ship

Structured release pipeline with pre-flight checks, AI code review, version bump, changelog, PR creation, platform publish, and GitHub release. Triggers on "ship", "release", "publish".

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/ship/SKILL.md

Quality

Content

66%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.

The body excels at workflow clarity with gated phases and escalation, and it organizes content well as an overview pointing to per-phase references. Its weaknesses are triple-listing of the phases (conciseness) and deferring most executable detail to phase files that are not present in the bundle (actionability).

Suggestions

Consolidate the three phase listings — keep either the ASCII architecture diagram or the Execution Flow list, and let the Reference Documents table carry navigation, to remove redundancy.

Inline at least one fully executable phase (e.g. the version-bump commands for npm/Python/generic) so the body is actionable on its own when the phase files are not bundled.

Ensure the referenced phases/*.md and ../_shared/SKILL-DESIGN-SPEC.md files ship with the skill, or note their absence, so the progressive-disclosure references resolve.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the seven phases are restated three times — the ASCII architecture diagram, the 'Execution Flow' numbered list, and the 'Reference Documents' table — which is redundant padding that could be tightened.	3 / 5
Actionability	The Pre-Flight Checklist table gives concrete, executable commands with pass conditions, but the detailed per-phase steps are deferred to the phase reference files, so the body's own guidance is incomplete rather than copy-paste ready.	3 / 5
Workflow Clarity	A clear seven-phase sequence with an explicit gate per phase ('Each phase must pass before the next begins'), a pre-flight checklist, and a three-strike escalation feedback loop for error recovery, matching the score-5 anchor; validation is present so the destructive-operation cap does not apply.	5 / 5
Progressive Disclosure	The overview is well structured with one-level-deep references signaled clearly via the 'Reference Documents' table, but the referenced phase files and shared spec are absent from the bundle, so the split cannot be fully verified.	4 / 5
	Total	15 / 20 Passed

Description

88%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.

The description is strong: it concisely names a comprehensive set of concrete release-pipeline actions and pairs them with explicit, natural trigger phrases. The only gap is trigger-term breadth, where a couple of common synonyms would round out coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'pre-flight checks, AI code review, version bump, changelog, PR creation, platform publish, and GitHub release' — giving comprehensive coverage of the release pipeline, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (structured release pipeline with seven named phases) and 'when' ('Triggers on "ship", "release", "publish"') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	'Triggers on "ship", "release", "publish"' supplies natural terms users would actually say, but coverage stops at three words with no synonyms (e.g. 'deploy', 'cut a release'), so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The 'structured release pipeline' framing with specific phases carves a clear niche, though generic triggers like 'publish' carry minor overlap risk with adjacent git/deploy skills.	4 / 5
	Total	18 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 14 missing, 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: catlog22/Claude-Code-Workflow
Path: .claude/skills/ship/SKILL.md
Commit: 07491b0

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.