nm-sanctum-doc-updatesUpdate documentation after code changes with quality gates, slop detection, consolidation, and accuracy verification
Install via ClawdBot CLI:
clawdbot install athola/nm-sanctum-doc-updatesGrade Limited — 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/sanctumAudited Apr 16, 2026 · audit v1.0
Generated May 11, 2026
A small team maintains a popular open-source library and needs to keep README, docstrings, and changelog in sync with frequent code changes. This skill automates the detection of stale documentation, consolidates redundant files, and verifies accuracy of version numbers.
An enterprise IT department updates a microservices architecture and must update internal API docs, architecture decision records (ADRs), and developer guides. The skill enforces directory-specific style rules, scans for AI-generated slop, and syncs plugin metadata with documentation.
A SaaS company releases bi-weekly updates and needs to update user-facing documentation, release notes, and capability references. This skill identifies undocumented features from CHANGELOG, consolidates bloated documentation, and ensures accuracy before deployment.
A fast-moving startup adds new features to its MVP and requires lightweight documentation updates. The skill reduces manual toil by automatically targeting relevant files, detecting redundancy, and validating edits against style guidelines.
A research lab maintains simulation software and needs to keep documentation precise and up-to-date with code changes. The skill's accuracy verification and slop detection are critical for maintaining credibility in published materials.
Offer automated documentation updates as a service to software teams, ensuring their docs stay synchronized with code changes. This could be bundled with CI/CD pipelines or offered as a standalone plugin.
License the skill as part of a larger developer tool suite that reduces time spent on documentation by 50-70%. Generate revenue through per-seat licensing or enterprise contracts.
Provide the skill freely to open-source projects to improve documentation quality, while offering premium support and customization for enterprise users. Revenue comes from enterprise support contracts and consulting.
💬 Integration Tip
Add the skill as a post-merge CI step to automatically run after code changes. Ensure the required plugin dependencies (git-workspace-review, slop-detector, proof-of-work) are installed in your Claude Code environment.
Scored May 11, 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。