CtrlK
BlogDocsLog inGet started
Tessl Logo

release-notes

Generates polished GitHub release notes for a ToolHive release by analyzing every merged PR, cross-referencing linked issues, dispatching expert agents to assess breaking changes, and producing a formatted release body. Use when the user provides a GitHub release URL, tag name, or says "release notes".

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

A well-structured, highly actionable multi-phase workflow with strong sequencing and an approval gate before publishing. Its sole weakness is progressive disclosure: the single referenced bundle file (TEMPLATE.md) is missing, leaving a dangling reference.

Suggestions

Add the referenced TEMPLATE.md to a references/ (or repo root) directory so the Phase 4 link resolves; otherwise inline the template structure directly in SKILL.md.

Move the per-area expert-agent prompts and the category classification table into a separate reference file, keeping SKILL.md as a concise overview that links one level deep.

Verify all referenced paths exist before relying on them (e.g. confirm TEMPLATE.md is present) to avoid a broken navigation hop.

DimensionReasoningScore

Conciseness

The body is dense and actionable — gh/jq commands, classification tables, and decision rules — with no padding explaining concepts Claude already knows; despite its length, nearly every token earns its place for a genuinely complex multi-phase task.

3 / 3

Actionability

Provides fully executable commands (e.g. 'gh release view', 'gh api .../compare', 'gh pr diff <number> --stat'), concrete jq filters, a named expert-agent dispatch table, and copy-paste-ready approval prompts.

3 / 3

Workflow Clarity

Five phases are explicitly sequenced with validation checkpoints — agent verdicts override initial classification, the draft is presented with uncertainties highlighted, and publishing is gated on explicit user approval before the destructive outward-facing 'gh release edit' step.

3 / 3

Progressive Disclosure

The only external reference, [TEMPLATE.md](TEMPLATE.md) in Phase 4, points to a file that does not exist in references/scripts/assets or the repo root, and the rest of the detail (template, agent prompts) is inline rather than split out.

2 / 3

Total

11

/

12

Passed

Description

100%

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 strong, third-person description that pairs concrete capabilities with an explicit 'Use when' trigger and ToolHive-scoped distinctiveness. It satisfies every anchor at the top of the scale.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'analyzing every merged PR', 'cross-referencing linked issues', 'dispatching expert agents to assess breaking changes', 'producing a formatted release body' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly answers both 'what' (generate release notes via PR/issue analysis and expert agents) and 'when' with an explicit 'Use when the user provides a GitHub release URL, tag name, or says "release notes"' trigger clause.

3 / 3

Trigger Term Quality

Natural terms a user would say are well covered: 'GitHub release notes', 'GitHub release URL', 'tag name', and the literal phrase "release notes".

3 / 3

Distinctiveness Conflict Risk

Scoped to 'a ToolHive release' with distinct release-notes triggers, giving it a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
stacklok/toolhive
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.