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

81%

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

76%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 extremely lean pointer skill that correctly offloads detail to a single, clearly-signaled reference file. It is maximally concise and well-structured for progressive disclosure, but the body alone provides no workflow sequence or overview, capping workflow clarity.

Suggestions

Add a 2-3 line overview summarizing what the skill produces (e.g., the EPIC iteration model and cut-readiness checklist) so SKILL.md is a true overview rather than a bare redirect.

Inline the high-level workflow sequence (scope derivation -> per-arc mining -> per-claim V-B-A -> cross-family review -> cut-readiness) before pointing to the reference for detail, so the body conveys the multi-step shape.

Mention the key validation checkpoint (the §7 cut-readiness checklist) in the body so the destructive/batch-style discipline is visible without reading the reference.

Dimension	Reasoning	Score
Conciseness	The body is two lean sentences that assume Claude's competence and redirect to the detailed reference; every token earns its place with no padding or over-explanation.	5 / 5
Actionability	It gives one concrete executable instruction ("use the `view_file` tool to read ...references/release-notes-workflow.md") with a specific tool and exact path, but delegates all actual authoring guidance to the reference rather than covering common cases inline.	4 / 5
Workflow Clarity	The body states only a single gating action (read the reference before acting); the multi-step sequence and validation checkpoints this complex skill requires live entirely in the referenced file, so the body itself has no visible sequence or checkpoints.	3 / 5
Progressive Disclosure	A well-signaled one-level-deep reference (exact path, verified to exist) with no nesting, but the body is a pure redirect with no overview or summary content, keeping it just below the ideal.	4 / 5
	Total	16 / 20 Passed

Description

87%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 dense, specific description that answers both what and when with explicit trigger guidance and a clearly distinct niche. Its only weakness is heavy project-internal jargon (V-B-A, precedent-SET, orphan-guard interplay) that slightly impairs plain-language clarity.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("scope derivation", "heavy per-arc Memory-Core mining", "per-claim V-B-A", "publish.mjs flat-root staging lifecycle"), but the dense project-internal jargon keeps it just below comprehensive clarity.	4 / 5
Completeness	Clearly states what the skill does (authoring protocol with named sub-disciplines) AND provides an explicit "Triggers:" clause with concrete when-phrases, satisfying the anchor for both.	5 / 5
Trigger Term Quality	The explicit "Triggers: a release window opens, release notes are requested/authored/iterated, or cut-prep begins" gives good natural keyword coverage, though a few common phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	Highly specific niche (Neo.mjs release notes, publish.mjs staging lifecycle, named version precedents) with distinct triggers yields minimal overlap with other skills.	5 / 5
	Total	18 / 20 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: 210c03c

Reviewed: 3 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.