CtrlK
BlogDocsLog inGet started
Tessl Logo

branch-wrapup

Pre-PR quality gate that runs build, type-check, lint, test, security scans, and finishes with a conventional commit. Use before creating a PR, after completing features, or when wrapping up a branch.

Install with Tessl CLI

npx tessl i github:0xrabbidfly/eric-cartman --skill branch-wrapup
What are skills?

87

1.51x

Quality

81%

Does it follow best practices?

Impact

100%

1.51x

Average score across 3 eval scenarios

SKILL.md
Review
Evals

Evaluation results

100%

25%

Pre-PR Security Review: AI Hub Portal

Constitutional security violations

Criteria
Without context
With context

localStorage detected

100%

100%

console.log detected

100%

100%

Hardcoded secret detected

100%

100%

Hardcoded i18n string detected

0%

100%

Violations are P0

0%

100%

Security phase is FAIL

100%

100%

Branch not ready

100%

100%

File references included

100%

100%

Verification report produced

100%

100%

Without context: $0.2013 · 1m 3s · 8 turns · 13 in / 3,796 out tokens

With context: $0.4432 · 2m 9s · 16 turns · 273 in / 7,075 out tokens

100%

55%

Pre-PR Quality Audit: Dashboard Refactor

Code smell detection and tracking

Criteria
Without context
With context

eval() identified as P0

100%

100%

No commit on P0

100%

100%

code-smells.md written

0%

100%

Refactoring opportunities listed

0%

100%

Creative Implementation Ideas section

0%

100%

1-2 creative ideas present

0%

100%

Relative import flagged

100%

100%

Orphan script flagged

66%

100%

Without context: $0.4236 · 2m 35s · 16 turns · 21 in / 8,277 out tokens

With context: $0.5453 · 2m 43s · 21 turns · 280 in / 8,547 out tokens

100%

20%

Branch Wrapup: Payment Integration Feature

Conventional commit and verification report

Criteria
Without context
With context

Conventional format

100%

100%

Valid commit type

100%

100%

Scope present

100%

100%

Ticket ID included

100%

100%

Body lists key changes

100%

100%

Verification report produced

100%

100%

Report uses box format

20%

100%

Overall status is READY

100%

100%

Commit phase shown as DONE

0%

100%

Phases ordered correctly

60%

100%

Without context: $0.1282 · 39s · 9 turns · 14 in / 2,113 out tokens

With context: $0.2386 · 56s · 15 turns · 20 in / 2,856 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.