AI & ML

argentaios Bundle

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

argentaios Skill

Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

argentaios Bundle

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

argentaios Bundle

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.

argentaios Bundle

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

argentaios Bundle

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.

argentaios Bundle

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

argentaios Bundle

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

argentaios Bundle

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.

s3yed Skill

Use fal.ai for pay-per-use image, video, voice, and generative-media model workflows in Weblyfe content production.

s3yed Skill

Drive the macOS desktop in the background — screenshots, mouse, keyboard, scroll, drag — without stealing the user's cursor, keyboard focus, or Space. Works with any tool-capable model. Load this skill whenever the `computer_use` tool is available.

s3yed Bundle

Run Ralph Wiggum autonomous coding loops where each fresh agent iteration implements, verifies, commits, and records one task.

s3yed Skill

Port OpenClaw Appie to Hermes Agent and spawn new client or internal instances. Clone appie-brain, configure identity files (SOUL.md, USER.md, IDENTITY.md, AGENTS.md), set up git sync, copy secrets, configure beta WhatsApp/wacli access, and start Hermes gateway.

s3yed Skill

Build qualification/delivery Typeforms for coaching funnels. Covers country/profession gates, logic jumps, thankyou screen refs, and embedding in landing pages.

s3yed Skill

Operate Hermes Kanban multi-agent boards as an orchestrator or worker: decompose work, route tasks, follow worker lifecycle, manage dependencies, heartbeat, block/unblock, recover stuck workers, and summarize results. Use for any Hermes Kanban collaboration workflow.

s3yed Skill

rtk (Rust Token Killer) — CLI proxy that filters/compresses command output before it reaches the LLM, cutting tokens 60-90% on ls/cat/grep/git/tests/etc. Token-discipline tool. Prefix heavy read/inspect commands with `rtk`.

s3yed Skill

Operate Hermes-style agent fleets across machines: provision remote hosts, validate transport/auth, refresh knowledge packs, and recover provider or gateway runtime failures.

s3yed Skill

Guard-rail for debugging launchd cron failures caused by env isolation. Use when a launchd job works interactively but fails headless (missing keys, no TTY, MCP hangs).

s3yed Skill

Author in-repo SKILL.md: frontmatter, validator, structure.

s3yed Skill

Umbrella workflow for delegating coding work to local agent CLIs such as Claude Code, Codex, and OpenCode.

fabioc-aloha Bundle

Notion-as-source-of-truth dispatch board for running your work like an AI agency. One Tasks database is the source of truth; tasks flow Suggestion through Discussion, To-Do, In Progress, and Done with subtasks, recurring cadences, dependencies, and template subtrees. Batch execution fans approved To-Do rows out to parallel agents with per-task model selection. Use when capturing chat to Notion, running the To-Do queue, suggesting, approving, or discussing tasks, or coordinating multi-task batches. Trigger with "/agency-os" subcommands or natural-language variants ("add a suggestion: …", "let's discuss X", "run the queue").

fabioc-aloha Bundle

Use when a Head of People Ops, BizOps lead, or Internal Communications owner needs to draft and sequence an internal-only change-management communication — a re-org announcement, a tool rollout, a policy change, a benefit change, a leadership transition, a layoff, an acquisition close, or an internal product launch — and the audience is employees (not customers). Triggers on "all-hands announcement", "town-hall script", "change comms", "internal newsletter", "rollout comms", "policy change announcement", "re-org announcement", "internal FAQ", "manager talking points", "Prosci ADKAR", "Kotter 8-step", "layoff comms", "RIF comms", "internal memo". Pairs Prosci ADKAR (Awareness / Desire / Knowledge / Ability / Reinforcement) and Kotter's 8-step change model with deterministic stdlib-only Python tools to produce a sequenced touchpoint calendar, a Kotter-compliant primary announcement, an audience-segmented FAQ, and manager cascade talking points. Industry-tuned via --profile {tech-startup, scaleup, enterprise, pu

fabioc-aloha Skill

Generate branded SVG banners for documents (READMEs, plans, changelogs, release artifacts) using a configurable Node.js muscle. Covers watermark selection, subtitle craft, and embedding. Requires the generate-banner.cjs muscle from Alex_ACT_Edition.

fabioc-aloha Bundle

Render data dashboards as static SVG panels embeddable in Markdown. Uses D3.js v7 mental model for scales, shapes, and axes. No runtime JS; output is pure SVG with inline styles for GitHub compatibility.

fabioc-aloha Bundle

Render data dashboards as pure ASCII art in monospace text -- the cheapest, most portable delivery method. No rendering engine, no SVG, no browser. LLM-native output with predictable character geometry.

aipoch Bundle

Healthcare AI toolkit for clinical ML. EHR processing, clinical prediction (mortality, readmission, drug recommendation), medical coding (ICD/NDC/ATC), signals (EEG/ECG), datasets (MIMIC-III/IV, eICU, OMOP), and healthcare deep learning (RETAIN, SafeDrug, Transformer, GNN) via...

aipoch Bundle

Statistical modeling and regression analysis for biomedical data. Linear/logistic/ordinal regression, Cox proportional hazards, mixed-effects models, ANOVA, with odds ratios, hazard ratios, confidence intervals, and model diagnostics.

aipoch Bundle

Conduct comprehensive literature research with target disambiguation, evidence grading, and structured theme extraction. Creates a detailed report with mandatory completeness checklist, biological model synthesis, and testable hypotheses. For biological targets, resolves offic...

aiescu Bundle

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.

aiescu Bundle

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

aiescu Bundle

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

aiescu Bundle

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

coupler-io Skill

Use this skill when the user wants to explore a dataset's context, or write or update documentation for the data it holds. Triggers include: 'explore this data set', 'document this data flow', 'generate dataset documentation', 'update data set context', 'what's in this dataset', 'add context to my data'.

ngxtm-devkit Bundle

Use when querying Jira issues, searching Confluence pages, creating tickets, updating documentation, or integrating Atlassian tools via MCP protocol.

ngxtm-devkit Bundle

Use when building MCP servers or clients that connect AI systems with external tools and data sources. Invoke for MCP protocol compliance, TypeScript/Python SDKs, resource providers, tool functions.

ngxtm-devkit Bundle

World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.