generate-release-notes

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

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/generate-release-notes/SKILL.md

Quality

Content

62%

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 well-sequenced, actionable workflow with strong validation checkpoints and fallback handling, but it is a monolithic single file whose templates and collector prompts could be split into references, and placeholders reduce copy-paste readiness.

Suggestions

Move the external/internal release-note templates and per-tracker collector prompts into reference files (e.g. references/templates.md, references/collectors.md) and link to them from SKILL.md.

Provide one fully-worked concrete example (real repo/version) alongside the [CUSTOMIZE] placeholders to improve copy-paste actionability.

Consolidate the two audience templates into one with a clearly marked audience switch to reduce duplication.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient instructional content with no basic-concept over-explanation, but the two near-duplicate full markdown templates and verbose agent prompts could be tightened, matching the "mostly efficient but could be tightened" anchor.	2 / 3
Actionability	It provides concrete, executable commands (gh pr list, JQL, MCP calls), but pervasive [CUSTOMIZE: …] and [VERSION_TAG] placeholders make examples configuration-dependent rather than copy-paste ready, fitting the "concrete but incomplete" anchor.	2 / 3
Workflow Clarity	Phases 1–6 are clearly sequenced with an explicit Review Gate checkpoint and a hard "NEVER auto-publish" validation rule, plus fallback and error-handling tables, matching the anchor for clear sequence with explicit validation steps.	3 / 3
Progressive Disclosure	No bundle files exist and everything lives inline in one long file; sections are well organized, but the two templates and per-tracker agent prompts are content that could be split out, matching the "content that should be separate is inline" anchor.	2 / 3
	Total	9 / 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, naming concrete actions and data sources, but it lacks an explicit use-when trigger clause and misses common trigger variations like "changelog". Adding a trigger clause would lift completeness and trigger-term quality.

Suggestions

Append a trigger clause, e.g. "Use when the user asks for release notes, a changelog, or what shipped in a version/sprint/cycle."

Include common natural variations such as "changelog", "what shipped", and "version" to broaden trigger coverage.

Keep the existing third-person voice and concrete source list, which already read well.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions and sources — "Generate categorized release notes from any source (GitHub, Linear, Jira, or manual input) with optional publishing" — matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	It clearly answers what the skill does, but there is no "Use when…" clause or equivalent explicit trigger guidance, which the rubric guidelines say caps completeness at 2.	2 / 3
Trigger Term Quality	"release notes" is a natural term a user would say, but common variations like "changelog", "what shipped", or "version bump" are absent, so coverage of natural terms is partial rather than complete.	2 / 3
Distinctiveness Conflict Risk	The named-tracker sourcing plus "categorized release notes" framing carves out a clear niche 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
Path: .claude/skills/generate-release-notes/SKILL.md
Commit: dfbf9e9

Reviewed: 2 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.