CtrlK
BlogDocsLog inGet started
Tessl Logo

flow-nexus-platform

Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges

68

5.55x
Quality

52%

Does it follow best practices?

Impact

100%

5.55x

Average score across 3 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/flow-nexus-platform/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

84%

Automated Data Processing Pipeline in the Cloud

Sandbox creation and execution lifecycle

Criteria
Without context
With context

Python template

0%

100%

sandbox_create called

0%

100%

install_packages provided

25%

100%

env_vars no hardcoded secrets

100%

100%

sandbox_upload called

0%

100%

sandbox_execute called

0%

100%

capture_output true

0%

100%

execution timeout set

0%

100%

sandbox_logs called

0%

100%

logs lines within limit

50%

100%

sandbox_delete called

0%

100%

100%

68%

Publish a Rate-Limiting Middleware to the Flow Nexus App Store

App store publishing with metadata and deployment

Criteria
Without context
With context

app_store_publish_app called

0%

100%

All required top-level fields

66%

100%

Valid category value

0%

100%

Semantic version format

100%

100%

Metadata author field

0%

100%

Metadata license field

0%

100%

Metadata repository field

0%

100%

Metadata docs/homepage fields

0%

100%

template_deploy called

0%

100%

template_deploy deployment_name set

0%

100%

Publishing best practices documented

40%

100%

tags is an array

100%

100%

source_code provided

100%

100%

100%

92%

Automate a Competitive Programming Challenge Workflow

Challenge submission and credit earning workflow

Criteria
Without context
With context

challenge_get called

0%

100%

challenge_submit called

0%

100%

challenge_submit execution_time

33%

100%

challenge_submit language field

0%

100%

app_store_complete_challenge called

0%

100%

submission_data passed_tests

25%

100%

submission_data total_tests

0%

100%

submission_data memory_usage

25%

100%

app_store_earn_ruv called

0%

100%

earn_ruv source field

0%

100%

leaderboard_get called

0%

100%

Credit range documented

0%

100%

Repository
ruvnet/ruvector
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.