mcpbeat

Research Skills

2 264 research skills from 396 authors. They find sources and get you up to speed on unfamiliar ground. Half of them fit into 2 278 tokens or less — that is what one costs your context window when the agent loads it. 663 ship runnable scripts rather than instructions alone. 4 of them cannot work without an MCP server, most often rube. We also found 264 copies of these same skills sitting in other people's repositories — counted once here, not 264 times.

2 264 unique 396 authors 1 174 updated this month 87 from vendors

2 278
tokens, median
what a typical one costs in context
663
ship scripts
code that runs, not instructions alone
4
need a server
most often rube
264
copies elsewhere
counted once here, not once per repository

2 257–2 264 of 2 264

page 48 of 48
Aer Paper Body
brycewang-stanford

Use when drafting or revising the body sections of an AER, AER:Insights, or AEJ manuscript — institutional background, data, empirical strategy, results, mechanisms, and conclusion. Covers equation conventions, results-paragraph narration, magnitude interpretation, and back-of-envelope policy calculations. Apply after the empirics are stable and before or alongside aer-introduction.

6k tokens
Aer Topic Selection
brycewang-stanford

Use when evaluating whether a research idea clears the AER top-5 bar, when routing between AER, AER:Insights, and the AEJ family, or when sharpening a fuzzy contribution sentence into one publishable claim. Apply before any writing begins.

4k tokens
Last30flames vendor
firecrawl

Research what's genuinely new about a topic in a recent time window. Use when the user asks what's new, recent, or trending on a subject and wants a source-grounded brief rather than a quick lookup.

18k tokens scripts
Cowork Roi Report vendor
microsoft

| Generates a Microsoft-branded "What Cowork Did for Me" self-contained HTML impact report from the signed-in user's own Copilot Cowork session history in OneDrive. Quantifies leverage as a speed multiplier and a professional-services-equivalent value using research-anchored task-category bands and an artifact-scaled two-clock model, with a live hourly-rate control, KPIs, a work-by-business-process breakdown, a projects-by-category view, and an activity heatmap. Use when the user asks to "generate my impact summary report", "generate my impact report", "my impact summary", "my Cowork ROI", "what Cowork did for me", "Cowork impact report", "Copilot Cowork ROI report", "how much time has Cowork saved me", "my Cowork value report", or any request for a personal impact / ROI / value report on Copilot Cowork usage. or daily briefings.

73k tokens scripts
Pwc CLI vendor
huggingface

Papers With Code CLI (`pwc`) for searching and reading AI/ML papers, discovering recent and trending research, finding related work and paper lineage, browsing tasks, methods, conferences, and benchmark leaderboards through the public Papers With Code catalog. Use whenever the user asks to find papers, survey literature, compare research, inspect an arXiv paper, explore AI/ML taxonomy or conferences, discover benchmarks or state-of-the-art models, or mentions Papers With Code, `pwc`, or the `pwc-cli`. Prefer this skill for grounded AI/ML research even when the user does not explicitly ask for a CLI command.

32k tokens scripts
Cranky Old Sam vendor
microsoft

| Simplicity-obsessed design reviewer that interrogates complexity, questions every abstraction, and insists on the minimal viable design. Sounds like a senior engineer who has watched too many systems collapse under their own weight and now treats every unnecessary layer as a personal affront. Not a generalist skeptic — a simplicity zealot. A lens for any checkpoint — brainstorm, design, plan, implement, debug, or review — not just design. a layer, an over-built fix — any time the worry is "do we actually need this, or can it be deleted?"

3k tokens
Mass Change vendor
microsoft

Research and plan a large-scale change, then execute it in parallel across isolated agents that each open a PR.

1k tokens
Amplifier Openclaw vendor
microsoft

Delegate complex tasks to Amplifier's multi-agent framework. Use when: (1) research/comparison needing multiple perspectives, (2) multi-file code projects, (3) architecture/design reviews, (4) user asks for deep/thorough work. NOT for: simple Q&A, quick edits, casual chat, anything needing <5s response. CLI: amplifier-openclaw.

3k tokens scripts