CtrlK
BlogDocsLog inGet started
Tessl Logo

prepare-release

Use when preparing or executing a release - verifies changelog content, updates version references, commits release prep, and, when the maintainer explicitly asks, pushes the release tag that triggers automation

67

Quality

81%

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

77%Weight 40%Scale 1-3

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

A highly actionable release runbook with strong sequencing and validation gates, but it is a long monolithic file that repeats guardrails and could split large policy blocks into referenced files. Conciseness and progressive disclosure are the weak spots.

Suggestions

Consolidate the keep-release-notes-under-[Unreleased] rule and other repeated guardrails into a single stated location to cut duplication and reduce token weight.

Move the v3 topology/Tailscale/Cloudflare alignment checks and the readiness-gate command block into a referenced file (e.g. references/v3-release-gates.md) and link to it, converting SKILL.md into a leaner overview.

Tighten Step 6's long prose paragraphs into terse bullet assertions so each token earns its place.

DimensionReasoningScore

Conciseness

Operational and free of generic concept explanations, but ~450 lines with duplicated guardrails (the keep-notes-under-Unreleased rule restated across sections) and dense policy prose (v3 Tailscale/Cloudflare/Cilium alignment) that could be tightened; lands at the 'could be tightened' anchor.

2 / 3

Actionability

Provides concrete, copy-paste-ready bash (git log, awk extraction, tag creation, gh run rerun), templates, and a checklist, matching the fully-executable anchor.

3 / 3

Workflow Clarity

Numbered Steps 1-7 plus Execute/Post-Release sections with a DOT graph, explicit validation checkpoints (clean master, tag-existence check, completed CI success, live-body inspection) and feedback loops (workflow failure -> rerun -> gh release create recovery), matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

No bundle files exist and all content is inline in a ~450-line SKILL.md; sections are well-organized but substantial content (v3 alignment prose, readiness gates, templates) that should be separate remains inline, matching the 'content that should be separate is inline' anchor.

2 / 3

Total

10

/

12

Passed

Description

85%Weight 40%Scale 1-3

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, specific description that names concrete actions and explicit triggers with a clear, distinct release-prep/authorization niche. Its only weakness is narrow trigger-term coverage leaning almost entirely on the word 'release'.

Suggestions

Broaden trigger terms to include natural variations a maintainer might say, e.g. 'cut a release', 'publish', 'ship', or 'tag a release', so it surfaces on phrasings beyond 'preparing or executing a release'.

DimensionReasoningScore

Specificity

Lists four concrete actions ('verifies changelog content', 'updates version references', 'commits release prep', 'pushes the release tag that triggers automation'), matching the multi-action anchor rather than the partial score-2 anchor.

3 / 3

Completeness

Explicitly answers both what (the four actions) and when ('Use when preparing or executing a release ... when the maintainer explicitly asks'), satisfying the explicit-trigger anchor for score 3.

3 / 3

Trigger Term Quality

Has natural triggers ('Use when preparing or executing a release', 'when the maintainer explicitly asks') but coverage is narrow around the single term 'release', missing common variations a user might say ('cut/publish/ship a release').

2 / 3

Distinctiveness Conflict Risk

The maintainer-explicit-authorization framing and tag/automation scope carve a clear niche unlikely to fire for generic commit or docs skills.

3 / 3

Total

11

/

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

referenced_paths_exist

Referenced path issues: 5 missing

Warning

Total

15

/

16

Passed

Repository
mysticaltech/terraform-hcloud-kube-hetzner
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.