CtrlK
BlogDocsLog inGet started
Tessl Logo

write-changelog

Write a CHANGELOG.md entry for a new extension release. Use when: writing changelog, updating changelog, adding release notes, preparing a release, documenting milestone changes. Requires a milestone name and extension version number.

75

Quality

95%

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

100%

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

An exemplary procedural skill body: concise, fully actionable, with a clear sequenced workflow including an explicit validation step and clean section organization. No meaningful improvements are needed against this rubric.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what a changelog, milestone, or PR is — and every section (Inputs, Procedure, Format Rules, Validate) earns its place without padding.

3 / 3

Actionability

Provides executable GitHub search query strings, a concrete classification table with explicit criteria, and a copy-paste-ready markdown template with precise format rules (bullet styles, blank-line rules, linking policy).

3 / 3

Workflow Clarity

A clearly sequenced four-step workflow (Gather, Classify, Write, Validate) with an explicit validation step containing concrete checkpoints (positioning, link correctness, no duplicates); validation is present, so it is not capped at 2.

3 / 3

Progressive Disclosure

Self-contained single-task skill with no bundle files needed; content is well-organized into clearly signaled sections with no nested references and nothing that would benefit from being split out.

3 / 3

Total

12

/

12

Passed

Description

90%

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, well-scoped description that clearly states the task and provides explicit natural-language triggers plus required inputs. Its only weakness is specificity, as it names a single action rather than enumerating multiple concrete actions.

Suggestions

Expand the action list to name multiple concrete steps (e.g. 'Gather closed issues and merged PRs from a GitHub milestone, classify them, and write a formatted CHANGELOG.md entry') to reach the score-3 specificity anchor.

DimensionReasoningScore

Specificity

Names a concrete deliverable and domain ('Write a CHANGELOG.md entry for a new extension release') but lists a single action rather than multiple specific actions, matching the 'names domain and some actions, but not comprehensive' anchor.

2 / 3

Completeness

Clearly answers both what ('Write a CHANGELOG.md entry for a new extension release') and when via an explicit 'Use when:' trigger clause, plus required inputs; satisfies the score-3 anchor.

3 / 3

Trigger Term Quality

The 'Use when:' clause lists natural user phrases — 'writing changelog, updating changelog, adding release notes, preparing a release, documenting milestone changes' — giving good coverage of terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche — changelog generation for extension releases scoped to a GitHub milestone — with distinct triggers, making overlap with other skills unlikely.

3 / 3

Total

11

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 2 missing

Warning

Total

14

/

16

Passed

Repository
microsoft/vscode-pull-request-github
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.