release-notes

Authoritative protocol for authoring release notes as an EPIC with mining-driven iterations — scope derivation (the tracker lags shipped reality), heavy per-arc Memory-Core mining, per-claim V-B-A, the precedent-SET quality bar — majors AND minors, v13.0.0 + v12.1.0 + v11.22-24 (hero chapters, named case studies with real timelines, War Stories, honest bounds, never downplay a release), and the publish.mjs flat-root staging lifecycle. Triggers: a release window opens, release notes are requested/authored/iterated, or cut-prep begins (staging file, atomic-hash line, orphan-guard interplay).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%Weight 40%Scale 1-3

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

The body is a minimal, well-structured pointer that delegates all detail to a single verified reference file, which is exactly the progressive-disclosure pattern the rubric rewards. It is concise, actionable, and unambiguous for a simple delegating skill, with no excess explanation or nested references.

Dimension	Reasoning	Score
Conciseness	The body is a single lean directive — 'use the view_file tool to read and strictly adhere to .agents/skills/release-notes/references/release-notes-workflow.md' — that assumes Claude's competence with no padding, matching the lean, token-efficient score-3 anchor rather than the slightly padded score-2.	3 / 3
Actionability	It gives a concrete, executable instruction naming the exact tool (view_file) and the exact reference path to read before acting, which is fully actionable copy-paste-ready guidance rather than the vague or pseudocode anchors at lower scores.	3 / 3
Workflow Clarity	This is a simple single-action skill whose one step — read the workflow reference before writing, judging, or moving any notes — is unambiguous and gated before any risky work; per the rubric's simple-skills note, that merits a 3 without a multi-step sequence.	3 / 3
Progressive Disclosure	The body is a concise overview pointing to one real, one-level-deep reference (references/release-notes-workflow.md, verified present and 98 lines), clearly signaled and easy to navigate, matching the score-3 well-structured reference anchor rather than inline monoliths or nested references.	3 / 3
	Total	12 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 is a dense, highly specific third-person protocol statement that covers both capability and explicit triggers, giving it strong specificity, completeness, and distinctiveness. Its main weakness is trigger-term quality: genuine natural triggers are smothered by a heavy layer of project-internal jargon that a user would be unlikely to say verbatim.

Suggestions

Strip or parenthetically gloss internal jargon (e.g. 'EPIC', 'Memory-Core mining', 'V-B-A', 'precedent-SET') so the natural trigger phrasings ('release notes are requested', 'a release window opens', 'cut-prep begins') lead the description.

Add common user phrasings such as 'write release notes', 'draft a changelog', or 'prepare a release' to broaden natural keyword coverage.

Trim the version-specific detail ('v13.0.0 + v12.1.0 + v11.22-24') from the description; that historical context belongs in the reference, not the trigger surface.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions such as 'scope derivation', 'per-arc Memory-Core mining', 'per-claim V-B-A', and 'publish.mjs flat-root staging lifecycle', matching the anchor for multiple specific concrete actions rather than the score-2 partial coverage.	3 / 3
Completeness	It explicitly states both what the skill does ('Authoritative protocol for authoring release notes...') and when to use it via an explicit 'Triggers:' clause, matching the anchor that clearly answers both what AND when.	3 / 3
Trigger Term Quality	It includes some natural triggers ('release notes are requested/authored/iterated', 'a release window opens', 'cut-prep begins') but these are buried under heavy internal jargon like 'EPIC', 'Memory-Core mining', and 'precedent-SET', missing common user phrasings; not the broad, natural keyword coverage of the score-3 anchor.	2 / 3
Distinctiveness Conflict Risk	The skill occupies a clear niche — release-note authoring tied to a specific publish.mjs staging lifecycle — with distinct triggers unlikely to fire for unrelated skills, matching the score-3 distinct-niche anchor rather than the more generic score-2.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: neomjs/neo
Path: .agents/skills/release-notes/SKILL.md
Commit: c1ce853

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.