Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 377,256 indexed, measured the same four ways as everything else here.
A traditional Chinese Xiaoliuren divination method for making a reading from numbers, dates, times, or positions. It maps the result to six named categories used to judge whether a situation is favorable, delayed, difficult, or empty.
Summarize video URLs or local videos into timestamped Markdown notes from complete transcripts and actual visual evidence, with adaptive sampling and targeted visual follow-up. Supports Bilibili, YouTube, Douyin and Kuaishou.
An adapt-first playbook that helps Opus (or any Claude model) pick up the work habits that made Fable effective — render-level verification, hypothesis-driven debugging, delegation guards, input fidelity, confirm-before-irreversible, and execution rhythm. It does NOT auto-inject rules or fake model capability. Its…
★not rated 6 4mo agoA
tokens not measured
originalMIT
The Filter (兔). Orchestrator and post-processor that makes LLM output actually readable. Invokes other zodiac animals based on what the user needs, then synthesizes and reshapes their raw output for the specific human reading it. Breaks the LLM default of audience-blind verbosity — walls of text, wrong detail level…
A writing skill for producing clear, concise Russian text. It removes bureaucratic phrasing, passive constructions, vague wording, and common AI clichés.
A workflow for creating visual designs in the Figma desktop app through a coding agent. Figma is a design tool; the workflow can read design context and write design elements to its canvas.
Windows-compatible implementation of the Ralph Wiggum technique - continuous self-referential AI loops for iterative development. Uses PowerShell instead of bash/jq.
★not rated 6▲
+1 9mo agoA
tokens not measured
originalMIT
An error-recovery add-on for coding agents that handles connection failures, service errors, and message-level errors. It also combines interruption recovery with behavior signals and language-model analysis when using goal mode.
Configurable Claude Code plugin for professional development workflows. Bundles skills, agents, hooks, and automation into a single installable plugin.
Use when user mentions remembering something, asks what you know about them, references past decisions, or needs to store/retrieve personal context across sessions.
Render HTML, Markdown, or URLs to images, PDF, or branded artifacts; extract and watch pages. Runs locally from the @copperline/rendex-mcp npm package. Needs 1 environment variable to run.
★not rated 6 2mo agoA
tokens not measured
originalMIT
Persistent project knowledge base for Claude Code. Records current state, phased roadmap, decisions and their rejected alternatives, and failed approaches — so a new session resumes from what was recorded instead of re-reading the whole codebase.
★not rated 6 2mo agoA
tokens not measured
originalMIT
Convert any document into a production-ready Ozor.ai video prompt. Use this skill whenever the user uploads a document (PDF, PowerPoint, Google Doc, Markdown, text file, or URL) and wants to turn it into a video. Also trigger when the user mentions 'turn this doc into a video', 'make a video from this PDF', 'video…
Evaluates any project's folder architecture against the ICM five-layer context hierarchy. Scores Layer 0 (Map/CLAUDE.md), Layer 1 (Rooms/CONTEXT.md), Layer 2 (Stage Contracts), Layer 3 (Reference Material), Layer 4 (Working Artifacts), plus Tools assessment. Checks 14 anti-patterns (8 base + 6 ICM), measures 5…
★not rated 6 2mo agoA135 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: