nm-leyline-risk-classificationInline risk classification for agent tasks using a 4-tier model. Hybrid routing: GREEN/YELLOW use heuristic file-pattern matching, RED/CRITICAL escalate to w...
Install via ClawdBot CLI:
clawdbot install athola/nm-leyline-risk-classificationGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/athola/claude-night-market/tree/master/plugins/leylineAudited Apr 17, 2026 · audit v1.0
Generated May 6, 2026
Integrate risk classification into CI/CD pipelines to automatically block or flag pull requests modifying critical paths like auth or database. This reduces human review burden and prevents accidental high-risk merges.
AI coding agents use risk tiers to prioritize tasks: GREEN tasks execute in parallel while RED tasks pause for human approval. This optimizes throughput without sacrificing safety.
Regulated environments require every production change to have risk scoring. This skill enforces that CRITICAL changes get war-room checkpoint scoring and human sign-off, ensuring audit trails.
A platform with multiple tenants uses risk classification to isolate high-risk changes affecting one tenant from impacting others. YELLOW changes get conflict checks, RED changes get full isolation.
Offer the risk classification skill as an add-on subscription for CI/CD platforms. Pricing based on number of repositories or tasks classified per month.
Combine the skill with human review for RED/CRITICAL tasks. Clients pay per review for rapid risk assessment and compliance documentation.
License the skill to enterprise AI agent platforms to embed risk classification natively. Revenue from licensing or revenue share on agent task fees.
💬 Integration Tip
Start by adding risk_tier metadata to existing tasks; default GREEN for backward compatibility. Then enable hybrid routing for RED/CRITICAL tasks to invoke war-room-checkpoint.
Scored May 6, 2026
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Chat with Grok models via xAI API. Supports Grok-3, Grok-3-mini, vision, and more.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero,...
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。