Tessl • The package manager for agent skills

Blog Docs Log inGet started

SkillPublic

changelog

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

Quality

73%

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

71%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 a tight, well-sectioned overview with executable example commands and clearly flagged script usage. Its weaknesses are structural: all referenced file paths fail to resolve against the actual bundle, and the lint workflow lacks a fix-and-retry feedback loop.

Suggestions

Fix the referenced paths so they resolve within the skill bundle (e.g. scripts/generate_changelog.py), and remove the self-referential "Skill Reference" line, since it points back at this SKILL.md.

Add a short feedback loop for lint, e.g. "If lint reports violations, fix the commit messages and re-run /changelog lint", plus defaults when no --from-ref is given.

State briefly what the linter checks (conventional commit type(scope): subject) so Claude can act on failures without reading the script.

Dimension	Reasoning	Score
Conciseness	Sections are lean with no concept over-explanation — usage, examples, and a script listing earn their tokens. It is not a 5 because the self-referential "Skill Reference → engineering/skills/changelog-generator/SKILL.md" line adds no value and could be trimmed.	4 / 5
Actionability	Concrete copy-paste commands ("/changelog generate --from-tag v2.0.0") and script invocations with enumerated flags cover the common cases. Not a 5 because the script paths do not resolve to actual bundle files and the conventional-commit rules the linter enforces are never stated.	4 / 5
Workflow Clarity	Each subcommand is a single unambiguous action with concrete flags ("--from-tag", "--to-ref"), so the sequence is clear. Minor gaps keep it below 5: no stated defaults when flags are omitted and no guidance on what to do when lint reports failures.	4 / 5
Progressive Disclosure	Sections are well organized (Usage, Examples, Scripts), but scored against the actual bundle structure — no references/, scripts/, or assets/ exist — every referenced path, including the Skill Reference pointing at the skill's own SKILL.md, is dangling, so navigation fails.	3 / 5
	Total	15 / 20 Passed

Description

65%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, third-person, and names a distinct niche with two concrete actions and good trigger terms. Its main weakness is the missing 'Use when...' clause, which caps completeness, and only partial coverage of what the skill covers (no mention of output formats or commit-message rules).

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for a changelog, release notes, or wants commit messages checked against conventional commit format."

Broaden trigger terms with natural synonyms like "release notes" and "commit message format" so users phrasing the need differently still match.

Mention what the output looks like (e.g. Keep a Changelog format, text or JSON) to lift specificity beyond two bare actions.

Dimension	Reasoning	Score
Specificity	"Generate changelogs from git history" and "validate conventional commits" name the domain plus exactly two concrete actions, matching the 1-2 concrete actions anchor. It is not a 4 because no further specifics (output format, commit-format rules) are listed, so coverage is not 'several specific actions'.	3 / 5
Completeness	The 'what' is clearly stated ("Generate changelogs from git history and validate conventional commits") but there is no 'Use when...' clause; the "Usage: /changelog <generate\|lint> [options]" line is invocation syntax, not trigger guidance, so completeness is capped at 3.	3 / 5
Trigger Term Quality	"changelogs", "git history", and "conventional commits" are natural phrases users would say when needing this skill. Not a 5 because common synonyms and variations like "release notes" or "commit messages" are missing.	4 / 5
Distinctiveness Conflict Risk	"changelogs" and "conventional commits" define a clear niche with distinct triggers and minimal conflict risk. Validation of commit format is cleanly separable from a commit-message-writing skill, so it fits the anchor better than the 'minor overlap risk' anchor at 4.	5 / 5
	Total	15 / 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
Revision: 19392f7

Reviewed: 14 hours ago

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.

changelog

Table of Contents

Is this your skill?