Use when you have a spec or requirements for a multi-step task, before touching code
80
53%
Does it follow best practices?
Impact
82%
4.31xAverage score across 10 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/writing-plans/SKILL.mdPlan document structure with correct header, save path, and announcement
Skill announcement
0%
0%
Dated file path
0%
100%
Header contains Goal
0%
100%
Header contains Architecture and Tech Stack
0%
100%
Sub-skill reference in header
0%
100%
TDD cycle with bite-sized steps and frequent commits
Write failing test step
0%
100%
Verify test fails step
0%
100%
Minimal implementation step
0%
100%
Verify test passes step
0%
100%
Commit step per task
0%
100%
Execution handoff offering two choices with sub-skill references
Offers subagent-driven option
0%
0%
Offers parallel session option
0%
0%
References executing-plans sub-skill
0%
100%
References subagent-driven-development sub-skill
0%
0%
Zero-context plan writing with complete task structure and numbered tasks
Numbered task format
0%
100%
Self-contained instructions
88%
100%
Multiple tasks covering distinct components
100%
100%
Test file paths included
100%
100%
DRY/YAGNI adherence
66%
100%
Exact file paths, complete code snippets, and runnable commands in tasks
Files section with exact paths
0%
100%
Complete code blocks
0%
100%
Exact run commands
0%
100%
Expected output descriptions
0%
100%
45a1bdf
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.