agent-production-validator

Agent skill for production-validator - invoke with $agent-production-validator

1.22x

Quality

—

Does it follow best practices?

Impact

98%

1.22x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a verbose, single-file collection of validation code examples covering many topics but lacking a clear sequenced workflow, validation feedback loops, and any progressive disclosure structure. Several code blocks are corrupted and non-executable, undermining actionability.

Suggestions

Move the lengthy per-domain test examples into separate reference files and keep SKILL.md as a concise overview with one-level-deep links.

Replace the corrupted regex literals and URL strings so the code examples are actually executable, or mark illustrative snippets as pseudocode.

Add an explicit numbered validation workflow with validate-fix-retry checkpoints, especially before any deployment-readiness verdict.

Dimension	Reasoning	Score
Conciseness	The body is a long wall of large TypeScript test blocks that over-explain validation concepts Claude already knows; it does not respect the context budget and every token does not earn its place.	1 / 3
Actionability	Concrete code examples are present, but many are non-executable due to corrupted syntax (e.g. "$mock[A-Z]\w+$g" regex literals and "https:/$api.stripe.com$v1" URLs), so they are not copy-paste ready.	2 / 3
Workflow Clarity	Validation areas are listed as parallel sections rather than a clearly sequenced process, and there are no explicit validate-fix-retry checkpoints for destructive or batch validation operations, capping this at 2.	2 / 3
Progressive Disclosure	The skill is a monolithic single-file dump with no references, no bundle files, and no navigation signaling; all detailed material is inline with no layered structure.	1 / 3
	Total	6 / 12 Passed

Description

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 a low-information placeholder that names the skill's domain but states no concrete capabilities or natural trigger conditions. It reads as an auto-generated invocation hint rather than a genuine activation description.

Suggestions

Replace the description with concrete actions, e.g. "Verifies applications are fully implemented and deployment-ready by detecting mock/stub code and running tests against real databases, APIs, and infrastructure."

Add an explicit trigger clause such as "Use when validating production readiness, checking for mock implementations, or confirming an app is deployment-ready."

Drop the "$agent-production-validator" invocation syntax from the description; it is not a term users would naturally say.

Dimension	Reasoning	Score
Specificity	The description "Agent skill for production-validator - invoke with $agent-production-validator" names only the domain; it lists no concrete actions, matching the vague/abstract anchor rather than the multi-action anchors.	1 / 3
Completeness	It gives a weak "what" (a skill for production-validator) and no explicit "Use when..." trigger guidance, so it is missing the "when" entirely.	1 / 3
Trigger Term Quality	The only trigger phrase is the technical invocation syntax "$agent-production-validator", which is jargon a user would not naturally say; no natural keywords like "production validation" or "deployment readiness" appear.	1 / 3
Distinctiveness Conflict Risk	The term "production-validator" carves out a recognizable niche, but the generic framing and lack of explicit triggers mean it could still overlap with general testing or deployment skills.	2 / 3
	Total	5 / 12 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: ruvnet/claude-flow
Commit: 03d4f84

Reviewed: 2 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.