-Level Plan:
PROJECT: [Name]
GOAL: [What achieving]
TIMELINE: [Start] - [End]
OWNER: [Person]
PHASES:
1. Phase Name (dates) - Major deliverables
2. Phase Name (dates) - Major deliverables
MILESTONES:
- [Date]: Milestone
- [Date]: Milestone
TOP RISKS:
1. Risk [Mitigation]
2. Risk [Mitigation]
Detailed Task List:
TASK: [Description]
├─ Owner: [Person]
├─ Duration: [Estimate]
├─ Dependencies: [Prerequisites]
├─ Deliverable: [Output]
└─ Status: [Not started/In progress/Complete]
Use scripts/timeline_visualizer.py for visual timelines.
See assets/templates/ for ready-to-use formats.
Product Launch: Backward plan from launch date, include dry-run, post-launch monitoring
Research Project: WBS + phased approach, exploratory time, iteration based on findings
Event Planning: Backward plan, critical path for venue/speakers, detailed day-of checklist
Software Dev: Agile sprints, testing in each iteration, deployment and monitoring
Process Improvement: Phased rollout, training/change management, measurement cycles
Additional resources in this skill:
Reference these for deeper guidance or ready-made formats.
Remember: The best plan is the one that gets executed. Make plans clear, actionable, and realistic. Perfect planning is the enemy of starting.
tools
Spreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze data, visualization, recalculate formulas, for spreadsheet processing and analysis.
tools
Expert assistant for VASP (Vienna Ab initio Simulation Package) calculations - input file generation, parameter selection, workflow setup, and best practices for accurate DFT calculations
data-ai
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
tools
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.