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.
63
45%
Does it follow best practices?
Impact
99%
1.03xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/changelog-generator/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-written description with strong specificity and natural trigger terms that clearly define a distinct niche. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The last sentence ('Turns hours of manual changelog writing into minutes') is slightly promotional fluff but does contain useful trigger terms.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to generate a changelog, write release notes, summarize git commits for users, or prepare release documentation.'
Remove or rephrase the marketing-style sentence ('Turns hours of manual changelog writing into minutes of automated generation') and replace it with concrete trigger guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: analyzing commit history, categorizing changes, transforming technical commits into customer-friendly release notes, and automated changelog generation. | 3 / 3 |
Completeness | The 'what' is clearly answered with specific actions, but there is no explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied through the description of capabilities, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'changelogs', 'git commits', 'commit history', 'release notes', 'changelog writing'. These cover the main ways users would describe this need. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a very clear niche: git-commit-to-changelog transformation. This is distinct from general git skills, general writing skills, or documentation skills, with specific terms like 'changelogs', 'release notes', and 'commit history' that define a narrow use case. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a marketing description or README for a product feature than an actionable skill for Claude. It lacks any executable code, concrete git commands, commit parsing logic, or categorization rules. The example output is helpful but without implementation guidance, Claude would have to invent the entire approach from scratch.
Suggestions
Add concrete git commands for extracting commit history (e.g., `git log --oneline --since='2024-03-01' --until='2024-03-15'`) and show how to parse the output.
Provide explicit categorization rules with patterns (e.g., commits starting with 'feat:' → New Features, 'fix:' → Bug Fixes) and a concrete mapping table or code.
Include a step-by-step workflow: 1) Run git log command, 2) Parse and categorize commits, 3) Filter noise (with specific exclusion patterns like 'chore:', 'ci:'), 4) Transform to user-friendly language, 5) Format output.
Remove the 'When to Use This Skill', 'Related Use Cases', and most of the 'Tips' sections—these waste tokens on information Claude can infer.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Heavily padded with unnecessary content. The 'When to Use This Skill' section lists 7 obvious use cases Claude doesn't need. 'What This Skill Does' explains the concept rather than instructing. 'Tips' and 'Related Use Cases' sections add little actionable value. Much of this is describing rather than instructing. | 1 / 3 |
Actionability | No executable code, no git commands, no concrete implementation steps. The 'How to Use' section just shows natural language prompts rather than actual commands or scripts. There's no code for parsing commits, no regex patterns for categorization, no concrete logic Claude can execute—just a description of what the skill should do and an example output. | 1 / 3 |
Workflow Clarity | No actual workflow steps for Claude to follow. The 'What This Skill Does' lists conceptual steps but provides no concrete sequence, no git commands (e.g., `git log --since=...`), no validation checkpoints, and no error handling. Claude has no clear procedure to execute. | 1 / 3 |
Progressive Disclosure | The content is organized into clear sections with headers, which provides some structure. However, there are no bundle files or external references, and the content that exists is mostly filler rather than substantive material that would benefit from being split across files. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
364c6b2
- Reviewed
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.