changelog

Generate changelogs from git history and validate conventional commits. Usage: /changelog <generate|lint> [options]

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/changelog/SKILL.md

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly concise and actionable, with clean sectioning and well-signaled references. Its main weakness is the absence of validation/checkpoint steps for the batch commit-processing operations, which caps workflow clarity, and references that resolve to external repo paths rather than a verifiable local bundle.

Suggestions

Add validation/checkpoint guidance for the batch operations, e.g., verify the tag/ref range resolves before generating, and define what to do when lint finds non-conventional commits.

Include a short rendered example of generate output so the expected changelog format is unambiguous.

Make script references resolve to a local bundle (e.g., scripts/generate_changelog.py) or clarify the repo-relative path so progressive disclosure navigation is verifiable.

Dimension	Reasoning	Score
Conciseness	The ~30-line body is lean and assumes Claude's competence, explaining no basic concepts and keeping every token purposeful, matching the 5 anchor.	5 / 5
Actionability	Provides concrete example commands and exact script flag interfaces (--from-tag, --to-tag, --format markdown\|json, --strict) that are mostly executable, but lacks a rendered output example or a full copy-paste script invocation, keeping it just below 5.	4 / 5
Workflow Clarity	The two single-action subcommands are clearly sequenced, but both operate over ranges of git commits (batch operations) with no validation or checkpoint guidance, triggering the rubric's destructive/batch cap of 3.	3 / 5
Progressive Disclosure	Well-organized sections with one-level-deep, clearly signaled references (two script files with descriptions and a single SKILL.md pointer); minor gaps keep it below 5, namely the references point to external repo paths with no local scripts/ bundle to verify and a self-referential SKILL.md pointer.	4 / 5
	Total	16 / 20 Passed

Description

61%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise and names two concrete, distinct capabilities, but it omits an explicit 'Use when...' trigger clause, which caps completeness and weakens trigger guidance. Overall a solid, specific description that would benefit from explicit usage-trigger phrasing.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when generating release notes/changelogs from git history or validating conventional commit format').

Broaden trigger-term coverage with synonyms users say, such as 'release notes' and the '.md' output, to improve trigger_term_quality.

Optionally enumerate the generate vs lint capabilities more fully to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('Generate changelogs from git history', 'validate conventional commits') but is not comprehensive, matching the 3 anchor; it does not enumerate the full set of capabilities to reach 4.	3 / 5
Completeness	Has a clear 'what' but no 'Use when...' clause (only a 'Usage:' invocation hint), so per the rubric a missing explicit trigger guidance caps completeness at 3 rather than 4.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('changelogs', 'git history', 'conventional commits') that users would actually say, though synonyms like 'release notes' or file extensions are missing, placing it just above the 3 anchor.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (changelog generation plus conventional-commit linting) with distinct triggers and only minor overlap risk with closely related git-commit skills; it does not fully spell out a unique trigger niche to reach 5.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/changelog/SKILL.md
Commit: 19392f7

Reviewed: ~2 hours ago

Table of Contents

Discovery Implementation Validation

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.