77,210 skills — best first
Wrap multi-write operations in transactions; use dispatchAfterCommit and idempotency patterns to ensure consistency
Define responsive layout grid systems with columns, gutters, margins, and breakpoint behavior.
Extract business and contact information from directory pages and company websites.
Set up a lean4 repository clone with proper elan toolchains.
Manually record an insight, correction, preference, or rule that the agent should remember for future tasks.
Map allegations to contract language and draft a response letter with no unintended admissions.
Generate a legal research memo with claim-level source verification, confidence flags, and primary-authority priority.
Create and maintain a lightweight Crabshell W worklog for a standalone Codex task. Use when the user asks for light workflow or wants traceable one-shot work.
Professional narrative style with line breaks, hashtag strategy, and hooks in first 2 lines to avoid truncation
Stop a running real-time transcription. Use when user wants to stop/end live transcription. Triggers on: 'עצור תמלול', 'תעצור את התמלול', 'stop transcribing', 'end transcription', 'תפסיק להקליט'.
Load a GitHub issue as the current plan
Load Crabshell project memory into the current Codex conversation. Use when the user asks to load memory, resume context, or inspect saved project notes.
Design loading, skeleton, and progressive content reveal patterns.
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
Next.js 16 portfolio with MDX blog/projects, Once UI, auto SEO, and endless theming.
React 19 admin dashboard with Material UI v7, Vite 7, and MUI X Charts.
Markdown conversion: PDF, Office, HTML, data, OCR, audio, ZIP, YouTube.
Review guidelines for Mathlib PRs. Use when reviewing pull requests, checking code quality, or assessing whether a PR is ready to merge.
View statistics and recent entries from the persistent memory database. Shows session count, knowledge areas, facts, and recent activity.
Use the mermaid-diagrams skill whenever you are creating or updating mermaid diagrams. Provides guidance on mermaid best practices.
Define UX metrics and KPIs that connect design decisions to measurable business and user outcomes.
Specify micro-interactions with trigger, rules, feedback, and loop/mode definitions.
A minimal demonstration skill showing the simplest possible skill structure with no references, scripts, or assets.
Use when the user wants to explore, list, summarize, or inspect items on a Miro board.
Run test and lint validation gate. Use after implementation to verify code quality.
HOUSTON executes feature tasks directly. No agents. Best for small features (1-3 tasks).
Mobile testing strategies and best practices for the mobile-dev team
Write clean, modern, and highly accessible HTML & JSX code, using semantically correct elements and attributes
molt-agent skill for Claude.
Construct statistical arguments for MVP/awards. Narrative framing, comparison to past winners, advanced metrics, counter-arguments.
Establish a naming convention system for design elements, components, and tokens with clear rules and examples.
Generate nginx config from plain English. Use when configuring nginx.
# Keep Going, Don't Ask for Permission
# NORSOK Standards Specialist
Articulate a compelling north-star product vision that aligns teams and inspires strategic design decisions.
Mine lost deal notes to identify recurring objection patterns. Create objection response playbooks from won deals.
Maintain an Obsidian-friendly memory wiki vault with wikilinks, frontmatter, and official Obsidian CLI awareness.
Test skill for debugging
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Identify, evaluate, and prioritize design opportunities using impact-effort frameworks and strategic criteria.
Master orchestrator for cross-repo infrastructure with dependency graph dispatch
Coordinates other skills and agents. ALWAYS use this skill on startup.
Foodora-only CLI for checking past orders and active order status (Deliveroo WIP).
Use when the user wants to create, list, load, release, or drop partitions in a Milvus collection.
Structure a pattern library entry with problem context, solution pattern, usage examples, and related patterns.
macOS screenshots, UI inspect, clicks, typing, app/window automation.
Profile and optimize bottlenecks. Use for performance issues or caching strategies.
Use when animation runs slow, janky, or causes frame drops
Act as a customer support agent using Google Workspace. Use when the user asks to "handle support tickets", "respond to customers", or needs customer support workflows.
Act as an HR coordinator using Google Workspace. Use when the user asks to "manage onboarding", "track PTO", "handle HR tasks", or needs HR coordination workflows.
Act as an IT administrator using Google Workspace. Use when the user asks to "manage workspace users", "check admin reports", "audit activity", or needs IT administration workflows.
Act as a researcher using Google Workspace. Use when the user asks to "research topic", "collect findings", "organize research", or needs research workflows.
Act as a team lead using Google Workspace. Use when the user asks to "run standup", "manage team tasks", "send team update", or needs team leadership workflows.
Scan code for legacy PatternFly CSS classes and recommend PF6-safe replacements. Use when upgrading from PF4/PF5 or auditing a codebase for deprecated class names.
Audit and fix invalid PatternFly import paths across packages. Use when imports fail, modules are unresolved, or after upgrading PatternFly versions.
Read-only local workspace scout subagent for Pi. Use it to narrow context to relevant files/snippets before implementation.
Use this skill when the user wants to find and work on a GitHub issue.
Break down a coding task into a structured implementation plan with clear steps, file identification, and risk assessment.
Side-by-side stat comparisons with context. Adjust for era, pace of play, league differences. Advanced metrics explained in plain English.
Generate podcast scripts from text content. Use Tone.js and Howler.js for audio mixing. Create intro/outro music, transitions, sound effects.
Guidance for working with the PolicyEngine GitHub agent bot
Review investment portfolios for risk, diversification, fees. Asset allocation recommendations, tax-loss harvesting, rebalancing.
Pull request template for story-driven development. Use when creating PRs or need PR structure reference.
Design sport-specific practice sessions. Drills by skill level and time, warm-up, skill work, scrimmage, cool-down.
Running precommit checks and build validation. ALWAYS use after ANY code changes.
Detect and run project linters, formatters, and type checkers before committing or claiming completion. Auto-detects tools from project config files.
Commit, push, create PR. Use after verification passes and ready to share work for team review.
Structure compelling presentations with clear narratives and visual suggestions
Structure compelling design presentations for stakeholders, reviews, and showcases.
Transform text-heavy slides into visual storytelling. Suggest layout improvements, icon usage, and data visualization.
Track and compare prices across e-commerce websites using stealth scraping.
This skill should be used when the user asks to "prime the project", "load context", "get oriented", "what is this project", or wants to understand the codebase structure before starting work.
# Product Lens — Think Before You Build
# Professional Greeting
Ralph-town development guidelines. Use for code style, project structure, and build commands.
Plan and track projects with timelines, resources, and risk management
# Prompt Craft
# Restart Prompt Skill
Aggregate prospect intelligence from multiple sources including news, social media, company websites, and financial data.
Choose the right prototyping fidelity and method for the design question.
# PubMed Database
Slidev presentation for teaching Python with interactive code execution.
Quickly add always-allow permissions to all AI tool permission lists
Create multiple choice, true/false, fill-in-blank, matching quizzes. Auto-generate plausible distractors. Instant grading with explanations.
Top-down vs bottom-up quota models. Historical attainment, market growth assumptions, ramp periods, territory complexity.
Market salary research, accomplishment quantification, negotiation scripts, total compensation analysis, timing strategy.
Hard reset repository to last good state when Ralph gets stuck
30/60/90/120 day ramp milestones. Activity expectations by week, certification progress, early warning indicators.
React development best practices and patterns, including modern data fetching with React 19.
Use when writing or editing a React component. Covers preferred patterns for functional components, prop types, and styling.
Set optimal line lengths for readability across typography scales and responsive layouts.
Update main/master from origin, rebase current branch on it, resolve conflicts, and push.
Interactive clarification mode for uncertain situations. Use only when user invokes with --askme flag.
Analyzes the conversation and tool usage to propose improvements to skills or store user preferences.
Run a Codex-compatible D/P/T iterative improvement workflow. Use when the task needs repeated plan-execute-verify cycles rather than a one-shot worklog.