Comprehensive prompt engineering reference for Claude Opus 4.6.
Search meme templates, suggest formats, and generate local or hosted image memes.
Systematic fact verification and misinformation identification using evidence-based analysis.
Web search and research using Perplexity AI.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms.
Validate documentation for unsupported claims, made-up metrics, and unverifiable statements
Manage mo markdown viewer — check status, add/remove patterns and groups, refresh, stop servers, reset.
Create safety-bounded draft structures and run local deterministic checks for clinical case, diagnostic, trial, safety, and aggregate…
Automatically discover diagram and visualization skills when working with flowcharts, sequence diagrams, architecture diagrams, ER…
Create HTML flowcharts and process diagrams with decision trees, color-coded stages, arrows, and swimlanes.
Transforms conversations and discussions into structured documentation pages in Notion.
Use this skill for \"humanize this text\", \"remove AI tells\", \"make this less AI-sounding\", \"strip AI patterns\", \"de-AI my…
Install and use pdflatex to compile LaTeX documents into PDFs on Linux.
Transform structured podcast notes into engaging video scripts with a conversational, first-person broadcasting style.
Bi-directional translator between verbose descriptions and established terminology (semantic anchors).
Transforms story descriptions into polished scripts and consistent visual storyboards using AI-generated imagery.
Framework-driven audit and optimizer for any markdown vault.
Writing style guide for technical content, social media, blog posts, READMEs, git commits, and developer documentation.
Use when targeting ACM CoNEXT (CoNEXT) or deciding whether a computer-science manuscript fits this venue.
Capture atomic notes, search and browse PrivateBox, and run SlipBox semantic link, cluster, tension, and theme-synthesis workflows.
Optimizes software project structures and documentation to enhance AI collaboration efficiency and context management.
Learning & Documentation agent skills on mcprush shape the writing itself: what a release note leads with, which clauses a contract is read for, how much hedging a paragraph is allowed to carry. The kinds are workflow, expertise, output format, voice & style and guardrail, and the one a skill belongs to, where its author declared it, is the fastest way to guess what it will do to your prompt.
What to look at before installing one is what it costs in context and what it takes away: a guardrail that refuses an action and a voice that rewrites a sentence are both skills, and only one of them will stop the agent doing something. Every skill here says what it costs in context, which kind it is where its author declared one, what it needs beside it to work and the licence it is published under, next to the publisher it came from and whether that publisher has been verified. The filters on the left narrow it further and the sort at the top decides what comes first.
A skill is not connected to anything: there is no endpoint to authorise and nothing routed through the gateway. Installing one drops a folder of instructions into the client’s own skill folder, and uninstalling it is deleting that folder. The exact line for each client is on the skill’s own page, because it differs by client rather than by skill.