Top Agent Skills

Guides users through creating, refining, and evaluating agent skills, including drafting, testing, and optimizing descriptions for better triggering.

Apply idiomatic Python patterns and best practices for writing robust, efficient, and maintainable code, covering type hints, error handling, context managers, and data classes.

Creates and manages design token systems with three-layer architecture, generates CSS variables, validates token usage, and produces brand-compliant slide presentations with Chart.js and contextual decision logic.

Analyzes local SEO signals including Google Business Profile optimization, NAP consistency, citation health, review signals, local schema markup, and location page quality, with business type and industry vertical detection.

Drive Graphify from its CLI to build, refresh, query, export, and serve a durable code/corpus knowledge graph. Use when the user wants `.graphify/GRAPH_REPORT.md`, `graph.json`, `graph.html`, `graphify update`/`summary`/`query`/`path`/`explain`/`tree`, change-aware review context, git-hook or watch-based refresh, a stdio MCP graph server, or an install into jeo, jeopi, gjc, opencode, Claude, Codex, or Gemini. Also covers the honest structural fallback when native extraction is empty or misleading. Route simple locate/reference work to `codebase-search`, narrative knowledge-base work to `llm-wiki`, and project-memory handoff to `opencontext`. Triggers on: graphify, graphify update, graphify query, knowledge graph CLI, GRAPH_REPORT.md, graph.json, codebase graph, graph refresh, graphify install, graphify serve, review context, affected flows.

GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.

Show the quick-reference guide for the whiteboard planning system (whiteboard, hot-seat, napkin, connotation-cop) — the flow, what to say, and the rules. Use when the user asks "whiteboard help", "how do I use the whiteboard", "what's the flow", "remind me how whiteboard works", "which skill do I use", or seems unsure how to start or continue a whiteboard effort. This skill only DISPLAYS the guide — it never starts a board, resolves tickets, or does any work.

Imported skill inventory from anthropic

Translate text faithfully into a target language while preserving meaning, register, and intent.

A creative-direction (taste) layer for music videos and short-form edits in the angelcore / cloud-trance / hyperpop visual family. Distills a named-genre aesthetic vocabulary, a mood + color + light system, and a beat-synced editing grammar, then chains ECC's video skills (video-editing, fal-ai-media, remotion-video-creation, motion-*, content-engine) into one production pipeline. Use when the work is not just making a video function but making it feel intentional, when building a music video, a fancam/edit, a moodboard-driven reel, or when choosing a coherent visual direction for AI-generated b-roll.

Generate readme generator operations. Auto-activating skill for DevOps Basics. Triggers on: readme generator, readme generator Part of the DevOps Basics skill category. Use when working with readme generator functionality. Trigger with phrases like "readme generator", "readme generator", "readme".

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

Design and implement transactional and marketing email templates. Use when asked to "build an email template", "transactional email", "welcome email", "password reset email", "email design", "React Email", "MJML", "dark mode email", or "email copy review". Inbox / SPF / spam → enhance-email-deliverability.

Comprehensive legal document review specialist for contracts, litigation documents, and real estate agreements — summarizing documents, flagging risk clauses, comparing contract versions, and checking compliance across any law firm size or practice area

Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.

Drafts professional legal letters for personal injury litigation including settlement demands, cease-and-desist, notice letters, and response correspondence. Tailors tone by recipient type. Use when drafting demand letters, pre-suit correspondence, insurance claim letters, cease-and-desist notices, or litigation response letters.

Data analysis best practices with pandas, numpy, matplotlib, seaborn, and Jupyter notebooks.

Manage GitHub issues, PRs, branches, and repositories via OAuth (3LO). For reading issues or PR details, not for deep code analysis — delegate that to code-agent.

Write legal memoranda with analysis and conclusions. TRIGGERS - Use when user needs help with legal-memo related tasks.

Generate unit tests, integration tests, and test plans. TRIGGERS - Use when user wants tests, test cases, testing strategy, or test coverage.

Manage local skills - list, add, remove, search, edit, setup wizard

Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.

Drive development with tests by writing a failing test before implementing code, and reproduce bugs with tests before fixing them.

Tests and debugs web applications in real browsers using Chrome DevTools MCP, enabling DOM inspection, console error capture, network analysis, performance profiling, and visual verification with live runtime data.

Protects stateful GKE workloads by configuring backup plans, restore workflows, and disaster recovery using Backup for GKE.

Plans, configures, and manages GKE networking including private clusters, VPC-native configurations, Gateway API, DNS, ingress/egress, Dataplane V2, and IP planning.

Configures GKE workload reliability with PodDisruptionBudgets, health probes, topology spread constraints, and graceful shutdown patterns.

Analyze a winning short video's formula and generate a new branded video with your product, character, and language (English or Spanish) for social media ads.

Query, inspect, and manage Redis databases from the command line using redis-cli, covering connection, data operations, scanning, and server diagnostics.

Helps write and edit EAS CI/CD workflow YAML files for Expo projects, including schema validation and resource fetching.

Drafts structured goal-loop prompts for long-running agent work with verifiable stop conditions, validation commands, and documentation requirements.

Reviews code through the lens of 12 classic software engineering books, catching design smells, coupling issues, and architectural risks that linters miss.

Produces clear, credible, and conversion-focused marketing copy for landing pages and emails, with mandatory brief confirmation and strict no-fabrication rules.

Treats rough ideas as competing organisms on an evolution island, scoring, selecting, crossing, and evolving them through structured rounds to surface the strongest concepts.

Audits Pinterest Ads measurement, tag and Conversions API setup, catalog readiness, creative, audiences, automation, budget, brand safety, and reporting.

Reads every source file in a codebase to build a deep understanding of the project, using pagination for large files.

Pressure-tests GDPR compliance with six Article-cited questions covering RoPA, lawful basis, DPIA, DSARs, transfer impact assessments, and breach logging for audit readiness.

Guides SOC 2 Type II audit preparation with six forcing questions covering scope, control consistency, evidence tracking, and cross-walk to ISO 27001.

Prepares for FDA QSR audits by asking six forcing questions covering complaints, process validation, DHRs, CAPAs, labeling, and Form 483 history.

Pressure-tests medical-device QMS work with six traceability-obsessed questions before internal audits, regulatory reviews, or product launches.

Manage Microsoft Fabric capacities and resources programmatically using the Azure SDK for Python.

Translate text, transliterate between scripts, detect languages, and perform batch document translation using Azure Translation SDKs for TypeScript.

Manage Azure Cache for Redis instances via the Azure Resource Manager .NET SDK, including creation, firewall rules, access keys, patch schedules, geo-replication, and private endpoints.

Manage cryptographic keys in Azure Key Vault and Managed HSM using the .NET SDK. Create, rotate, encrypt, decrypt, sign, and verify keys with KeyClient and CryptographyClient.

Extract text, tables, and structured data from documents using Azure AI Document Intelligence SDK for .NET, with support for prebuilt and custom models.

Manage Azure Application Insights resources including components, web tests, workbooks, and API keys using the .NET SDK.

Migrate Slack bots to Microsoft Teams, build dual-platform bots, and convert between Block Kit and Adaptive Cards using a routed expert system with 100+ micro-expert files.

Defines vehicle routing problem types (TSP, VRP, PDP) and the data requirements needed to formulate them, without covering any API or interface details.

Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.

Routes NuRec/Neural Reconstruction requests to the correct upstream NVIDIA skill (datasets, conversion, training, rendering, object harvesting, frame cleanup).

Provides practical guidance for training Mixture-of-Experts Vision-Language Models in Megatron Bridge, comparing FSDP and 3D-parallel approaches with lessons from recent multimodal experiments.

Validate and configure packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs with correct context parallelism constraints.

Create library-grade Vue composables that accept maybe-reactive inputs (MaybeRef/MaybeRefOrGetter) so callers can pass plain values, refs, or getters. Normalize inputs with toValue()/toRef() inside reactive effects for predictable behavior.

Create product backlog items in Why-What-Acceptance format — independent, valuable, testable items with strategic context.

Create job stories using the 'When [situation], I want to [motivation], so I can [outcome]' format with detailed acceptance criteria, focusing on user situations and outcomes for JTBD-style backlog items.

Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script).

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations.

Evaluate industry dynamics and market attractiveness by analyzing competitive rivalry, supplier power, buyer power, threat of substitutes, and threat of new entrants.