Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 388,742 indexed, measured the same four ways as everything else here.
Use when user requests systematic deep research on a topic. Six-phase pipeline (survey → evidence → outline → chapter research → assembly+editing → delivery) producing Markdown+HTML dual-format reports with evidence matrices. Enforces no-fabrication red lines, source tiering, claim-ledger audits, workflow modes, and…
Guides the Architect Agent to apply Hexagonal Architecture (Ports & Adapters) and Dependency Inversion to maximize component decoupling, enabling the highest degree of parallel task execution by AI agents. Use this skill whenever designing the architecture for a new feature or module.
Use this agent when the user is planning new features or functionality and needs guidance on technology choices, architecture decisions, or implementation approaches. Examples include: 1) User mentions 'planning' or 'research' combined with technical decisions (e.g., 'I'm planning to add real-time notifications, what…
Use when selecting, benchmarking, or tuning Ollama models on constrained edge hardware; analysing LLM inference performance and context window behaviour; designing or evaluating prompt injection detection approaches; or producing model research documentation. Produces research notes, configuration recommendations, and…
A quality gate for any work produced in your workspace. Run this against a plan, prompt, deliverable, script, or any output before considering it final.
A collection of reusable implementation patterns that can be applied automatically when a task matches their context. The description does not specify which patterns it contains.
Expert Django developer mastering Django 5+ with modern Python practices. Specializes in scalable web applications, REST API development, async views, and enterprise patterns with focus on rapid development and security best practices.
This skill should be used when self-hosting, installing, configuring, operating, updating, troubleshooting, or learning to use NousResearch Hermes Agent, including CLI usage, gateway and Slack setup, plugins, tools, skills, profiles, memory, MCP, cron, Kanban, delegatetask subagents, dashboards, and tmux-managed…
This skill enables Cortex Code to act as an AI FinOps advisor for Snowflake environments. It provides governance strategies, optimization patterns, cost tracking queries, and shadow waste detection capabilities for managing Snowflake AI credit consumption.
A workflow for moving business features between Cocos Creator projects, including locating entry points, mapping code dependencies, checking resources, and fixing paths. Cocos Creator is a tool for building games and interactive applications.
Use when building React components with @n4s/xcomponent, converting MobX observer/useEffect code to X, X.useState, Value, Value.Async, Value.Boxed, Value.Bool, lifecycle hooks, observable props, or component composition with .with().
Use when creative or marketing work risks premature convergence on the first plausible AI output, especially when benchmarks are present and must inform structure without causing imitation.
Operational workflow for contributing posts to Botbies Log. Covers repository setup, frontmatter formatting, PR creation, and deployment. Use this skill when you need to publish, format, or manage posts on the blog.
A set of rules for building or changing PTO pages with shared layouts, design tokens, components, and patterns. A design system is a reusable collection of interface rules and building blocks.
A Chinese-language guide to developing agent skills, including setup, the difference between skills and tools, pricing case studies, integration, and agent coordination.
Guides users through migrating OpenSearch Dashboards saved objects (dashboards, visualizations, index patterns) between instances using the osd-migrate CLI tool.
Use when the user asks to make slides, a slide deck, a presentation, or training/teaching materials as HTML slides and PPTX (or just one of the two). Produces human-readable, plain-tone decks with interactive quizzes in the HTML and a matching PPTX generated with python-pptx, keeping presenter prep out of the deck.…
A Chinese-language editing checklist based on a specific reviewer’s standards for examining article drafts. It checks artificial-sounding phrasing, problematic titles, absolute claims, confusing structure, and incomplete endings.
Diagnoses GitHub Actions CI/CD failures for FanHub's Node.js workflows. Identifies test failures, build errors, Docker issues, and environment problems.
★not rated 2
changed 13d agoA37 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: