CtrlK
BlogDocsLog inGet started
Tessl Logo

draft-release-notes

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

48

Quality

52%

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

51%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 commendably lean but leans too far: it delegates the actual structure and rules to an external Grok skill that is not bundled, so Claude lacks the concrete template and categorization scheme needed to execute. Workflow steps are only loosely implied and lack validation checkpoints.

Suggestions

Inline the concrete structure/rules (category headings, per-entry format, breaking/security flagging format) instead of deferring to the unbundled 'Grok draft-release-notes skill', or bundle that reference as a file under references/ and link to it explicitly.

Lay out the workflow as an explicit numbered sequence with a verification checkpoint (e.g., '1. Categorize entries; 2. Flag breaking + security at top; 3. Verify every changelog entry is placed; 4. Append review note for human').

Add a minimal output template for RELEASE_NOTES_DRAFT.md so the guidance is copy-paste ready rather than abstract.

DimensionReasoningScore

Conciseness

The body is lean with no padding and no over-explanation of concepts Claude already knows; every line is a directive. This matches 'Lean and efficient; assumes Claude's competence; every token earns its place'. Not a 4 because there are no noticeable instances of over-explanation to trim.

5 / 5

Actionability

It gives high-level directives ('Output a clean RELEASE_NOTES_DRAFT.md', 'flag breaking + security at top', 'End with review note') but defers the actual structure/rules to an external 'Grok draft-release-notes skill' that is not bundled, leaving the specific steps to execute undefined. This fits 'Minimal concrete guidance; high-level hints but missing the specific steps'. Not a 3 because no concrete template or partial executable detail is provided, not a 1 because some concrete directives (output filename, top-flagging, closing note) are present.

2 / 5

Workflow Clarity

A rough sequence is implied (follow structure -> output draft -> flag at top -> end with review note) but steps are poorly defined and validation checkpoints are absent. This fits 'Rough sequence present but many gaps; steps poorly defined; validation absent'. Not a 3 because the steps are not clearly listed as a sequence, not a 1 because some ordering is implied.

2 / 5

Progressive Disclosure

The body is short and has a title plus directive paragraphs, but its key reference ('the Grok draft-release-notes skill') points to an external, non-bundled resource rather than a file in references/scripts/assets (none exist). This fits 'Some structure but could be better organized; references present but not clearly signaled'. Not a 4 because the one reference is external and not navigable within the bundle, not a 2 because the content is short and not a monolithic wall of text.

3 / 5

Total

12

/

20

Passed

Description

53%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 states a clear purpose and is concise and in the correct voice, but it omits any 'Use when' trigger guidance and relies on a narrow tool name rather than broader natural trigger terms. It is competent but lacks the trigger completeness that would make it reliably discoverable.

Suggestions

Add an explicit 'Use when ...' clause naming natural triggers (e.g., 'Use when drafting release notes from changelog-scan output, or when the user asks to summarize changelogs into version notes').

Broaden trigger terms beyond the tool name 'changelog-scan' to include synonyms users actually say: 'release notes', 'changelog', 'what's new', 'version notes'.

Spell out 1-2 more concrete sub-actions (e.g., 'categorize entries, flag breaking and security items, propose a draft') to lift specificity.

DimensionReasoningScore

Specificity

Names the domain ('changelog-scan output', 'release notes') and one concrete action ('Turn ... into polished, categorized release notes draft'), but does not enumerate multiple specific actions. This matches the anchor for 1-2 concrete actions; it is not a 4 because no list of several specific actions is given, and not a 2 because the domain and a concrete action are clearly stated.

3 / 5

Completeness

It clearly states what ('Turn changelog-scan output into polished, categorized release notes draft') but provides no 'Use when...' clause or equivalent trigger guidance, which per the guidelines caps completeness at 3. Not a 4 because 'when' is entirely missing rather than weakly present, not a 2 because the 'what' is clear rather than vague.

3 / 5

Trigger Term Quality

'release notes' is a natural term users would say, but 'changelog-scan' is a specific tool/output name (technical jargon) and common synonyms like 'changelog', 'what's new', or 'version notes' are absent. This fits 'some relevant keywords but missing common variations or synonyms'; not a 4 because keyword coverage is thin, not a 2 because a genuinely natural term is present.

3 / 5

Distinctiveness Conflict Risk

The tie to 'changelog-scan output' gives it a fairly specific niche with minor overlap risk against generic release-note skills. Not a 5 because there is no explicit distinct trigger phrase, not a 3 because the upstream-pipeline framing makes it more specific than 'works with document files'.

4 / 5

Total

13

/

20

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.