agent-test-long-runner

Agent skill for test-long-runner - invoke with $agent-test-long-runner

Install with Tessl CLI

npx tessl i github:ruvnet/claude-flow --skill agent-test-long-runner

What are skills?

0.98x

Review — 11%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Evaluation — 96%

↓ 0.98x

Agent success when using this skill

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

Security Audit: Internal API Gateway

Security audit report with code examples and action items

Criteria

Without context

With context

Section headers present

100%

All major vulnerabilities covered

100%

Reasoning per issue

100%

Corrected code examples

100%

Vulnerable code cited

100%

References or standards cited

100%

Action items or next steps

100%

Severity or priority ranking

100%

SQL injection addressed

100%

Secret key exposure addressed

100%

SSRF / unvalidated URL proxy addressed

100%

Admin route missing auth addressed

100%

Without context: $0.3500 · 2m 7s · 8 turns · 11 in / 7,907 out tokens

With context: $0.4632 · 2m 26s · 18 turns · 23 in / 7,888 out tokens

97%

-3%

Distributed Caching Architecture for a Growing SaaS Platform

Architecture design document with text diagrams

Criteria

Without context

With context

Section headers used

100%

Text-based diagram present

100%

Multiple diagrams

100%

Design decision reasoning

100%

Comprehensive component coverage

100%

Cache invalidation strategy

100%

Failure modes addressed

100%

References to technologies or patterns

100%

Action items or next steps

100%

70%

Incremental adoption addressed

100%

Non-trivial detail depth

100%

Without context: $0.4069 · 2m 45s · 13 turns · 20 in / 8,362 out tokens

With context: $0.6407 · 3m 55s · 23 turns · 63 in / 12,230 out tokens

93%

Technical Research Report: Vector Database Selection for a RAG Pipeline

Research report with progress documentation and citations

Criteria

Without context

With context

Progress log produced

100%

Progress log shows evolution

62%

87%

Section headers in report

100%

All four databases covered

100%

Multiple comparison dimensions

100%

Citations or named references

100%

Reasoning documented

100%

Recommendation section

100%

Action items or next steps

25%

Report depth

100%

Managed vs. self-hosted addressed

100%

Indexing algorithm mentioned

100%

Without context: $0.5567 · 3m 41s · 20 turns · 27 in / 10,367 out tokens

With context: $0.5373 · 3m 6s · 24 turns · 30 in / 9,340 out tokens

Evaluated: 3 days ago
Agent: Claude Code
Model: Unknown

Table of Contents

Security Audit: Internal API Gateway Distributed Caching Architecture for a Growing SaaS Platform Technical Research Report: Vector Database Selection for a RAG Pipeline

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.