Top Agent Skills

Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Hermes-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or red-team model robustness.

Production pipeline for ASCII art video — any format. Converts video/audio/images/generative input into colored ASCII character video output (MP4, GIF, image sequence). Covers: video-to-ASCII conversion, audio-reactive music visualizers, generative ASCII art animations, hybrid video+audio reactive, text/lyrics overlays, real-time terminal rendering. Use when users request: ASCII video, text art video, terminal-style video, character art animation, retro text visualization, audio visualizer in ASCII, converting video to ASCII art, matrix-style effects, or any animated ASCII output.

Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric/mathematical content.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Read, search, and create notes in the Obsidian vault.

Play Pokemon games autonomously via headless emulation. Starts a game server, reads structured game state from RAM, makes strategic decisions, and sends button inputs — all from the terminal.

Fetch YouTube video transcripts and transform them into structured content (chapters, summaries, threads, blog posts). Use when the user shares a YouTube URL or video link, asks to summarize a video, requests a transcript, or wants to extract and reformat content from any YouTube video.

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

Review code changes by analyzing git diffs, leaving inline comments on PRs, and performing thorough pre-push review. Works with gh CLI or falls back to git + GitHub REST API via curl.

Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes/plans/` directory, and do not execute the work.

Delegate coding tasks to OpenAI Codex CLI agent. Use for building features, refactoring, PR reviews, and batch issue fixing. Requires the codex CLI and a git repository.

Infographics: 21 layouts x 21 styles (信息图, 可视化).

Inspect and analyze codebases using pygount for LOC counting, language breakdown, and code-vs-comment ratios. Use when asked to check lines of code, repo size, language composition, or codebase stats.

Create and manage webhook subscriptions for event-driven agent activation. Use when the user wants external services to trigger agent runs automatically.

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration for Hermes. Uses Hermes-managed OAuth2 setup, prefers the Google Workspace CLI (`gws`) when available for broader API coverage, and falls back to the Python client libraries otherwise.

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated experiment monitoring, statistical analysis, iterative writing, and citation verification.

Use when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Use Alpaca CryptoDataStream websocket for real-time crypto bars in live trading (OHLC only, volume excluded)

Example skill demonstrating the registry structure and format

Diagnosing and fixing bimodal matching score distributions in MaxFuse

Integrates Mem0 Platform SDK for persistent memory in AI applications. Use when building agents or chatbots that need to remember user preferences, past interactions, or personalized context across sessions. Covers Python and TypeScript SDKs, plus LangChain, CrewAI, OpenAI Agents, LlamaIndex, AutoGen, and LangGraph integrations.

Bagman

Helps users discover and install agent skills from the open ecosystem. Use when the user asks "how do I do X", "find a skill for X", "is there a skill that can...", or expresses interest in extending Claude's capabilities with a new skill or tool.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Design game audio systems including music, sound effects, ambient soundscapes, adaptive audio, and audio implementation strategy. Use when planning the sonic identity of a game. Also trigger for "game music", "sound effects", "game audio", "soundtrack", "SFX design", "ambient sound", or "adaptive music".

Brainstorm and develop game concepts, exploring genres, themes, target audiences, and unique selling points. Use when starting a new game project from scratch or pivoting an existing idea. Also trigger for "game idea", "what kind of game", "I want to make a game", "game pitch", or "explore game concepts".

Design game user interfaces and user experience flows including HUD, menus, inventory screens, accessibility, and player feedback systems. Use when designing how the player interacts with game systems visually. Also trigger for "game UI", "game UX", "HUD design", "menu design", "inventory UI", "game accessibility", or "game interface".

Define the visual identity of a game including art style, color palettes, character design language, environment aesthetics, and asset pipelines. Use when establishing the look and feel of a game project. Also trigger for "art style", "visual style", "game aesthetics", "color palette", "character art", "pixel art", or "game graphics".

Design telemetry systems, define KPIs, analyze player behavior data, and set up dashboards for data-driven game design decisions. Use when instrumenting a game for analytics or interpreting player data. Also trigger for "game telemetry", "player analytics", "game metrics", "KPIs", "player retention", "funnel analysis", or "player behavior".

Balance game systems including difficulty curves, stat tuning, economy rates, matchmaking fairness, and player power progression. Use when tuning numbers and systems for fair, engaging gameplay. Also trigger for "game balance", "difficulty tuning", "stat balancing", "nerf", "buff", "power curve", or "difficulty curve".

A technical writer who crafts clear, comprehensive documentation. Specializes in README files, API docs, architecture docs, and user guides.

Autonomously runs iterative experiment loops to optimize code against a measurable metric. Use when the user wants to improve execution time, memory usage, test pass rate, or any numeric performance goal across repeated experiments — NOT for one-shot bug fixes or simple code review.

Build reproducible ML experiment plans with hypotheses, metrics, and ablations. Use when: (1) planning experiments, (2) comparing variants, (3) defining acceptance thresholds. NOT for: long-running experiment execution.

Design and evaluate A/B tests with power, sample size, and robust metric interpretation. Use when: (1) planning controlled experiments, (2) reading p-values/effects, (3) sequential testing safeguards. NOT for: dark-pattern optimization.

Create a Product Requirements Document using a comprehensive 8-section template covering problem, objectives, segments, value propositions, solution, and release planning. Use when writing a PRD, documenting product requirements, preparing a feature spec, or reviewing an existing PRD.

Create job stories using the 'When [situation], I want to [motivation], so I can [outcome]' format with detailed acceptance criteria. Use when writing job stories, creating JTBD-style backlog items, or expressing user situations and motivations.

Create user stories following the 3 C's (Card, Conversation, Confirmation) and INVEST criteria with descriptions, design links, and acceptance criteria. Use when writing user stories, breaking down features into backlog items, or defining acceptance criteria.

Generate an Ansoff Matrix analysis mapping growth strategies across market penetration, market development, product development, and diversification. Use when considering growth options, planning market expansion, or evaluating strategic growth paths.

Perform a detailed SWOT analysis — strengths, weaknesses, opportunities, and threats with actionable recommendations. Use when doing strategic assessment, competitive analysis, or evaluating a product or business position.

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

Identify 3-5 potential customer segments with demographics, JTBD, and product fit analysis. Use when exploring market segments, identifying target audiences, evaluating new markets, or learning how to segment a market.

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.

Dense, machine-readable API reference for PyFixest — high-dimensional fixed-effects OLS/WLS/IV and Poisson (feols, fepois, feglm), clustered/robust standard errors, R-style formula syntax, and post-estimation. Use when writing or debugging Python fixed-effects regressions with the pyfixest package.

Generate, continue, revise, polish, and stress-test game theory research papers. Use when the user provides a game theory topic, phenomenon, draft, outline, model idea, literature anchor, reviewer comments, or asks for 博弈论论文生成, 选题建模, 文献迁移, 模型修正, 均衡分析, 数值模拟, 论文润色, 改稿打磨, or R&R response work.

VS-Enhanced Qualitative Design Consultant with Ethnography & Action Research Enhanced VS 3-Phase process: Avoids overused phenomenology, proposes context-optimal qualitative strategies Absorbed H1 (Ethnographic Research Advisor) and H2 (Action Research Facilitator) capabilities Use when: selecting qualitative research design, planning phenomenology/grounded theory/case study/ethnography/action research Triggers: phenomenology, 현상학, grounded theory, 근거이론, case study, 사례연구, narrative inquiry, ethnography, 민족지, action research, 실행연구, qualitative design

VS-Enhanced Academic Style Humanizer - Transforms writing patterns to achieve authentic scholarly voice Applies transformations from G5 analysis to create natural academic prose Use when: improving AI-assisted writing quality, preparing manuscripts, enhancing scholarly voice Triggers: humanize, transform, make natural, improve writing quality, improve style

Use when writing Python code for DSGE models, HANK models, numerical economic computation, causal inference, or quantitative economic data analysis

Universal LaTeX document skill: create, compile, and convert any document to professional PDF with PNG previews. Supports resumes, reports, cover letters, invoices, academic papers, theses/dissertations, academic CVs, presentations (Beamer), scientific posters, formal letters, exams/quizzes, books, cheat sheets, reference cards, exam formula sheets, fillable PDF forms (hyperref form fields), conditional content (etoolbox toggles), mail merge from CSV/JSON (Jinja2 templates), version diffing (latexdiff), charts (pgfplots + matplotlib), tables (booktabs + CSV import), images (TikZ), Mermaid diagrams, AI-generated images, watermarks, landscape pages, bibliography/citations (BibTeX/biblatex), multi-language/CJK (auto XeLaTeX), algorithms/pseudocode, colored boxes (tcolorbox), SI units (siunitx), Pandoc format conversion (Markdown/DOCX/HTML ↔ LaTeX), and PDF-to-LaTeX conversion of handwritten or printed documents (math, business, legal, general). Compile script supports pdflatex, xelatex, lualatex with auto-detect

System diagnostics and health checks for Diverga plugin. OpenClaw-style Check-Report-Fix pattern with 5-layer diagnostics. Triggers: /diverga:doctor, diverga doctor, system check, diagnose, 진단

Use when the user asks about academic literature, research papers, scholarly works, authors, citations, institutions, journals, or any academic metadata. Trigger when users want to search for papers, find author profiles, track citations, discover related works, or explore academic topics. Also use when users mention DOIs, ORCIDs, h-index, publication venues, or research metrics.

Tail, read, or search a Stata log file from a previous command or background task.