CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

release-notes-one-pager

Release notes one-page HTML with highlights, Added, Fixed, Breaking changes, Known issues, and Upgrade note. Writes explicit "None" style sections whenever the user does not provide details.

68

Quality

85%

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

90%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.

An exemplary instruction-only skill body: token-lean, fully concrete steps with exact paths, ids, and fallback strings, plus a real P0 checklist gate. The two real gaps are the missing example.html promised in the resource map and an implicit (rather than explicit) fix-and-revalidate loop at the self-check step.

Suggestions

Resolve the dangling reference: either add example.html as the advertised quality bar/style reference or remove it from the resource map and rely on assets/template.html alone.

Make Step 4's failure path explicit: 'If any P0 fails, fix the HTML and re-run the checklist before emitting' — a concrete validate→fix→retry loop.

Name the six :root design variables in Step 0 (or point to where they are enumerated) so the DESIGN.md mapping step is actionable without guessing.

DimensionReasoningScore

Conciseness

The ~80-line body is lean and instructional throughout — no concept explanations, no padding — with every line either a step, a constraint, or an exact value ('Copy assets/template.html to project index.html', 'use `—` and label the field rather than guessing'). It matches anchor 5 ('lean and efficient; assumes Claude's competence; every token earns its place'); the CTA guidance is the only place with slight repetition between Step 1 and Step 2, not enough to drop a level.

5 / 5

Actionability

Guidance is fully executable: exact file paths ('assets/template.html', 'references/layouts.md'), required section ids ('id="added"', 'id="breaking-changes"'), verbatim fallback strings ('No summary provided.', 'None reported'), named layouts per section, and a copy-paste artifact wrapper with exact syntax and emission rule ('One sentence before the artifact. Nothing after </artifact>.'). This matches anchor 5 — concrete, copy-paste-ready instructions covering the common cases.

5 / 5

Workflow Clarity

Steps 0–5 are clearly sequenced (read inputs → copy seed → build sections → honesty rules → self-check → emit) with an explicit validation gate ('Run references/checklist.md. Every P0 must pass.') before emitting, matching anchor 4 ('clear sequence with most checkpoints present'). It is not 5 because the error-recovery loop is implicit — the body never says what to do when a P0 fails (fix the HTML and re-run the checklist) — and it is well above 3 because the checkpoint is explicit and gate-like rather than missing.

4 / 5

Progressive Disclosure

The body is a genuine overview: a resource map, a five-step workflow, and one-level-deep references (checklist.md, layouts.md) whose real files exist and deliver what is promised (layouts.md contains Layouts 1–8 including the release-note variant; checklist.md contains P0/P1/P2 gates). It matches anchor 4 rather than 5 because the resource map advertises 'example.html ← quality bar and style reference' which is absent from the bundle — a dangling navigation pointer — and the six ':root' variables referenced in Step 0 are not named in the body.

4 / 5

Total

18

/

20

Passed

Description

75%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 clear, concrete, appropriately concise description that names the deliverable and its section structure verbatim, including the honest 'None' fallback behavior. Its main weakness is that the 'when to use' guidance lives in a separate frontmatter triggers list rather than an explicit 'Use when...' sentence in the description itself, and a couple of triggers are broad enough to invite overlap.

Suggestions

Fold trigger phrasing into the description with a self-contained clause such as 'Use when the user asks for release notes, a changelog, or a what's-new page for a release' so the 'when' is explicit in the description field.

Add an explicit action verb ('Generates a single-page HTML release-notes document...') so the capability reads as an action rather than a noun phrase.

Narrow the broadest triggers ('version update', 'changelog') or qualify them ('product release changelog') to reduce conflict risk with general documentation or dependency-update skills.

DimensionReasoningScore

Specificity

The description names the domain ('Release notes one-page HTML') and enumerates the concrete deliverable parts — 'highlights, Added, Fixed, Breaking changes, Known issues, and Upgrade note' — plus a specific behavior ('Writes explicit "None" style sections whenever the user does not provide details'), matching the anchor 'lists several specific actions; minor gaps in coverage'. It is not 5 because it never states an action verb like 'Generates' or 'Produces' — the capability is implied by a noun-phrase list — and it omits inputs (user-provided details, version, date) from the capability statement.

4 / 5

Completeness

The 'what' is clearly answered (a single-page HTML release-notes document with named sections and explicit 'None' fallbacks), and 'when' guidance exists — but only in the separate frontmatter 'triggers' list, not as an explicit 'Use when...' clause inside the description itself, matching anchor 4 ('when' could be more explicit or specific). It is not 5 because anchor 5 requires the concrete trigger phrases to appear explicitly in the description; it is not capped at 3 because the triggers field is equivalent explicit trigger guidance.

4 / 5

Trigger Term Quality

The description text itself contains 'Release notes' plus natural section terms ('Breaking changes', 'Known issues'), and the same frontmatter's triggers list covers 'release notes', 'changelog', 'change log', 'what's new', 'version update', 'release summary' — good natural coverage matching anchor 4. It is not 5 because a few natural phrases a user might say ('release announcement', 'ship notes', 'release highlights') are absent, and no file-extension-style variations exist for this domain; not 3 because synonym coverage goes well beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — a release-notes one-pager with a fixed six-section structure — and most triggers ('release notes', 'what's new', 'release summary') are unlikely to fire for the wrong skill, matching anchor 4 ('mostly distinct; minor overlap risk'). It is not 5 because 'changelog' and 'version update' are broad enough to overlap with general documentation/changelog-generation or dependency-update skills.

4 / 5

Total

16

/

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.

Validation — 15 / 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

nexu-io/open-design

Path

skills/release-notes-one-pager/SKILL.md

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.