CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

release-notes

Draft release notes from merged pull requests since the last tag. Use when preparing a release.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 lean, instruction-only workflow with concrete grouping rules, filtering criteria, a defined output artifact, and explicit scope boundaries. The only notable gaps are the absence of specific git/gh commands and unhandled edge cases like a repository with no previous tag.

DimensionReasoningScore

Conciseness

Three short paragraphs with zero padding: no explanation of what tags, PRs, or conventional commits are — every sentence instructs. It assumes Claude's competence and every token earns its place.

5 / 5

Actionability

Concrete, specific guidance throughout: an explicit grouping scheme ('features, fixes, other'), output format ('one line per pull request in plain language, naming the user-visible change'), a filtering rule ('Skip pull requests whose title starts with chore: or ci:'), and a defined artifact ('RELEASE_NOTES.md at the repository root'). It falls short of 5 only because no executable commands are given for finding the tag or listing merged PRs.

4 / 5

Workflow Clarity

The sequence is clear and ordered (find tag → list merged PRs → group → write draft → show user) and the scope boundary ('Do not create the tag or publish the release') is explicit. Minor gaps remain: no guidance for the no-previous-tag edge case and no verification step, keeping it below the score-5 anchor.

4 / 5

Progressive Disclosure

The skill is well under 50 lines, single-purpose, with no need for external references, and no bundle files exist. Per the rubric's simple-skill guideline, the tight, well-organized inline content earns a 5.

5 / 5

Total

18

/

20

Passed

Description

70%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 clearly states what the skill does and includes an explicit 'Use when' trigger with concrete domain terminology. Its main gaps are that it lists only one primary action and omits common trigger synonyms such as 'changelog'.

Suggestions

Enumerate the concrete sub-actions (e.g., 'Find the last tag, list merged PRs, group them by conventional-commit type, and write a RELEASE_NOTES.md draft') to lift specificity beyond a single action.

Add natural trigger synonyms such as 'changelog', 'new version', or 'summarize changes since the last release' to broaden keyword coverage and make the 'Use when' clause more explicit.

DimensionReasoningScore

Specificity

The description names the domain ('release notes') and one concrete action with a precise scope ('from merged pull requests since the last tag'), but does not enumerate several specific actions the way the score-4 anchor does. It stays at the '1-2 concrete actions, not comprehensive' level.

3 / 5

Completeness

It answers both questions: what ('Draft release notes from merged pull requests since the last tag') and when ('Use when preparing a release'). The 'when' clause is present but could be more explicit with additional concrete trigger phrases, matching the score-4 anchor rather than 5.

4 / 5

Trigger Term Quality

Natural keywords include 'release notes', 'pull requests', 'tag', and 'release', plus an explicit trigger in 'Use when preparing a release' — good coverage for this narrow domain. It falls short of 5 because common synonyms like 'changelog' or 'new version' are missing, but exceeds the 'some relevant keywords' level of 3.

4 / 5

Distinctiveness Conflict Risk

'Draft release notes from merged pull requests since the last tag' carves out a clear niche with a distinct trigger, so it is unlikely to fire for unrelated skills. Minor overlap risk remains with closely related changelog/versioning skills, keeping it just below the 'minimal conflict risk' anchor.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

EveryInc/compound-engineering-plugin

Path

tests/skill-eval-cell/fixtures/review-roster-skill-prose/skills/release-notes/SKILL.md

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.