CtrlK
BlogDocsLog inGet started
Tessl Logo

draft-release-notes

Turn changelog-scan output into polished, categorized release notes draft. Propose only.

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./starters/changelog-drafter/.claude/skills/draft-release-notes/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

The content is concise, actionable, and well-organized with a concrete output template and clear escalation rules; its only gap is the absence of an explicit validation feedback loop for the batch drafting step.

Suggestions

Add an explicit verify checkpoint before finalizing — e.g., 'Confirm every draft line maps to a scanned input item; remove or flag anything not in the scan before saving.'

Make the output sequence explicit as numbered steps (consume scan → draft sections in priority order → verify against scan → write file → update state) to surface the validation loop.

Consider moving the full section template into a referenced file only if the skill grows; at current size inline is appropriate.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — short Inputs, a concrete output template, tight Rules, and escalation criteria with no padding or explanation of concepts Claude already knows.

3 / 3

Actionability

Provides a copy-paste-ready output template with real section names, a thanks line, and a compare-URL format, plus specific actionable rules like 'One line per item with link to PR' and 'include a one-sentence Upgrade note'.

3 / 3

Workflow Clarity

Steps and escalation checkpoints are present and sequenced, but drafting from a list is a batch operation with no explicit verify-then-proceed feedback loop on the draft, which per the rubric caps workflow clarity at 2.

2 / 3

Progressive Disclosure

Self-contained with no bundle files and well-organized sections (Inputs, Output, Rules, Escalation), which per the simple-skill note earns a 3 for a sub-50-line single-purpose skill.

3 / 3

Total

11

/

12

Passed

Description

67%

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 specific and well-scoped with concrete actions and a clear niche, but it lacks an explicit 'Use when...' trigger and natural keyword coverage, which caps completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' trigger clause naming what the user would ask for (e.g., 'Use when drafting release notes from a changelog or preparing a version bump summary').

Include more natural trigger terms users actually say — 'changelog', 'what changed', 'version', 'release summary' — alongside 'release notes draft'.

Keep the third-person voice but surface the trigger earlier so Claude can match it on invocation.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Takes a structured list of changes', 'produces a clean, categorized, user-facing release notes draft', and 'Never publishes — only proposes a draft file or section' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Clearly answers 'what' (produce a categorized draft, never publish) but 'when' is only implied with no 'Use when...' clause, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Has relevant natural terms like 'release notes' and 'draft' but misses common variations users would say (changelog, what changed, version bump, publish) and lacks explicit trigger phrasing.

2 / 3

Distinctiveness Conflict Risk

Has a clear niche tied to changelog-scan output, and the 'Never publishes — only proposes' boundary distinguishes it from a publishing skill, making conflicts unlikely.

3 / 3

Total

10

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
cobusgreyling/loop-engineering
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.