ship
Release engineering. Diagnose and fix CI/CD failures, get to green, cut releases, manage versioning and changelog notes. Pragmatic about getting changes safely into production — not perfect, shipped.
60
72%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./deliver/skills/ship/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with specific, concrete actions and excellent natural trigger terms that developers would actually use. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill over others. The personality/philosophy note ('not perfect, shipped') adds flavor but doesn't aid skill selection.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user mentions CI/CD pipelines, build failures, release cutting, version bumps, changelogs, or getting changes into production.'
Consider removing or shortening the editorial comment ('Pragmatic about getting changes safely into production — not perfect, shipped') and replacing it with more trigger terms or explicit selection guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Diagnose and fix CI/CD failures', 'get to green', 'cut releases', 'manage versioning and changelog notes'. These are distinct, actionable capabilities. | 3 / 3 |
Completeness | The 'what' is well-covered with specific actions, but there is no explicit 'Use when...' clause or equivalent trigger guidance. The description implies when to use it but never states it explicitly, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'CI/CD failures', 'get to green', 'cut releases', 'versioning', 'changelog', 'release engineering', 'production'. These cover common terms developers use when needing release help. | 3 / 3 |
Distinctiveness Conflict Risk | The focus on release engineering, CI/CD failures, cutting releases, versioning, and changelogs creates a clear niche that is unlikely to conflict with general coding, testing, or deployment skills. The combination of these terms is quite distinctive. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured instructional skill with strong workflow clarity and good categorical thinking for CI failure diagnosis. Its main weaknesses are the lack of concrete executable examples (no actual commands, no sample release notes, no example log reading) and moderate verbosity in sections that restate or over-explain concepts. The skill reads more like a philosophy document for release engineering than a concrete how-to guide.
Suggestions
Add concrete executable examples: a sample `git tag` command, an example version bump commit, a short example of well-written release notes vs. bad ones, and a sample CI log snippet showing how to trace to root cause.
Trim the 'Failure Modes' section — it largely restates guidance already given in the main workflow sections. Consider condensing it to a brief checklist or removing it entirely.
Add a concrete example of reading a CI log: show a snippet of a failing GitHub Actions log and annotate which line is the 'first real error' vs. cascade errors.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is well-written and mostly efficient, but includes some sections that over-explain concepts Claude already understands (e.g., the detailed explanation of failure categories, the 'What Ship Does NOT Do' section, and the 'Failure Modes' section which restates guidance already given). The 'Your Stance' section is somewhat motivational rather than instructional. Could be tightened by ~30%. | 2 / 3 |
Actionability | The skill provides clear categorical guidance and decision frameworks (diagnose → fix → release), but lacks concrete executable commands or code examples. Version bumping says 'follow the project's versioning scheme' without showing a single example command. Release tagging says 'show the tag command' but doesn't provide one. No example CI log reading, no example release notes, no example git commands for cutting a release. | 2 / 3 |
Workflow Clarity | The three-move workflow (Diagnose → Fix → Release) is clearly sequenced with explicit validation checkpoints. The fix section includes category-specific actions with verification steps ('verify CI is genuinely green — not just the failing job passed once. Run it twice if the test was flaky'). The release workflow has clear steps: confirm scope, bump version, draft notes, tag and publish. Feedback loops are present (retry → escalate, skip → issue link). | 3 / 3 |
Progressive Disclosure | References to foundation skill, model.md, guidelines.md, and the release-engineer agent are clearly signaled and one level deep. However, the SKILL.md itself is quite long with sections like 'Failure Modes' and 'Transitions' that could be in separate files. No bundle files are provided to support the referenced paths, though the references themselves are well-structured. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- audenaert/etak
- Commit
632c389
- 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.