CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-production-validator

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

40

1.22x
Quality

7%

Does it follow best practices?

Impact

98%

1.22x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-production-validator/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

2%

Production Readiness Auditor

Mock and code quality detection

Criteria
Without context
With context

Scans for mock pattern

100%

100%

Scans for fake pattern

100%

100%

Scans for stub pattern

100%

100%

Excludes test directories

100%

100%

Excludes test files

100%

100%

Scans for TODO/FIXME

75%

100%

Scans for hardcoded test data

100%

100%

Scans for console.log

100%

100%

Produces JSON report

100%

100%

Violations detected in sample

100%

100%

Test files not flagged

100%

100%

100%

38%

Deploy-Ready API Server

Health check and deployment readiness

Criteria
Without context
With context

Health endpoint exists

100%

100%

Health response: status field

75%

100%

Health response: timestamp field

0%

100%

Health response: uptime field

100%

100%

Health response: dependencies object

0%

100%

Env validation: DATABASE_URL

0%

100%

Env validation: REDIS_URL

0%

100%

Env validation: JWT_SECRET

0%

100%

Env validation: error message

100%

100%

SIGTERM handler registered

100%

100%

Graceful server close

100%

100%

No FORCE_HTTPS in dev

100%

100%

94%

12%

Integration Test Suite for E-Commerce Platform

Real integration test suite authoring

Criteria
Without context
With context

DB connects via env vars

100%

100%

DB CRUD: create + findById

100%

100%

DB CRUD: update + delete

100%

100%

Redis env vars

100%

100%

Redis set/get/delete

100%

100%

Payment real API key

100%

100%

Payment error test

100%

100%

Auth 401 test

100%

100%

XSS sanitization test

66%

100%

Concurrent 100 requests

0%

100%

Avg response time threshold

0%

25%

Sustained load 95% success

100%

100%

No in-memory DB

100%

100%

No mock service objects

100%

100%

Repository
ruvnet/claude-flow
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.