Use when you have a spec or requirements for a multi-step task, before touching code
82
67%
Does it follow best practices?
Impact
86%
3.58xAverage score across 8 eval scenarios
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./bundled/skills/writing-plans/SKILL.mdTest design guidance for unfamiliar implementers
Specific test function signatures
100%
100%
Concrete assert statements
66%
100%
Happy path and edge/error cases
100%
100%
Expected failure output in TDD verify step
40%
70%
Exact pytest run command
50%
100%
Test file in Files section
0%
100%
TDD step order maintained
30%
100%
Minimal implementation step
0%
100%
Dated plan file path
0%
100%
Plan header present
20%
100%
Execution handoff offering two choices with sub-skill references
Offers subagent-driven option
0%
100%
Offers parallel session option
0%
100%
References executing-plans sub-skill
0%
60%
References subagent-driven-development sub-skill
0%
0%
Zero-context plan writing with complete task structure and numbered tasks
Numbered task format
40%
100%
Self-contained instructions
80%
88%
Multiple tasks covering distinct components
100%
100%
Test file paths included
50%
75%
DRY/YAGNI adherence
80%
80%
Exact file paths, complete code snippets, and runnable commands in tasks
Files section with exact paths
60%
100%
Complete code blocks
72%
88%
Exact run commands
0%
100%
Expected output descriptions
0%
100%
Plan document structure with correct header, save path, and announcement
Skill announcement
0%
100%
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
25%
100%
Verify test passes step
0%
100%
Commit step per task
0%
100%
@ syntax sub-skill references in plan steps
@ syntax used
0%
0%
Colon-separated namespace format
0%
0%
@ reference in header sub-skill callout
0%
100%
Skill announcement
0%
0%
Dated plan file path
0%
100%
Header: Goal, Architecture, Tech Stack
20%
100%
Files section with annotations
30%
100%
Complete code blocks
100%
100%
Exact run commands
100%
100%
Documentation references and zero-context completeness
External doc references present
75%
65%
Doc reference per relevant task
50%
50%
Zero-context completeness
86%
80%
Complete code examples
90%
100%
Exact install/run commands
100%
100%
Files section with annotations
50%
100%
TDD cycle steps
0%
100%
Dated plan file path
0%
100%
Plan header present
40%
100%
Sub-skill reference in header
0%
100%
f627ab5
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.