Top Agent Skills

Use to audit a customer-facing support bot or AI agent for harm rather than for volume — manipulation and prompt-injection attempts, customers stranded without a human, fabricated answers, and unsafe commitments or disclosures. Trigger for "are people trying to jailbreak our bot", "show me attempts to manipulate the assistant", "is our bot giving wrong answers", "customers stuck with the bot and never got a human", or reviewing an AI agent before or after launch.

Use to design or audit the executive escalation path for a major account — intake, ownership, communication cadence and follow-through — so escalations are resolved rather than merely attended. Trigger for "design our escalation process for key accounts", "an executive escalation went badly", "customer went to our CEO", red account war rooms, or escalations that get attention and then quietly stall.

Use to design or audit complaint identification and classification in customer support, especially in regulated sectors. Trigger for "are we identifying complaints correctly", "complaint detection", regulatory complaint definition, FCA or CFPB complaint handling, vulnerable customer identification, root cause categorisation for complaints, or building an AI classifier for complaints.

Use to compare CX performance to a published or vendor benchmark without fooling yourself — scope mismatch, survivor bias, and definition mismatch usually make external benchmarks incomparable, and internal baselines often beat them. Trigger for "how do we compare to industry", "is our CSAT good", benchmark slide for the board, vendor benchmark report, "are we above average", outsourcing RFP benchmarks, or when someone cites a round-number industry standard.

Use to draw a defensible sample of support conversations for QA review, an audit or a manual analysis, so the results generalise to the population rather than to whatever was easy to pull. Trigger for "which tickets should we review", "how do we pick a sample", "is our QA sampling representative", stratified or risk-based sampling, review coverage design, or a finding based on a handful of hand-picked tickets.

Use to design or audit a QA dispute and appeal workflow with timeboxes, adjudication standards, and second-level consistency so appeals improve trust instead of rewriting scores without rules. Trigger for "QA appeal process", "agents disputing scores", "who adjudicates QA disputes", "overturn rate too high", second-level review standards, or calibration erosion from ad-hoc score changes.

Use to review how call recordings are notified, stored, accessed, redacted and deleted, including the parts that differ from text conversations. Trigger for "review our call recording practices", "do we need to tell customers we're recording", "who can listen to our calls", recording retention, card details spoken on a call, or a request for a customer's own recording.

Builds, ships, and debugs native iOS apps: lifecycle, permissions, entitlements, push, widgets, StoreKit, and App Store review. Use when a submission is rejected or a guideline blocks a release; when a permission prompt never appears, or a call fails with a missing-entitlement error; when push, background refresh, or a background upload never runs; when a universal link opens Safari instead of the app; when the app is killed by the watchdog, by jetsam, or with 0xdead10cc, hangs on launch, or crashes only on device; when a widget, Live Activity, or app extension runs out of memory; when purchases, subscriptions, or restore fail; when a privacy manifest, tracking prompt, or data label is required; when layout breaks under Dynamic Type; or when a new iOS release breaks a shipped app. Not for Swift language mechanics (`swift`), IDE, signing and build settings (`xcode`), store listings and submission workflow (`app-store`), or cross-platform apps (`react-native`, `flutter`).

Write readable, maintainable code through disciplined naming, small functions, and clean error handling. Use when the user mentions "code review", "naming conventions", "function too long", "code smells", "readable code", "boy scout rule", "single responsibility", or "unit test quality". Also trigger when reviewing pull requests for readability, refactoring messy functions, debating comment styles, or improving error handling patterns. Covers SRP, comment discipline, formatting, and unit testing. For refactoring techniques, see refactoring-patterns. For architecture, see clean-architecture.

Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "timeout strategy", "deployment pipeline", "chaos engineering", "bulkhead pattern", "retry with backoff", or "health checks". Also trigger when designing resilient microservices, planning zero-downtime deployments, or investigating cascading failure scenarios. Covers capacity planning, health checks, and anti-fragility patterns. For data systems, see ddia-systems. For system architecture, see system-design.

Systematic Obsidian vault audit and normalization — structure, frontmatter, wikilinks, broken links, Git hygiene.

Use when designing iOS interfaces, implementing accessibility (VoiceOver, Dynamic Type), handling dark mode, ensuring adequate touch targets, providing animation/haptic feedback, or requesting user permissions. Apple Human Interface Guidelines for iOS compliance.

Discover trending, anticipated, and popular movies and TV shows via the Trakt.tv API from the terminal. No authentication required for read-only discovery. Use when the user asks about what to watch, trending movies, popular shows, or media discovery.

Use this skill for any creative writing task involving narrative, character, story structure, or franchise development. Triggers: building or tracking characters, designing plots, writing scenes or chapters, organizing a story universe, developing motifs or themes, building a series or franchise bible, tracking character arcs, resolving plot gaps, or any request to write or develop fiction at any scale — from a single moment to a multi-story cluster. This skill operates like a narrative OS: it tracks state, identifies gaps, organizes hierarchy, and generates content that is consistent with the established world.

Author a Hermes color theme that skins every surface.

Skills system architecture — progressive disclosure, frontmatter, platform filtering, self-editing

Deploy, configure, and troubleshoot Traefik v3 reverse proxy — covers all providers, routing, TLS/ACME, middlewares, and production patterns with YAML examples. Load when setting up or debugging a Traefik instance.

Manage your Radarr (movies) and Sonarr (TV series) media library from the terminal. Search and browse movies/series, add new content, check calendars, view queue and download history, inspect quality profiles, and trigger searches. Use when the user mentions Radarr, Sonarr, the *arr stack, adding a movie or series, checking the library, finding something to watch, what's in the queue, download history, upcoming releases, media server setup, or movie/TV automation.

MCP client: connect servers, register tools (stdio/HTTP).

Use when asked to fix, build, refactor, review, verify, or release software and the work is non-trivial — including delivering a change request (issue, ticket, or request) from intake through planning, gates, implementation, review, verified PR, and authorized post-merge release. neckbeard routes the change through framing, discovery, design, implementation, review, verification, delivery, and learning — choosing the smallest *safe* intervention, proving it at the real delivery boundary, and leaving an inspectable evidence ledger. For change-request / issue-to-PR work, conditionally loads a 9-phase journey with gates, delivery packet, and lifecycle integration. Composes specialist catalog skills rather than replacing them. Not a persona, not a '10x developer' prompt, not a LOC-minimizer. The journey is not loaded for plain fixes, refactors, or reviews that lack an issue/ticket trajectory.

EPUB file format expert — read, write, and edit EPUB2/EPUB3 ebooks. Extract text, metadata, structure, and knowledge from EPUB files for enrichment or memory. Create valid EPUBs from scratch. Validate against the EPUB specification. Use when the user mentions epub, ebook, EPUB file, ebook format, read epub, write epub, create ebook, extract from epub, epub to text, or ebook structure.

HeartMuLa: Suno-like song generation from lyrics + tags.

Teach and guide GitHub workflows. Explains concepts, recommends approaches, and references specialist GitHub skills for execution.

Operate Playwright for browser automation end to end: author and debug E2E test suites (robust locators, network interception and mocking, parallel workers, accessibility snapshot checks), wire them into CI, and drive headless browsing and scraping with an extract -> validate -> save loop. Use when writing, running, fixing, or scraping with Playwright, when a Playwright CI failure or JSON report needs triage, or when the bundled pwrun script should analyze a run. Do not use for QA strategy or test framework selection (route to qa-methodology), for frontend component or architecture design (route to frontend-engineering), or for Cloudflare/DDoS-GUARD challenge bypass (use flaresolverr).

High-fidelity ASCII/Braille rendering via the Risomorphism-1911 pipeline — edge-aware downsampling, presets, quality gates, and eikon mirror workflows

Expert skill for building LLM applications with LangChain — LCEL chains, RAG pipelines, agent orchestration, LangGraph integration, LangSmith observability, and production deployment via LangServe. Use when working with LangChain or comparing LLM application frameworks.

Build multi-agent AI systems with LangGraph — the low-level orchestration framework for stateful, graph-based agent workflows. Covers supervisor, swarm, and hierarchical multi-agent patterns; subgraph composition; state management (checkpointers/stores); persistence; evals; and production debugging. Reach for this when designing agent architectures that need cycles, conditional branching, parallel execution, or human-in-the-loop patterns.

Run PyTorch training across GPUs with minimal changes.

Build or refactor CLI tools designed for AI agent consumption: non-interactive, flag-driven, idempotent, with --json output and --dry-run preview. Use when creating a new script the agent will call, adding agent-friendly flags to an existing tool, or debugging why an agent keeps failing to use your CLI.

CLI for Forgejo API — issues, PRs, repos, labels, webhooks, Actions runners. Dual auth (AGENT/USER).

Operate, troubleshoot, secure, upgrade, and automate Kubernetes clusters and workloads safely across upstream Kubernetes, k3s, RKE2, MicroK8s, k0s, Talos, OpenShift/OKD, kind, Minikube, Rancher-managed clusters, EKS, AKS, and GKE. Use when a task involves kubectl, Kubernetes APIs, Pods, Deployments, StatefulSets, Services, Ingress or Gateway API, CRDs, RBAC, NetworkPolicy, storage, scheduling, autoscaling, cluster lifecycle, or the bundled agent-first k8s-cli.

Manage your Lidarr music library from the terminal. Search and browse artists and albums, add new artists, check calendars, view queue and download history, inspect quality and metadata profiles, and trigger searches. Use when the user mentions Lidarr, music management, adding an artist, searching for music, checking the music library, upcoming album releases, or download queue.

Manage Transistor.fm podcast hosting from the terminal: view shows, list episodes, check analytics, and get subscriber counts. Use when the user mentions Transistor, podcast hosting, podcast analytics, show management, or episode tracking.

Generate project ideas via creative constraints.

Manage Ghost CMS content from the terminal — create and list posts, pages, and tags, and fetch site info via the Ghost Admin API (v5/v6). Use when the user asks about ghost, cms, blog, blogging, posts, pages, tags, publishing, or site configuration.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Clinic-architecture-aligned iOS animation craft guidelines for SwiftUI (iOS 26 / Swift 6.2) covering motion tokens, spring physics, gesture continuity, spatial transitions, micro-interactions, and accessibility. Enforces @Equatable on animated views and keeps animation state aligned with Domain/Data feature boundaries. Use when writing, reviewing, or refactoring SwiftUI animation code under the clinic modular MVVM-C architecture.

Query your Jellyfin media server from the terminal — recently added movies and episodes, search across your library, browse libraries, and check server info and stats. Use when the user asks about Jellyfin, media server, movies, TV shows, recently added content, or their media library.

Manage your Prowlarr indexer hub from the terminal. List and inspect indexers, view query/grab statistics, check health, manage connected *arr applications and download clients, browse search history, and test indexer connectivity. Use when the user mentions Prowlarr, indexers, indexer management, testing indexers, search history, or the indexer hub.

Create C4 software-architecture diagrams using Mermaid or Structurizr. Use when teams need clear system context, container, component, or code-level views.

Search, download, and extract public-domain books from Project Gutenberg. Look up books by ID or keyword via gutendex, download plain-text and EPUB editions, strip licensing boilerplate, extract clean text from EPUB for illustrated works, and classify fiction vs non-fiction. Ships a portable CLI script with zero external dependencies. Use when the user says "gutenberg", "public domain", "download a book", "classic literature", "free ebook", "gutenberg.org", or names any public-domain title or author.

Systematic exploratory QA testing of web applications — find bugs, capture evidence, and generate structured reports

Gather fresh frontier signals for AI agent infrastructure, Vue, and Vite from live public feeds before producing summaries or strategic analysis.

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Production pipeline for interactive and generative visual art using p5.js. Creates browser-based sketches, generative art, data visualizations, interactive experiences, 3D scenes, audio-reactive visuals, and motion graphics — exported as HTML, PNG, GIF, MP4, or SVG. Covers: 2D/3D rendering, noise and particle systems, flow fields, shaders (GLSL), pixel manipulation, kinetic typography, WebGL scenes, audio analysis, mouse/keyboard interaction, and headless high-res export. Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.

Generate spectrograms and audio feature visualizations (mel, chroma, MFCC, tempogram, etc.) from audio files via CLI. Useful for audio analysis, music production debugging, and visual documentation.

CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

Search and retrieve academic papers from arXiv using their free REST API. No API key needed. Search by keyword, author, category, or ID. Combine with web_extract or the ocr-and-documents skill to read full paper content.

Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art, typographic flow around obstacles, text-as-geometry games, kinetic typography, and text-powered generative art. Produces single-file HTML demos by default.

Classify tasks by complexity and route heavy isolated coding work to Codex CLI with the correct current command syntax.

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

Generate ASCII art using pyfiglet (571 fonts), cowsay, boxes, toilet, image-to-ascii, remote APIs (asciified, ascii.co.uk), and LLM fallback. No API keys required.

Author/validate/export Google's DESIGN.md token spec files.

Control Philips Hue lights, rooms, and scenes via the OpenHue CLI. Turn lights on/off, adjust brightness, color, color temperature, and activate scenes.

Create hand-drawn style diagrams using Excalidraw JSON format. Generate .excalidraw files for architecture diagrams, flowcharts, sequence diagrams, concept maps, and more. Files can be opened at excalidraw.com or uploaded for shareable links.

Find nearby places (restaurants, cafes, bars, pharmacies, etc.) using OpenStreetMap. Works with coordinates, addresses, cities, zip codes, or Telegram location pins. No API keys needed.

Manage Linear issues, projects, and teams via the GraphQL API. Create, update, search, and organize issues. Uses API key auth (no OAuth needed). All operations via curl — no dependencies.

Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal.