Audit and rewrite content to remove AI writing patterns ("AI-isms"). Activate whenever editing prose-heavy files (Markdown, documentation, blog posts, READMEs, release notes, emails). Cursor port of the avoid-ai-writing skill v3.16.0. See https://github.com/conorbronsdon/avoid-ai-writing.
Cursor rule "main" from amxv/terminal-mcp, covering terminal mcp project instructions, what this project does, key features, how it works and key components.
NEVER create a separate jest.config file, always put these in package.json. NEVER cd to another directory, always stay in the project root. NEVER use CommonJS, use ES6 JS for everything as much as possible. NEVER use npm, only yarn. NEVER swallow errors, or use a "fallback" codepath in case of errors, or do anything…
Use when navigating a codebase, searching for symbols, tracing definitions, analyzing change impact, or planning refactors. Requires the repository to be indexed with ok index . first.
This is a TypeScript-based MCP (Model Context Protocol) server that enables AI agents to interact with Gremlin-compatible graph databases. The server provides 6 tools and 2 resources for comprehensive graph database operations.
A writing-protection rule for changes to core cognitive documents. It requires path checks, version backups, attribution labels, change records, map updates, and system logs.
A Chinese-language workflow for improving an existing stock or futures trading factor. It covers testing different time periods, removing components to measure their value, refining the factor, and checking whether the results are reliable.
Musk 5-step engineering algorithm. Primarily for reviewing and cleaning up existing systems. Apply in strict order: question requirements, delete parts, simplify, accelerate, automate. Bias toward deletion. Never advance to a later step until earlier steps are visibly complete.
A repository rule for work inside the SumSec-Skills code repository. It tells contributors to read AGENTS.md and relevant skill instructions before changing skills, plugin manifests, or installation documents.
Generate real starter content for a project's What-L2 (requirements) and How-L2 (architecture/conventions) CEP layers once ult-repo-layout has resolved their paths but found them empty — an honest, minimal, YAML-frontmatter-first overview document per layer for small/single targets, or graphify-informed per-module…
Use Context Engine CLI (ctx-cli) to search code & the knowledge graph, investigate services, triage/resolve CVE & SAST findings, and apply coding guidelines.
★not rated 9 1mo agoA231 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: