generate-release-notes

Generate categorized release notes from any source (GitHub, Linear, Jira, or manual input) with optional publishing

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

92%

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

The content is highly actionable, concise, and sequenced with strong validation checkpoints around the destructive publish step. Its main weakness is monolithic structure — both full audience templates and all platform instructions sit inline with no split-out reference files or signaled navigation.

Suggestions

Split the two full release-note templates (external and internal) into separate reference files (e.g. templates/external-release-notes.md) and link to them from the main body to apply progressive disclosure.

Move the per-platform publish instructions (GitHub/Confluence/Notion/HackMD) into a references file and keep a one-line pointer plus the approval gate inline.

Confirm whether the inline [CUSTOMIZE: ...] placeholders are meant to be filled by the user; if so, note where that customization lives so the skill stays lean.

Dimension	Reasoning	Score
Conciseness	The body is lean instruction with concrete commands (gh pr list, JQL, gh release create) and templates, and avoids explaining concepts Claude already knows; every section carries actionable content rather than padding.	3 / 3
Actionability	Provides fully executable commands and copy-paste-ready templates (GitHub gh CLI, JQL queries, Linear/Jira/Notion tool calls, release-note markdown skeletons) rather than vague direction.	3 / 3
Workflow Clarity	A clear six-phase sequence with explicit checkpoints — Pre-Flight questions, Phase 4 Review Gate, "NEVER auto-publish. Always wait for explicit user approval", plus a Fallback Behavior table and Error Handling section — gives strong feedback loops for the risky publish step.	3 / 3
Progressive Disclosure	No bundle files (references/scripts/assets) exist and the entire ~340-line skill is a single monolithic file with full audience templates inline; the structure is sectioned, but large template content that could live in separate reference files is kept inline and no one-level-deep references are signaled.	2 / 3
	Total	11 / 12 Passed

Description

67%

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 specific and distinctive about what it does and which sources it supports, but it lacks an explicit Use-when trigger clause and common natural trigger terms like "changelog" or "what shipped".

Suggestions

Append a Use-when clause naming natural triggers, e.g. "Use when the user asks for release notes, a changelog, or 'what shipped' for a version, sprint, or cycle."

Add common trigger variations ("changelog", "what shipped", "ship log") so the skill surfaces for how users actually phrase the request.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and named sources — "Generate categorized release notes from any source (GitHub, Linear, Jira, or manual input) with optional publishing" — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does but provides no explicit "when to use it" trigger; per the judging guidelines, a missing Use-when clause caps completeness at 2.	2 / 3
Trigger Term Quality	Includes "release notes" and "publishing" but omits common natural variations users say ("changelog", "what shipped", "release") and lacks a Use-when clause, so it has some relevant keywords but is missing common variations.	2 / 3
Distinctiveness Conflict Risk	The release-notes-from-named-trackers niche with optional publishing is a clear, distinct purpose unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: huytieu/COG-second-brain
Commit: 5e9851c

Reviewed: 14 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.