prepare-release

Use when preparing or executing a release - runs the authoritative local gates, verifies release content, and, when explicitly authorized, pushes the release tag

Quality

80%

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

77%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.

A highly actionable, well-sequenced release runbook with strong validation and feedback loops for an irreversible operation. Its main weaknesses are redundancy across sections and a monolithic structure with no reference files for a skill of this size.

Suggestions

De-duplicate the v3 verification and contributor-credit rules so each appears in one authoritative place, with the checklist referencing rather than restating them, to cut length and drift risk.

Extract the large v3 topology-alignment prose and the release-notes/changelog templates into reference files under ./references/ and link to them from SKILL.md, turning the body into a lean overview.

Trim or move the 30-item Quick Checklist into a separate checklist reference so the core workflow stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is mostly earned project-specific knowledge rather than concepts Claude already knows, but it carries real redundancy: v3 verification rules are restated across the automation section, Step 6 prose, and the 30-item checklist, and contributor-credit rules recur in both their dedicated section and the checklist.	3 / 5
Actionability	Every release choreography step ships copy-paste-ready bash with named scripts and concrete commands (Steps 1, 3, 6, 7, Execute Release, Post-Release), plus filled-in changelog and release-notes templates covering the common cases.	5 / 5
Workflow Clarity	An irreversible tag-push operation is sequenced via a graphviz flow and guarded with explicit validation checkpoints (tag-existence refusal, live control re-proof, atomic push lease), feedback loops for publication failure, and a checklist.	5 / 5
Progressive Disclosure	Section structure is reasonable (Overview, Workflow, Steps 1-7, Execute, Post-Release, Checklist), but this ~500-line skill is monolithic: no reference bundle files exist, and content that clearly belongs in separate files (detailed v3 topology alignment rules, contributor-credit policy, full templates) is inlined.	3 / 5
	Total	16 / 20 Passed

Description

83%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 strong, third-person description that pairs concrete release actions with an explicit 'Use when' trigger, cleanly answering both what and when. Only minor gaps remain in trigger-term variation and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('runs the authoritative local gates', 'verifies release content', 'pushes the release tag'), but the action set is narrow to release prep with minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (runs gates, verifies content, pushes tag) and 'when' ('Use when preparing or executing a release') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Opens with a natural 'Use when preparing or executing a release' trigger and the keyword 'release', though common variations like 'cut a release' or 'ship a release' are absent.	4 / 5
Distinctiveness Conflict Risk	A clear release-prep niche with distinct triggers, carrying only minor overlap risk with general git/CI workflow skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (503 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 14 missing, 5 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: mysticaltech/terraform-hcloud-kube-hetzner
Path: .claude/skills/prepare-release/SKILL.md
Commit: bb1622c

Reviewed: 1 day 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.