skills.rest
Assamir
AssamirCOMMUNITY
Explore all skills by this author →
GitHub

10x-plan

Creates detailed phased implementation plans through iterative research and structured questioning.

Updated Jul 4, 2026
Search Tags:#planning#implementation plan#requirements gathering#technical specification#codebase research#phased workflow
One-click install
npx skills add https://github.com/Assamir/ai-toolkit --skill 10x-plan-assamir
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: 10x-plan
Source: https://github.com/Assamir/ai-toolkit/tree/main/.cursor/skills/10x-plan
Command: npx skills add https://github.com/Assamir/ai-toolkit --skill 10x-plan-assamir

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Writing implementation plans without sufficient codebase research or requirement clarification leads to costly rework and missed edge cases. This Skill guides an interactive, iterative planning process that grounds every plan in verified codebase facts and explicit user decisions. ## Core Features & Use Cases - Adaptive Questioning: Scales the number and focus of clarifying questions based on task complexity (LOW/MEDIUM/HIGH) and upstream artifacts like frame briefs and research docs, avoiding redundant questions. - Parallel Codebase Research: Spawns Explore and general-purpose sub-agents to map relevant files, patterns, and conventions before writing the plan. - Structured Plan Output: Writes a phased plan to context/changes/<change-id>/plan.md with automated and manual success criteria, plus a two-page plan brief and a machine-readable Progress section. - Use Case: Given a ticket to add OAuth login, the Skill reads prior research, asks targeted architecture and edge-case questions with recommended options, then produces a multi-phase plan with verification steps and progress checkboxes. ## Quick Start Ask the AI to create a detailed implementation plan for your task, optionally passing a change-id or path to an existing research or frame document.

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 with AI?▼

Invoke the planning skill with a task description, ticket reference, or change-id. It reads referenced files fully, researches the codebase with parallel sub-agents, asks complexity-scaled clarifying questions, then writes a phased plan with success criteria to context/changes/<change-id>/plan.md.

How does the skill decide how many questions to ask?▼

Question count scales with assessed complexity: LOW gets 4-6, MEDIUM 7-10, HIGH 11-15. Providing upstream artifacts reduces this further — a frame brief plus research doc can drop questioning to 1-7 questions focused only on solution design.

Can I use existing research documents with the planning skill?▼

Yes. Pass a research.md or frame.md path when invoking, and the skill treats them as authoritative. It skips re-asking settled questions and reuses code references instead of re-running redundant exploration.

What files does the implementation plan skill generate?▼

It writes plan.md containing phases, success criteria, and a Progress checkbox section, plus plan-brief.md as a two-page summary. Both live in context/changes/<change-id>/, and change.md is updated to status: planned.

When should I not use a full interactive planning workflow?▼

Skip it for trivial single-file changes or config tweaks where questioning overhead exceeds the risk of rework. The skill itself flags LOW complexity tasks, but very small edits are often faster to implement directly.

Related Skills

Explore More Software Engineering Skills→
shopsysshopsys
349

create-plan

Generate iterative implementation plans from codebase patterns and Jira tickets.

Official
Advanced
OskarovskyOskarovsky

10x-tdd

Executes approved implementation plans phase by phase through the red-green-refactor test-first cycle.

Community
Advanced
tonone-aitonone-ai
69

flux-health

Detect data quality issues and pipeline health across databases and warehouses.

Official
Intermediate
21StarkCom21StarkCom

stark-author

Authors human-gated specs and task DAGs through recon, interview, and sign-off.

Official
Advanced