CtrlK
BlogDocsLog inGet started
Tessl Logo

changelog-scan

Scan recent merges to main (and noteworthy direct commits) since a given window (last tag or date in state). Extract titles, labels, types, linked issues, and signals for breaking changes or security. Produces structured input for a release notes drafter. Use in changelog-drafter loops.

66

Quality

80%

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/.grok/skills/changelog-scan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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.

A tight, well-structured instruction-only skill with concrete output templates and explicit rules. Its gaps are the missing retrieval commands and the absence of an explicit validation checkpoint for what is inherently a batch scan.

Suggestions

Add the concrete retrieval command(s), e.g. `gh pr list --state merged --base main --search "merged:>{tag}"` or `git log --merges --since=<tag>`, so the scan step is executable rather than implied.

Insert an explicit validation checkpoint before emitting the summary, e.g. "Verify every listed item has a PR number or sha; reconcile Total items against the raw merge list before writing the Scan Summary."

Add a short feedback loop: "If Total items exceeds N, re-run with a narrower window per the 'split window' recommendation rather than emitting an oversized report."

DimensionReasoningScore

Conciseness

Lean and efficient across under 50 lines: no padding, no explanation of what PRs/git/labels are, and every section (inputs, output format, rules, signals, summary) earns its place; assumes Claude's competence throughout.

5 / 5

Actionability

Provides a copy-paste-ready output template with a worked example, explicit inclusion rules, and concrete signal keywords ("BREAKING", "CVE", "vuln", "deprecate"), but never gives the actual git/gh commands to retrieve the merge list, leaving the retrieval step as a hint rather than executable guidance.

4 / 5

Workflow Clarity

Section ordering implies a sequence (inputs → scan → apply rules → surface signals → summary) and the summary's "recommended next action" gives loop feedback, but this batch operation has no explicit validation checkpoint; per the batch-operation cap, workflow clarity cannot exceed 3 without a verify step.

3 / 5

Progressive Disclosure

A simple under-50-line single-purpose skill with no external references needed and clear section headers (Inputs, Output Format, Rules, Signals, Summary), meeting the bar for a well-organized short skill; no bundle files exist to verify.

5 / 5

Total

17

/

20

Passed

Description

80%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.

A specific, third-person description that clearly conveys the skill's purpose and scope with concrete actions. Its main weakness is a narrow, internally-oriented trigger clause that undersells the natural user situations in which the skill applies.

Suggestions

Rewrite the trigger as a user-facing phrase, e.g. "Use when drafting release notes, summarizing what changed since the last tag, or scanning recent merges for breaking changes."

Add common synonyms users actually say ("what's new", "since last release", "release notes") alongside "changelog" to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Scan recent merges to main", "Extract titles, labels, types, linked issues, and signals for breaking changes or security", "Produces structured input" — with comprehensive coverage of the scanning task; uses correct third-person voice.

5 / 5

Completeness

Explicitly states both what (scan/extract/produce structured input) and when ("Use in changelog-drafter loops"), but the when clause is narrow and internal-facing rather than concrete user trigger phrases, so it falls short of the level-5 anchor.

4 / 5

Trigger Term Quality

Includes natural terms ("changelog", "release notes", "breaking changes", "security") but the trigger "Use in changelog-drafter loops" references an internal mechanism rather than user-facing phrasing like "drafting release notes" or "what changed since the last release", leaving a few natural synonyms missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (changelog scanning for release notes) with distinct triggers, but it explicitly names closely related siblings ("release notes drafter", "changelog-drafter"), creating minor overlap risk with those skills.

4 / 5

Total

17

/

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.