CtrlK
BlogDocsLog inGet started
Tessl Logo

changelog

How to keep each app's user-facing changelog. Use when you ship a change a user would notice (a new feature, a visible improvement, a bug fix), when wiring the in-app "What's new" surface into a template, or when releasing pending changelog entries.

74

Quality

93%

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

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.

Tight, actionable guidance with concrete commands, file-format examples, and wiring code, plus a useful checklist. The main gap is the lack of an explicit validation/feedback loop around the destructive 'release' operation.

Suggestions

Add an explicit verify step before 'release' (e.g. run 'agent-native changelog list', confirm entries look right, then release) and a note on what to do if a pending entry is wrong before it is rolled in and the file deleted.

Clarify that 'release' is destructive (it deletes pending files) and whether/how it can be undone, so the risk is signalled at the point of action.

Tighten the opening paragraph's design-rationale ('mirrors changesets so it survives many agents working in parallel') to one line so the doc leads with the actionable model.

DimensionReasoningScore

Conciseness

Lean, sectioned guidance with executable commands and code; assumes Claude's competence and avoids explaining what a changelog is or how libraries work. The only slightly narrative part (the opening design-rationale paragraph) still earns its place by explaining the pending/release model.

3 / 3

Actionability

Provides copy-paste-ready commands ('agent-native changelog add "..." --type added', 'release', 'list'), a concrete entry-file frontmatter example, and complete TSX wiring snippets — fully executable rather than pseudocode.

3 / 3

Workflow Clarity

The add → preview(list) → release sequence and final checklist are present, but the destructive/batch 'release' (which 'deletes the pending files') has no explicit validate→fix→retry feedback loop, which the scoring notes say caps this dimension at 2 rather than 3.

2 / 3

Progressive Disclosure

A self-contained, well-organized doc with clear sections (When to add, How to add, Writing good entries, Releasing, Wiring, Checklist); no bundle files exist and no nested references, so well-organized inline sections are appropriate here.

3 / 3

Total

11

/

12

Passed

Description

100%

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 strong, third-person description that concisely states the skill's purpose and gives explicit, natural 'Use when' triggers covering the main scenarios. No vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists concrete actions — 'keep each app's user-facing changelog', 'wiring the in-app "What's new" surface into a template', 'releasing pending changelog entries' — rather than vague language, matching the multi-action anchor.

3 / 3

Completeness

Explicitly answers both what ('How to keep each app's user-facing changelog') and when via an explicit 'Use when you ship a change...' clause with multiple triggers, so it is not capped at 2.

3 / 3

Trigger Term Quality

Uses natural terms a user would say — 'changelog', 'ship a change', 'new feature', 'visible improvement', 'bug fix', 'What's new' — with good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The 'user-facing changelog' / 'in-app What's new surface' niche has distinct triggers unlikely to collide with other skills.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
BuilderIO/agent-native
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.