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.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

75%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 well-organized, largely actionable skill body with a clear multi-step workflow and sensible reference splitting. The recurring gap is the orphaned bundled scanner script (scripts/ship_gate_scanner.py) that the body never invokes, plus light inlining of detection logic that already lives in the references.

Suggestions

Reference and prefer the bundled scanner in Step 2 (e.g., 'Run `python scripts/ship_gate_scanner.py .` for automated checks; fall back to the grep patterns in references/patterns.md only if the script is unavailable') to lift actionability and use the bundle you ship.

Move the inlined Step 1 stack-detection rule block into references/patterns.md (or a references/stack-detection.md) and summarize it in the body, reducing duplication with the patterns file and improving conciseness.

Add an explicit validation/verification checkpoint in Step 2 or Step 4 for triaging likely false positives before issuing a CRITICAL verdict, strengthening the feedback loop for this blocking gate.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes Claude's competence (no basic concept explanations), but the inlined stack-detection rule block (Step 1) duplicates material that parallels references/patterns.md and the full report example is somewhat long — minor instances that could be trimmed.	4 / 5
Actionability	Provides concrete, copy-pasteable detection rules ('next in dependencies -> Next.js') and points Claude to grep patterns in references/patterns.md, but never references the bundled scripts/ship_gate_scanner.py, which would be the most directly executable path.	4 / 5
Workflow Clarity	Four clearly sequenced steps (Detect Stack -> Automated Checks -> Manual Confirmation -> Verdict) with progress reporting and a re-run feedback loop ('Fix critical items and re-run'), but verification of findings (false-positive handling) is only implicit and the script-backed check is not wired in.	4 / 5
Progressive Disclosure	Good overview structure with one-level-deep, clearly signaled references to references/checks.md and references/patterns.md, but the bundled scripts/ship_gate_scanner.py is never referenced from the body and some stack-detection content is inlined rather than split out.	4 / 5
	Total	16 / 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.

A strong, well-structured description: third-person voice, explicit what/when, rich natural trigger phrases, and a clear negative boundary. The only mild weakness is that the concrete action set is somewhat narrow (scan/intercept/block) despite broad category enumeration.

Dimension	Reasoning	Score
Specificity	Names the domain ('Pre-production audit') and concrete actions ('scans a codebase', 'Intercepts deploy commands and blocks until critical items pass') across 8 enumerated categories, but the underlying actions are scan/intercept/block rather than many distinct operations — minor gaps versus comprehensive coverage.	4 / 5
Completeness	Explicitly answers both 'what' (pre-production audit scanning 8 issue categories, intercepts/blocks deploys) and 'when' ('Use for ...' with concrete triggers) plus a negative boundary ('Not for CI/CD setup or infra provisioning').	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases with synonyms — 'run ship gate', 'am I ready to ship', 'pre-launch audit', 'can I deploy', 'push to production', 'go live checklist', 'preflight check' — exactly the phrasings a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (pre-deploy gate that intercepts deploy commands) with distinct triggers and an explicit 'Not for ...' boundary, minimizing overlap with general review or CI/CD skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: engineering/skills/ship-gate/SKILL.md
Commit: 19392f7

Reviewed: ~3 hours 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.