10x-plan

Create detailed implementation plans through iterative research and structured questioning.

Updated May 23, 2026
One-click install
npx skills add https://github.com/BMS-kmusial/bms-stream-monitor --skill 10x-plan-bms-kmusial
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: 10x-plan
Source: https://github.com/BMS-kmusial/bms-stream-monitor/tree/main/.claude/skills/10x-plan
Command: npx skills add https://github.com/BMS-kmusial/bms-stream-monitor --skill 10x-plan-bms-kmusial

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning a vague task or ticket into a reliable implementation plan requires deep codebase research and many decisions; this Skill guides an interactive, iterative process that produces thorough technical specifications without costly rework. ## Core Features & Use Cases - Complexity-scaled questioning: Assesses task complexity (LOW/MEDIUM/HIGH) and asks a calibrated number of probing questions with recommended options and tradeoff analysis. - Upstream artifact awareness: Reads frame briefs and research docs from context/changes/<change-id>/ and treats them as authoritative, skipping questions already answered. - Structured plan output: Writes a phased plan.md with success criteria, a canonical ## Progress checklist section, and a concise two-page plan-brief.md summary. - Use Case: Given a ticket for a new API endpoint, the Skill researches the codebase with parallel sub-agents, asks targeted design questions, and produces a phased plan with automated and manual verification steps. ## Quick Start Invoke the skill with a change id or task description, for example by asking to create an implementation plan for the oauth-login change.

Frequently Asked Questions about 10x-plan

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a detailed implementation plan from a ticket?

Invoke the skill with the ticket description or a change id, and it will research the codebase with parallel sub-agents, assess complexity, ask calibrated questions, and write a phased plan.md with verification criteria.

How does the skill decide how many questions to ask?

It assesses complexity as LOW (4-6 questions), MEDIUM (7-10), or HIGH (11-15), then scales down when upstream artifacts like frame briefs or research docs already settled decisions, avoiding re-asking.

Can I use a research doc or frame brief as input?

Yes. Passing context/changes/<change-id>/research.md or frame.md reduces questioning because those artifacts are treated as authoritative sources of decisions already made.

What files does the planning skill write?

It writes plan.md containing phased implementation steps with success criteria and a Progress checklist section, plus plan-brief.md, a concise two-page summary of what, why, and key decisions.

What happens if the change folder is archived?

The skill refuses to write into context/archive/ paths and instructs you to open a new change instead, preventing edits to historical records.