Name: agent-production-validator
Rating: 57.99999999999999 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-production-validator

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

1.22x

Quality

35%

Does it follow best practices?

Impact

98%

1.22x

Average score across 3 eval scenarios

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-production-validator/SKILL.md

The canonical home for this skill is agent-production-validator in ruvnet/claude-flow

Quality

Content

42%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 an over-long, monolithic collection of illustrative TypeScript test snippets whose syntax is corrupted, organized as a topic catalog rather than a runnable validation workflow. It conveys intent but is not directly executable and lacks the structure and feedback loops the task demands.

Suggestions

Trim the verbose illustrative test suites (CRUD, Redis, SMTP, load, security) to just the validation-specific patterns and grep commands; Claude already knows how to write these tests.

Fix the corrupted code syntax so examples are executable: regex delimiters and path/URL slashes currently render as '$' (e.g. '/mock[A-Z]\w+/g', 'https://api.stripe.com/v1', '/health').

Reframe the catalog as a sequenced validation workflow with explicit checkpoints (run scan -> review violations -> fix -> re-run) and move the bulk test templates into separate reference files.

Dimension	Reasoning	Score
Conciseness	The ~370-line body inlines full illustrative test suites (CRUD, Redis, SMTP, load, security) that explain testing mechanics Claude already knows. It is noticeably verbose with several padded sections, though not to the 'explains what a PDF is' extreme of anchor 1.	2 / 5
Actionability	Concrete code is provided throughout, but it is systematically corrupted and non-executable: regex delimiters and URLs use '$' instead of '/' (e.g. '$mock[A-Z]\w+$g', 'https:/$api.stripe.com$v1', '$health'), so none of it runs as written. This lands between pseudocode (anchor 3) and executable (anchor 4).	3 / 5
Workflow Clarity	The content is a catalog of validation strategies and checklists rather than a sequenced process, and there are no validate->fix->retry feedback loops for the batch/test operations it prescribes. Per the destructive/batch cap, workflow clarity cannot exceed 3 here.	3 / 5
Progressive Disclosure	Section headers exist (Validation Strategies, Checklist, Best Practices) giving some structure, but the file is monolithic with no bundle files and no signaled references, and large blocks of test code that belong in separate reference files are inlined.	3 / 5
	Total	11 / 20 Passed

Description

28%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 frontmatter description is a placeholder-grade string that names the skill but conveys no concrete capabilities and no usage triggers. It would not help a user or Claude decide when to invoke it.

Suggestions

Add a 'Use when...' clause stating concrete triggers, e.g. 'Use when verifying an application is fully implemented, free of mock/stub code, and ready for production deployment'.

Replace 'Agent skill for production-validator' with the specific actions the skill performs (e.g. 'Scans for mock/fake/stub implementations and runs integration tests against real databases, APIs, and infrastructure').

Include natural trigger terms users would actually say ('production readiness', 'deployment validation', 'remove mocks', 'end-to-end testing').

Dimension	Reasoning	Score
Specificity	The description names the domain ('production-validator') but gives no concrete actions, only 'Agent skill for production-validator - invoke with $agent-production-validator'. It does not reach anchor 3 because no specific capabilities are listed.	2 / 5
Completeness	It offers a vague 'what' ('Agent skill for production-validator') and entirely lacks a 'when' / 'Use when...' clause, matching anchor 2 exactly and staying below the cap of 3 for missing trigger guidance.	2 / 5
Trigger Term Quality	Only the technical skill name and invocation syntax appear; there are no natural phrases a user would say like 'production readiness' or 'deployment validation'. It sits above anchor 1 because 'production' and 'validator' are at least domain-relevant terms.	2 / 5
Distinctiveness Conflict Risk	The name 'production-validator' marks a fairly distinct niche, but the description itself is generic and articulates no distinct triggers, so it could still overlap with other testing/validation skills.	3 / 5
	Total	9 / 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: ruvnet/ruflo
Path: .agents/skills/agent-production-validator/SKILL.md
Commit: fa13ee4

Reviewed: about 8 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.