CtrlK
BlogDocsLog inGet started
Tessl Logo

changelog-generator

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Install with Tessl CLI

npx tessl i github:Lingjie-chen/MT5 --skill changelog-generator
What are skills?

55

Does it follow best practices?

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

100%

Release Notes for Taskflow v2.1.0

Noise filtering and user-friendly translation

Criteria
Without context
With context

Output saved to CHANGELOG.md

100%

100%

Release header present

100%

100%

New Features section

100%

100%

Bug Fixes section

100%

100%

All 5 features included

100%

100%

All 4 bug fixes included

100%

100%

Refactors excluded

100%

100%

Tests excluded

100%

100%

Chore/CI/Docs excluded

100%

100%

User-friendly language

100%

100%

Bold feature names

100%

100%

Without context: $0.1401 · 34s · 8 turns · 11 in / 1,898 out tokens

With context: $0.2903 · 1m 7s · 18 turns · 305 in / 3,696 out tokens

100%

Weekly Product Update — Meridian Analytics

Custom style guide adherence

Criteria
Without context
With context

Output saved to CHANGELOG.md

100%

100%

No emoji used

100%

100%

Past-tense entries

100%

100%

Executive summary line

100%

100%

Correct section headings

100%

100%

Bold entry format

100%

100%

Features included

100%

100%

Performance entry included

100%

100%

Bug fixes included

100%

100%

Internal commits excluded

100%

100%

Date range in header

100%

100%

Improvements section present

100%

100%

Without context: $0.1217 · 36s · 8 turns · 13 in / 2,157 out tokens

With context: $0.3860 · 1m 34s · 21 turns · 27 in / 4,386 out tokens

97%

7%

Release Changelog for Stockpile v3.0.0

Version release categorization and formatting

Criteria
Without context
With context

Output saved to CHANGELOG.md

100%

100%

Version header

100%

100%

Breaking changes section

100%

100%

Both breaking changes listed

100%

100%

New features section

100%

100%

All features included

100%

100%

Bug fixes included

100%

100%

Security section or entry

100%

100%

Performance entry included

100%

100%

Internal commits excluded

0%

70%

User-friendly descriptions

100%

100%

Structured sections

100%

100%

Without context: $0.2028 · 1m 39s · 12 turns · 18 in / 3,223 out tokens

With context: $0.4433 · 1m 51s · 22 turns · 1,450 in / 6,114 out tokens

Evaluated
Agent
Claude Code

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.