Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 390,948 indexed, measured the same four ways as everything else here.
Patient, one-step-at-a-time guidance — exactly one step per message, always starting at step 1, waiting for the user's "done" or "next" before continuing, and pausing in front of anything that changes something. Use this when the user says "step by step", "walk me through it", "slow down", "one step at a time"…
Fetch any URL and convert to clean, ad-free Obsidian Markdown using fetch CLI (Chrome CDP with network-level ad blocking, DOM ad/widget purification, semantic heading normalization, and native Obsidian Callout conversion > [!TYPE] Title). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and…
Deterministic LLM-first SEO audits for websites, blog posts, and GitHub repositories. Use this when the user asks to "perform SEO analysis", "run SEO audit", "analyze SEO", "check technical SEO", "review schema", "Core Web Vitals", "E-E-A-T", "hreflang", "GEO", "AEO", or GitHub repository SEO optimization. For…
Build, debug, test, and optimize WebGPU projects using vgpu, its CLI, or @vgpu packages. Use for vgpu API questions, WGSL workflows, browser or Node rendering, integrations, testing, and performance work.
Bloom financial harness: balances, payments, trades, wallet. The programmable financial harness for AI agents. Use when the user mentions Bloom, asks to set it up, or asks to check balances or positions, send, receive, or pay money or crypto (including paid APIs via x402 or MPP), swap, trade, lend, or use prediction…
Audit and lint Agent Skills (SKILL.md and bundled scripts/references) for YAML frontmatter errors, broken links, weak trigger descriptions, context bloat, hardcoded secrets, and unsafe shell or prompt-injection patterns. Use when the user asks to 'audit my skills', 'lint SKILL.md', 'check why my skill isn't…
Reverse-engineer native binaries (PE/ELF/Mach-O) with the agent-tool MCP server - decompile and disassemble functions, find what references a string, address or struct field, map C++ classes, and inspect or patch a running process. Use when asked to analyze, reverse, decompile, disassemble or patch an executable, DLL…
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 "Signs of AI writing" guide plus newer 2025-era tells. 30 patterns across content, language, style, communication, and filler categories. Severity-tiered (dead…
Publish HTML frontend projects to the PushWebly publishing platform, list published projects, obtain shareable project URLs, change a published app's public/private visibility, and package published HTML projects into Android APKs. Use when Codex needs to publish a local zip project, publish and build an APK, build an…
Interactive remediation of code review findings using parallel specialist agents. Elicits user input at key decision points (use --quick to skip prompts), deploys domain specialists, and verifies with pr-review-toolkit.
Git-backed issue tracker for multi-session work with dependencies and persistent memory across conversation compaction. Use when work spans sessions, has blockers, or needs context recovery after compaction.
Public Claude Code skills for the Webull Thailand OpenAPI, covering authentication, market data, accounts, watchlists, orders, and events.
★not rated 25 4mo agoA
tokens not measured
originalMIT
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: