Interview-based strategic planning for complex software tasks. Conducts structured requirements gathering, gap analysis, and generates detailed work plans before implementation begins.
npx skills add https://github.com/ArabelaTso/Skills-4-SE --skill strategic-planner
An intelligent interviewer that helps think through complex software tasks before writing code. Separates planning from execution to prevent cognitive drift and scope creep.
Adapt interview style based on intent:
| Intent | Focus | Example Questions |
|--------|-------|-------------------|
| Refactoring | Safety — behavior preservation | "What tests verify current behavior?" "Rollback strategy?" |
| Build from Scratch | Discovery — patterns first | "Found pattern X in codebase. Follow it or deviate?" |
| Mid-sized Task | Guardrails — exact boundaries | "What must NOT be included? Hard constraints?" |
| Architecture | Strategic — long-term impact | "Expected lifespan? Scale requirements?" |
Clearance check after each response:
Continue interviewing until all checks pass. Don't overwhelm — start with the most important questions, follow up as needed.
Before writing the plan, catch what the interview missed:
The plan author has "working memory ADHD" — makes connections that never make it onto the page. Gap analysis forces externalization of implicit knowledge.
Write a structured plan with:
Validate the plan against four criteria:
Approval requires:
If rejected, fix issues and resubmit. No maximum retry limit.
User: "I want to refactor the auth system to support OAuth"
Interview output:
Q: What OAuth providers need support? → Google + GitHub
Q: Keep existing password auth? → Yes, alongside OAuth
Q: What tests exist for current auth? → Unit tests in tests/auth/
Q: Rollback strategy? → Feature flag, disable OAuth without removing code
Plan output: 6 tasks with specific file paths, acceptance criteria, dependency ordering, and test strategy.
Inspired by: oh-my-opencode Prometheus planning agent
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Take arabelatso/strategic-planner from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.