Name: changelog-generator
Rating: 71.2 (1 reviews)
Author: alirezarezvani

changelog-generator

Produce consistent, auditable release notes from Conventional Commits. Separates commit parsing, semantic-bump logic, and changelog rendering for automated releases with editorial control. Use when cutting a release, generating CHANGELOG.md from git history, computing the next semantic version from commits, automating release notes in CI, or planning a hotfix/rollback. Examples: 'generate the changelog for v1.4.0', 'what version bump do these commits require', 'we need an emergency hotfix process'.

Quality

88%

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

The canonical home for this skill is changelog-generator in alirezarezvani/claude-skills

Quality

Content

82%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.

A highly actionable, well-structured skill body built around concrete script commands and clear workflows, with validation and error-handling guidance distributed across sections. The main weaknesses are some generic advisory padding and inline workflow checkpoints that could be made more explicit.

Suggestions

Trim the Best Practices and Common Pitfalls sections to skill-specific guidance only; drop generic advice like 'keep commits small' that Claude already knows, to improve conciseness.

Add an inline validate-then-proceed checkpoint to the CHANGELOG.md write workflow (e.g. run commit_linter.py --strict → review draft → only then --write CHANGELOG.md) so the feedback loop is visible in the workflow rather than only in the distributed Failure Handling / Output Quality Checks sections.

Verify the referenced bundle files (references/*.md, scripts/*.py, assets/sample_git_log.txt) are shipped with the skill, and consider moving the full Hotfix Severity and Rollback Triggers tables into references/hotfix-procedures.md to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	Largely efficient with concrete commands, script interfaces, and compact tables, but several advisory sections (Best Practices, Common Pitfalls) restate guidance Claude already knows and could be trimmed; not pervasive enough to drop to 3.	4 / 5
Actionability	Fully executable, copy-paste-ready commands across all five workflows (e.g. 'python3 scripts/generate_changelog.py --from-tag v1.3.0 --to-tag v1.4.0 --next-version v1.4.0 --format markdown') with flags and JSON outputs documented, covering the common cases.	5 / 5
Workflow Clarity	Clear numbered sequences and a governance flow with an approval checkpoint, plus linter validation, Output Quality Checks, and Failure Handling for error recovery; however, the inline changelog-write workflow lacks an explicit validate-then-proceed feedback loop, leaving minor validation gaps rather than the full inline checkpoint pattern of a 5.	4 / 5
Progressive Disclosure	Good structure with a clear overview and well-signaled one-level-deep references (references/hotfix-procedures.md, ci-integration.md, etc.), but the referenced bundle files are not present in the skill directory to verify, and the inlined hotfix/rollback tables are fairly long, leaving minor organization gaps versus a clean 5.	4 / 5
	Total	17 / 20 Passed

Description

95%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.

A strong, well-structured description that clearly states capabilities, provides rich natural-language triggers with example user quotes, and occupies a distinct niche. The only minor weakness is that the middle sentence describes architecture rather than additional concrete user actions.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — 'Produce consistent, auditable release notes', 'Separates commit parsing, semantic-bump logic, and changelog rendering' — but the architectural framing ('Separates...') is less a user-facing action than a design note, leaving minor coverage gaps versus a fully comprehensive action list.	4 / 5
Completeness	Explicitly answers both what ('Produce consistent, auditable release notes from Conventional Commits') and when ('Use when cutting a release, generating CHANGELOG.md...') with concrete trigger phrases, matching the anchor for clearly answering both what AND when.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage with synonyms (release notes/changelog, version bump/semantic version, hotfix/rollback), a file reference (CHANGELOG.md), and explicit user-quote examples like 'what version bump do these commits require' that users would naturally say.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche around Conventional Commits, semantic-version bumps, and Keep a Changelog rendering with distinct triggers, making overlap with generic release or git skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 7 missing	Warning
referenced_paths_exist	Referenced path issues: 23 missing	Warning

	Total	14 / 16 Passed

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

Reviewed: ~3 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.