81,390 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Reference tools for underused public healthcare data. Two Claude skills: hcris-analyst (look up nonprofit U.S. hospital reporting — related CMS Worksheet S-10 and IRS 990 Schedule H charity-care fields side-by-side, with home-county SVI context) and fda-analyst (look up FDA novel drug approvals from 2021–2024 and find.
★not rated 3 3mo agoA
tokens not measured
originalMIT
Automatically reviews every user message for English grammar, spelling, punctuation, and word-choice mistakes, showing a short correction tip at the top of Claude's response.
★not rated 3 6mo agoA
tokens not measured
originalMIT
An operating system for cognition: 135 composable Agent Skills that encode transferable thinking procedures (reasoning, decision-making, research, analysis, forecasting, creativity, communication, collaboration, learning, metacognition, ethics), routed through a better-thinking dispatcher backed by a machine-readable…
★not rated 3 3mo agoA
tokens not measured
originalMIT
Adversarial review for business documents (offers, proposals, pitches, strategy memos, pricing, important emails). Simulates the toughest realistic counterpart, delivers deal-killing objections with exact quotes and concrete fixes, and keeps a memory of the user's recurring blind spots so it checks those harder every…
Draw a hand-drawn-style diagram from a description and render it to an actual PNG: flowcharts, architecture, sequence/ER diagrams, graphs, mind maps, box-and-arrow layouts. Authors a D2 text file, renders it via a bundled script to a sketchy hand-drawn PNG offline (no browser), then reads the image back and fixes the…
Use when the user accepts, reviews, or asks about non-trivial code — their own or AI-generated — and should understand it rather than just ship it. Triggers on "mentor", "teach me", "explain this", "quiz me", or right after generating concurrency / security / DB-query / algorithm / auth code. Runs a comprehension loop…
A Claude Skill that automates web performance audits (LCP, CLS, INP) using web.dev guidelines, delivers structured reports, actionable fix scripts, and incremental analysis.
★not rated 3 4mo agoA
tokens not measured
originalMIT
Build a 90-day marketing + content tracker Excel file for a SaaS product or indie app, pre-filled with 180 main weekday tweets + 50 weekend bonus tweets across 9 content pillars, a Media Production Queue, Content Mix Rules, and an automated QA Check sheet. Use this whenever the user asks to create a marketing plan…
Test an Android app on a real phone or an emulator using adb. Use when the user wants to install an APK they just compiled, walk through the app's screens, check the on-screen text, reproduce a bug, capture screenshots, read crash logs, or set up an Android testing environment from scratch. Covers both a physical…
Wield Google's Gemini CLI as a powerful auxiliary tool for code generation, review, analysis, and web research. Use when tasks benefit from a second AI perspective, current web information via Google Search, codebase architecture analysis, or parallel code generation. Also use when user explicitly requests Gemini…
Devleck Senior Engineer Skills — turns Claude Code into a senior engineering organization: full-spectrum audits of existing projects and standards-grade construction of new ones across security, data, API, DevOps, observability, testing, performance, accessibility, web presence, privacy and release readiness — plus…
★not rated 3
changed 23d agoA
tokens not measured
originalMIT
Write AI-facing documents (llms.txt, llms-full.txt, FAQ pages, glossaries) to the llms.txt standard. Use when a document's only reader is an AI system.
Use when multiple CLI agents or assistants alternate on the same repository or explicit shared handoff workflow — especially with AGENTHANDOFF.md, side-by-side AGENTS.md/CLAUDE.md/GEMINI.md, dirty worktrees, ownership notes, red tests, resume/continue requests, or /cli-collaboration in Grok Build.
Run one request through several skills in parallel, isolated subagents, then merge their answers or judge the single best one. Use when the user invokes /council (or /council manage), or uses clear multi-skill-comparison language like "try this with a few different skills", "compare how different skills answer this"…
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
★not rated 3 10mo agoA84 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: