shipping-artifacts

The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded agents/automation. Defines what each doc must capture and how a reviewer or auditor uses it. Use when documenting a codebase for handoff, mapping user journeys and trust-boundary crossings, planning test coverage, or preparing for a security or performance audit.

Quality

93%

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

Quality

Content

93%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, instruction-only skill that delivers specific, actionable per-document guidance without padding. Workflow clarity is strong but lacks explicit validation/feedback checkpoints and relies on external producer commands that are referenced but not included.

Suggestions

Add an explicit validation/feedback step (e.g. 'after drafting each doc, re-check it against the must-capture list and fix gaps before moving on') to close the workflow-clarity checkpoint gap.

Clarify how the referenced commands (/document-app, /derive-tests, /ship-check) are invoked or where they live, so a reviewer can follow the end-to-end generation flow without guessing.

Dimension	Reasoning	Score
Conciseness	The body is lean and table/bullet-heavy, explicitly forbids padding ('skips generic theory', 'Keep examples and finished templates out'), and avoids re-explaining concepts Claude already knows; every section earns its place.	5 / 5
Actionability	Each document gets concrete must-capture fields, exact table column specs, explicit 'include only if' conditions, and anti-rules (e.g. 'Anti-PRD rule'), giving specific executable guidance despite being instruction-only with no code.	5 / 5
Workflow Clarity	The core/conditional structure is clearly sequenced and each doc defines must-capture plus reviewer-use, but there is no explicit validate→fix→retry checkpoint and the referenced producer commands (/document-app, /derive-tests, /ship-check) are not bundled here.	4 / 5
Progressive Disclosure	The skill is self-contained with no bundle files and well-organized sections (Purpose, Organization, Core, Conditional, Notes); external command references are one level deep and clearly signaled, satisfying the simple-skill exception.	5 / 5
	Total	19 / 20 Passed

Description

92%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, specific description that names a concrete documentation set, uses third person throughout, and pairs a clear 'what' with an explicit multi-trigger 'Use when' clause. The only minor gap is that a couple of natural shorthand phrasings a user might say are not surfaced.

Suggestions

Add one or two shorter natural trigger phrasings (e.g. 'shipping review' or 'code handoff docs') alongside the longer 'Use when' scenarios to broaden trigger-term coverage.

Consider naming the output location ('documentation/ at the repo root') in the description so users searching for where artifacts land can match it.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete artifacts (architecture, flows, permissions, variables/secrets, tests) and conditional docs (emails, cron, SEO, automation), giving comprehensive coverage of what the skill produces rather than vague abstractions.	5 / 5
Completeness	It clearly answers 'what' ('Defines what each doc must capture and how a reviewer or auditor uses it') and 'when' with a concrete 'Use when...' clause enumerating four trigger scenarios, satisfying both halves explicitly.	5 / 5
Trigger Term Quality	Natural trigger phrases users would say are present ('documenting a codebase for handoff', 'mapping user journeys and trust-boundary crossings', 'preparing for a security or performance audit'), but a few common phrasings a user might voice (e.g. 'shipping review', 'code handoff doc') are not explicitly surfaced.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche — reviewability/shipping documentation for AI-built apps — with distinct triggers that are unlikely to fire for unrelated skills, minimizing overlap risk.	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: phuryn/pm-skills
Path: pm-ai-shipping/skills/shipping-artifacts/SKILL.md
Commit: 18468a9

Reviewed: 3 days 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.