changelog-generator

Generates structured changelogs from git history and pull requests. Use when preparing release notes, summarizing changes between tags/branches, or maintaining a CHANGELOG.md file. Supports Conventional Commits parsing.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/changelog-generator/SKILL.md

Quality

Content

65%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 content is highly actionable with concrete commands, templates, and worked examples, and is well-sectioned internally. It loses points for redundancy across sections, lack of an output-validation feedback loop in a batch workflow, and absence of any progressive-disclosure file splitting despite its length.

Suggestions

Collapse the repeated ISO-8601 / deprecation / reverse-chronology rules into a single Constraints section and remove their restatements in Guiding Principles, Anti-Patterns, and Workflow to tighten conciseness.

Add an explicit output verification step to the workflow (e.g. re-read the rendered CHANGELOG.md, confirm every entry traces to a commit/PR, and confirm reference links resolve) with a fix-and-retry loop, lifting workflow clarity past the batch-operation cap.

Move the three full rendered examples and the detailed per-format templates into a references/ file (e.g. EXAMPLES.md) and link to it from SKILL.md so the main file stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with tables and concrete commands, but ISO 8601 dates, deprecation surfacing, and reverse-chronological ordering are each restated across Guiding Principles, Anti-Patterns, Workflow, and Constraints, and the Persona/Guiding Principles sections restate Keep-a-Changelog conventions Claude already knows. This is mostly efficient with some unnecessary explanation that could be tightened, matching anchor 3 rather than the leaner 4.	3 / 5
Actionability	It provides copy-paste-ready git and `gh` CLI commands, full output-format templates, a Conventional Commits mapping table, and three concrete rendered examples covering common cases. This matches the fully-executable anchor 5; it is not 4 because the examples are concrete and cover standard, breaking-change, and yanked cases.	5 / 5
Workflow Clarity	The five-stage workflow is clearly sequenced and includes an input checkpoint (warn and confirm when fewer than 3 commits exist), but this batch operation lacks an output verification or validate-fix-retry feedback loop. Per the rubric's destructive/batch cap, missing such validation caps workflow clarity at 3, so it cannot reach 4 despite the clear sequence.	3 / 5
Progressive Disclosure	The body is well-sectioned but is a ~320-line monolith with no bundle files and no one-level-deep references, and content such as the three full examples and format templates could live in separate reference files. This matches the some-structure anchor 3; it is not 4 because references are entirely absent rather than mostly clear, and not 2 because the internal sectioning is genuinely organized.	3 / 5
	Total	14 / 20 Passed

Description

87%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 strong: third-person voice, explicit what-and-when structure, and concrete trigger phrases that a user would naturally say. It is comprehensive on completeness and distinctiveness, with only minor gaps in action coverage and trigger synonyms.

Dimension	Reasoning	Score
Specificity	"Generates structured changelogs from git history and pull requests" and "Supports Conventional Commits parsing" name the domain plus several concrete actions, though a couple of sub-capabilities (e.g. multiple output formats) are absent. It lists several specific actions with minor coverage gaps, fitting the score-4 anchor rather than the comprehensive 5.	4 / 5
Completeness	It explicitly answers both what ("Generates structured changelogs from git history and pull requests") and when ("Use when preparing release notes, summarizing changes between tags/branches, or maintaining a CHANGELOG.md file") with concrete trigger phrases. This matches the score-5 anchor; it is not the weaker 4 because the when-clause is explicit and specific rather than implied.	5 / 5
Trigger Term Quality	Natural trigger phrases like "release notes", "summarizing changes between tags/branches", and "CHANGELOG.md file" give good keyword coverage a user would actually say, but common synonyms such as "version bump", "semantic versioning", or "release" are missing. This is good coverage with a few natural terms absent, matching anchor 4 rather than the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The changelog/release-notes niche with triggers like "CHANGELOG.md" and "Conventional Commits" is clearly distinct from other skills with minimal conflict risk. This matches the clear-niche anchor 5; it is not 4 because the triggers are specific enough to avoid overlap with general git or docs skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: canonical/copilot-collections
Path: skills/changelog-generator/SKILL.md
Commit: d41d8d9

Reviewed: 1 day 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.