finish-branch
Use when implementation is complete, all tests pass, and the work needs to be integrated or finalized
70
Quality
57%
Does it follow best practices?
Impact
91%
1.93xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/finish-branch/SKILL.mdEvaluation results
100%
37%Branch Finalization: Validator Feature
Test verification gate
Skill announcement
0%
100%
Tests executed
100%
100%
Failures displayed
100%
100%
Cannot-proceed message
0%
100%
Options not presented
100%
100%
Without context: $0.4103 · 2m 3s · 22 turns · 29 in / 6,093 out tokens
With context: $0.5597 · 2m 29s · 31 turns · 275 in / 7,284 out tokens
96%
54%Automate Branch Finalization for the Development Team
Branch finalization workflow automation
Skill announcement
0%
100%
Test gate before options
100%
100%
Test failure stops workflow
40%
100%
Exactly 4 options
100%
100%
Staging docs exclusion
33%
100%
Discard typed confirmation
0%
100%
Draft PR flag
100%
100%
No auto worktree cleanup
25%
50%
Post-merge test run
0%
100%
Autostash pull
0%
100%
Without context: $0.4373 · 2m 12s · 20 turns · 26 in / 7,454 out tokens
With context: $0.6383 · 2m 46s · 24 turns · 30 in / 10,490 out tokens
78%
42%Finalize the Price Formatter Feature Branch
Local merge with staging exclusions
Skill announcement
0%
100%
Pre-merge test run
100%
100%
Base branch identified
100%
100%
4 options shown
0%
0%
Planning docs not staged
0%
100%
Checkout base branch
100%
100%
Autostash pull
0%
0%
Post-merge test run
0%
100%
Feature branch deleted
0%
100%
No worktree auto-cleanup
100%
100%
Without context: $0.5312 · 1m 53s · 31 turns · 36 in / 6,172 out tokens
With context: $0.7149 · 2m 27s · 40 turns · 445 in / 7,962 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
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.