CtrlK
BlogDocsLog inGet started
Tessl Logo

ship-gate

Pre-production audit that scans a codebase for security, database, deployment, code quality, AI/LLM, dependency, frontend, and observability issues. Intercepts deploy commands and blocks until critical items pass. Stack-agnostic. Use for "run ship gate", "am I ready to ship", "pre-launch audit", "can I deploy", "push to production", "go live checklist", "preflight check". Not for CI/CD setup or infra provisioning.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is ship-gate in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

70%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 is well-organized with a clear, validated workflow and concrete stack detection, but it depends on two reference files (checks.md, patterns.md) that are absent from the bundle, which breaks both actionability of the core audit and the progressive-disclosure structure.

Suggestions

Ship the missing references/checks.md and references/patterns.md files in the bundle so the core audit checks (SEC-01, DB-07, etc.) and their scan patterns are actually available.

Inline at least one or two representative check definitions with their regex/grep patterns in SKILL.md so the skill remains actionable even before the reference files are loaded.

Verify every referenced path in the body (references/checks.md, references/patterns.md) resolves to a real file, and use markdown link syntax so broken references are obvious.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete detection rules and a compact categories table, though the full 25-line example SHIP GATE REPORT and the lengthy detection block could be trimmed slightly; no padding of concepts Claude already knows.

4 / 5

Actionability

The body gives concrete, executable stack-detection rules and a clear process, but the core check definitions (SEC-01, DB-07, etc.) are delegated to references/checks.md and references/patterns.md, which are not present in the bundle — leaving the central executable guidance incomplete.

3 / 5

Workflow Clarity

A clearly sequenced four-step process (Detect Stack, Run Automated Checks, Manual Confirmation, Verdict) with an explicit verdict validation gate, a fix-and-re-run feedback loop, a manual confirmation checklist, and per-category progress reporting.

5 / 5

Progressive Disclosure

The overview is well-structured and references are clearly signaled ("Full check details in references/checks.md", "using the patterns in references/patterns.md"), but those referenced files do not exist in the bundle, so the one-level-deep disclosure points to missing content and navigation fails.

3 / 5

Total

15

/

20

Passed

Description

95%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 excellent: it states a concrete capability, gives a rich set of natural trigger phrases, and bounds scope with an explicit "not for" clause. The only minor weakness is that the action verbs are somewhat limited relative to the broad category enumeration.

DimensionReasoningScore

Specificity

Lists several concrete actions ("scans a codebase for security, database, deployment, code quality, AI/LLM, dependency, frontend, and observability issues", "Intercepts deploy commands and blocks until critical items pass") with comprehensive category coverage, though the distinct action verbs are fewer than the score-5 anchor's four verbs.

4 / 5

Completeness

Explicitly answers both what (pre-production audit scanning 8 categories, intercepts/blocks deploys) and when ("Use for ..." trigger phrases plus "Not for CI/CD setup or infra provisioning" exclusion), matching the score-5 anchor.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural phrases users would say — "run ship gate", "am I ready to ship", "pre-launch audit", "can I deploy", "push to production", "go live checklist", "preflight check" — including multiple synonyms for the deploy intent.

5 / 5

Distinctiveness Conflict Risk

Clear niche (pre-production ship gate) with distinct trigger phrases and an explicit negative-scope clause, giving minimal conflict risk with other skills.

5 / 5

Total

19

/

20

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: 4 missing

Warning

Total

15

/

16

Passed

Repository
alirezarezvani/claude-skills
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.