Agent Skills

edit-article

★ 155,900

by mattpocock

Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.

frontend-design

✓★ 136,000

by anthropic

Distinctive, production-grade frontend interfaces that reject generic AI aesthetics through intentional design direction. Guides developers through design thinking before coding: establish purpose, tone, constraints, and a memorable differentiator to avoid cookie-cutter results Emphasizes typography choices (distinctive display and body fonts), cohesive color palettes with CSS variables, and high-impact motion through staggered animations and scroll triggers Covers spatial composition...

design-system

★ 100,600

by nextlevelbuilder

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.

slides

★ 100,600

by nextlevelbuilder

Create strategic HTML presentations with Chart.js, design tokens, responsive layouts, copywriting formulas, and contextual slide strategies.

cavecrew

★ 83,300

by juliusbrussee

Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn...

caveman-stats

★ 83,300

by juliusbrussee

Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.

bootstrap-realtime-eval

✓★ 74,500

by openai

Bootstrap a new realtime eval folder inside this cookbook repo by choosing the right harness from examples/evals/realtime_evals, scaffolding prompt/tools/data…

jupyter-notebook

✓★ 68,500

by microsoft

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and…

cookbook-audit

✓★ 46,400

by anthropic

Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.

analyzing-financial-statements

✓★ 46,400

by anthropic

This skill calculates key financial ratios and metrics from financial statement data for investment analysis

applying-brand-guidelines

✓★ 46,400

by anthropic

This skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messaging

creating-financial-models

✓★ 46,400

by anthropic

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment…

analyzing-financial-statements

✓★ 46,400

by anthropic

This skill calculates key financial ratios and metrics from financial statement data for investment analysis

applying-brand-guidelines

✓★ 46,400

by anthropic

This skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messaging

creating-financial-models

✓★ 46,400

by anthropic

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment…

defuddle

★ 39,700

by kepano

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.

typescript-advanced-types

★ 37,500

by wshobson

Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.

vscode-ext-localization

✓★ 36,200

by github

Localize VS Code extensions across configurations, walkthrough content, and source code messages. Three localization approaches: package.nls.LANGID.json for settings, commands, menus, and views; markdown files for walkthrough content; bundle.l10n.LANGID.json for source code strings Covers all user-facing resources including contributed configurations, commands, menus, views, ViewsWelcome, and walkthrough titles and descriptions Requires creating or updating localization files for all...

bigquery-pipeline-audit

✓★ 36,200

by github

Audits Python + BigQuery pipelines for cost safety, idempotency, and production readiness with exact patch locations. Analyzes every BigQuery job trigger and external API call to identify cost exposure, loop-driven query multiplication, and missing maximum_bytes_billed limits Enforces dry-run and execute modes with explicit prod confirmation, partition filter validation, and scan-size optimization Validates idempotent writes using MERGE, staging tables, or dedup logic; flags unsafe append...

refactor-plan

✓★ 36,200

by github

Plan a multi-file refactor with proper sequencing and rollback steps

winui3-migration-guide

✓★ 36,200

by github

Complete reference for migrating UWP apps to WinUI 3 with before/after code examples. Maps all namespace changes from Windows.UI.Xaml.* to Microsoft.UI.Xaml.* , plus threading, windowing, and dialog APIs Covers the three most common Copilot mistakes: ContentDialog without XamlRoot, MessageDialog usage, and CoreDispatcher patterns Includes migration tables for window management, pickers, background tasks, settings, and GetForCurrentView() replacements Provides a 15-item migration checklist...

acreadiness-assess

✓★ 36,200

by github

Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc…

acreadiness-policy

✓★ 36,200

by github

Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting…

agentic-eval

✓★ 36,200

by github

Iterative evaluation and refinement patterns for improving AI agent outputs through self-critique loops. Provides three core patterns: basic reflection (self-critique loops), evaluator-optimizer (separated generation and evaluation), and code-specific test-driven refinement Supports multiple evaluation strategies including outcome-based assessment, LLM-as-judge comparison, and rubric-based scoring with weighted dimensions Includes practical Python implementations with structured JSON output...

ai-prompt-engineering-safety-review

✓★ 36,200

by github

Comprehensive safety analysis and improvement framework for AI prompts with detailed assessment methodologies. Evaluates prompts across eight dimensions: safety, bias detection, security, effectiveness, best practices compliance, pattern analysis, technical robustness, and performance optimization Provides structured analysis reports with risk scoring, critical issue identification, and strength assessment across all evaluation criteria Delivers improved prompt versions with specific...

arch-linux-triage

✓★ 36,200

by github

Diagnose and resolve Arch Linux issues with pacman, systemd, and rolling-release best practices. Provides step-by-step triage plans using systemctl, journalctl, and pacman to identify root causes Delivers copy-paste-ready remediation commands with verification steps after each major change Addresses kernel updates, reboot considerations, and rollback procedures for safe recovery Accepts optional system snapshots and constraint inputs to tailor diagnosis to your environment

arize-link

✓★ 36,200

by github

Generate deep links to the Arize UI. Use when the user wants a clickable URL to open or share a specific trace, span, session, dataset, labeling queue,…

breakdown-feature-prd

✓★ 36,200

by github

Structured PRD generation prompt for breaking down Epics into detailed feature specifications. Generates complete Product Requirements Documents in markdown format with standardized sections covering goals, user personas, stories, functional and non-functional requirements, and acceptance criteria Prompts for clarifying questions when insufficient information is provided, ensuring comprehensive feature definition before engineering handoff Organizes output into a consistent file structure (...

cli-mastery

✓★ 36,200

by github

Interactive training for GitHub Copilot CLI with guided lessons, quizzes, scenarios, and reference materials. Covers slash commands, shortcuts, modes, agents, skills, MCP, and configuration through eight progressive modules Includes quiz mode (5+ questions per module), scenario challenges, and a comprehensive final exam with XP-based progression tracking Levels progress from Newcomer to Wizard (1500 XP max) with XP rewards for lessons, correct answers, perfect quizzes, and scenarios...

comment-code-generate-a-tutorial

✓★ 36,200

by github

Refactor Python scripts into beginner-friendly projects with instructional comments and markdown tutorials. Applies PEP 8 style guide compliance and standard Python best practices to improve code quality Adds instructional comments throughout the code explaining logic, reasoning, and importance for learners Generates a complete README.md tutorial with project overview, setup instructions, code breakdown, usage examples, and sample output Renames unclear variables and functions for clarity...