AI & ML

mbackschat Bundle

Author and validate A12 Kernel document models with the dmtool CLI — both a model's structure (fields, groups, type definitions, includes, config) and its validation rules. Use when a user (often a document modeller or business analyst) wants to create, edit, check, or understand an A12 document model — add or change fields and groups, factor out reusable includes, refactor structure, or author validation rules on it. Covers model creation, the structure edits and refactors (extract/move/rename), the rule envelope and error-scenario polarity, field-path references, per-row iteration, and the explore→compose→check loop.

mbenhard Skill

Compare agent-made alternatives in a local browser preview with Unship. Use for comparison setup, iteration, Canvas, selection, cleanup, and Unship installation or update troubleshooting.

meharajm Skill

Run deterministic, evidence-backed QA on a physical iOS device using WebDriverAgent. Use when validating app behavior, device-specific flows, or real-user journeys that cannot be proven in a simulator.

michellema8890 Bundle

Convert PDF to Word or PDF to DOCX while preserving the original page layout and keeping text editable, searchable, and selectable. Use for PDF-to-Word conversion, editable DOCX creation, fixed-layout documents, table-heavy PDFs, vertical text, resumable long-document conversion, or output validation. Works as a portable Agent Skill for Codex, Claude Code, and other agents that can run the CLI. Do not use for scanned PDFs without a text layer unless OCR is available.

mikkelkrogsholm Bundle

Build type-safe CLIs with Bun. Use when: (1) Creating a new CLI application with Bun, (2) Adding commands with defineCommand/option(), (3) Building a plugin system, (4) Using prompt/spinner APIs for interactive CLIs, (5) Building TUI components, (6) Publishing CLI to npm. For advanced TUI (custom components, animations, full layout control), use the 'opentui' skill. Covers: defineCommand, option() APIs, plugin architecture, bunli CLI commands (dev/build/generate/test/release/init/doctor), create-bunli scaffolding, and utilities.

mikkelkrogsholm Bundle

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

moda-design Skill

READ THIS BEFORE calling any Moda MCP tool. Recommended whenever the Moda MCP server is connected or the user mentions Moda, moda.app, a moda.app/s/ share link, or wants to create, edit, remix, or export a canvas (slide deck, social post, Instagram or LinkedIn carousel, PDF report, diagram, UI mockup), or turn a Moda canvas into code.

moonbitlang Bundle

Guide for writing, refactoring, and testing MoonBit projects, including exclusive use of `.mbtx` for agent-authored automation. Use when working in MoonBit modules or packages, organizing MoonBit files, using moon tooling (build/check/run/test/doc/ide etc.), or following MoonBit-specific layout, scripting, documentation, and testing conventions.

ethan-hang Skill

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.

family3253 Bundle

Interactive model selection workflow with paginated navigation. Use when users want to select a model interactively - guides them through provider selection then model selection using the question tool with pagination support for large lists.

fastclaw-ai Skill

Run this BEFORE any package install (pip / npm / apt / brew / cargo / gem / go install) you would otherwise execute via the exec tool — including when the user asks for a deliverable that needs third-party libraries (PDF generation, image processing, scrapers, dashboards, charts, OCR, audio/video, …). It searches the open agent-skill ecosystem (skills.sh) for an installable skill that already does the job; only fall back to direct package install if find-skills returns no credible match. Also covers explicit "find a skill for X" / "how do I do X" / "is there a skill that can..." requests, and any time the user expresses interest in extending agent capabilities.

fastclaw-ai Bundle

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

fathah Skill

Expert in building self-improving AI agents with tool use, multi-platform messaging, and a closed learning loop. Proficient in LLM orchestration, tool integration, session management, and agent autonomy.

francyjglisboa Bundle

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill, audit this skill, is this skill safe, vet a skill before installing, what does this skill access. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, spec validation, and security auditing of third-party skills before install.

frane Skill

Agent-native headless browser. 26 primitives over a Unix-socket wire protocol. Real WKWebView (macOS), WebKitGTK 6 (Linux), or WebView2 (Windows) — all three engines verified per-commit by a real-browser integration suite. Optimistic concurrency via state tokens; tree-delta wire format; durable session/page/auth state in SQLite.

fxjim Bundle

Inspect and buy the Agent Commerce Guard 1 USDC Base launch pass through an authorized Base MCP wallet, x402 client, or browser wallet. Use when a user wants to evaluate the offer, confirm payment details, purchase the package, verify a Base transaction, or unlock the paid download. Require explicit approval before any payment and never request wallet secrets.

fxjim Bundle

Evaluate non-sensitive AI-agent commerce action manifests with the free Agent Commerce Guard hosted policy endpoint. Use when a user wants to preflight wallet spend, paid API calls, deployments, token launches, marketplace jobs, social actions, destructive commands, billing changes, or credential access before execution. Never send secrets, private source, customer data, or credentials to the hosted demo.

gabriel-f-santos Bundle

Scan agent skills for security issues. Use when asked to "scan a skill", "audit a skill", "review skill security", "check skill for injection", "validate SKILL.md", or assess whether an agent skill is safe to install. Checks for prompt injection, malicious scripts, excessive permissions, secret exposure, and supply chain risks.

gannonh Bundle

Configure P-Stack for Pi, Codex, Cursor, OpenCode, and Claude Code. Use when installing P-Stack, choosing its small, medium, and large models, setting reasoning levels, adding harness adapters, or refreshing model identifiers.

ghosttypes Bundle

Interactive sub-agent creation skill for Claude Code. Use when user wants to create a custom subagent or mentions needing a specialized agent for specific tasks. This skill guides the entire subagent creation process including identifier design, system prompt generation, skill/context selection, and writing properly formatted agent files to .claude/agents.

gigio1023 Bundle

Use when drafting or revising Korean agent responses or artifacts where compression has omitted or blurred sentence components, particles, endings, predicates, logical relations, referents, or ordinary technical wording; or when the user asks to make Korean meaning clearer without changing facts. Restores semantic completeness without padding or invented context. NOT for translation, grammar- or spelling-only proofreading, AI-authorship detection, document structure, evidence, or voice problems without a Korean clarity defect, or changing code, identifiers, commands, quotations, and established product terms.

gigio1023 Bundle

Use for writing or revising documents in English, Korean, Italian, or Chinese when the work must prevent or remove AI slop while preserving meaning, evidence boundaries, reader context, and the writer's voice. Covers humanizing or deslop requests ("AI 티 빼줘"), formulaic or generic model-assisted drafts, session-dependent documents, terminology review, and slop-aware authoring of README, guides, specs, ADRs, memos, and posts. Also handles intra-Chinese locale or script normalization. NOT for grammar- or spelling-only proofreading, translation between languages, Python docstrings, prompt coaching, diagrams, PR/commit/issue copy, or implementation changes.

gitagenthq Skill

Build a stripped git-agent binary via scripts/build.sh, optionally embedding the free shared-gateway URL. Use for manual testing or pre-release verification.

glassflow Bundle

Installs Tares, the open-source platform for always-on AI agents, starts the daemon, adds a first source over the HTTP API, connects the agent it runs inside over MCP, and proves the connection with one read. Use when the user asks an agent to install or set up Tares, add a source, connect Claude Code, Codex or Cursor to Tares, or fix a local Tares install.

glassflow Skill

Use when you need cross-source context about this project's systems (recent deploys, logs, metrics, entities, correlated timelines), OR when organizing Tares itself — creating sources, labels, and views. Tares is the data plane; read it via the tares MCP tools for one correlated timeline per entity, and author its catalog with the create/derive tools following the rules below.

graphlit Skill

Use when the user wants an AI agent to answer questions or perform research from an already-synced Vault folder using local Markdown files and normal filesystem tools.

graphlit Bundle

Use when the user wants to install Vault Sync, connect an existing Vault Git repository to a local folder, refresh it, configure a recurring pull schedule, or make a local Vault available to an AI agent through filesystem files.

gu-dsan6725 Skill

Perform exploratory data analysis on a dataset. Use when asked to explore, profile, or analyze data.

gu-dsan6725 Skill

Evaluate a trained ML model and generate a performance report. Use when asked to evaluate, assess, or report on model performance.

haowjy Bundle

Agent execution engine that composes prompts, routes models, and writes run artifacts. Use when launching subagent runs.

haowjy Bundle

Multi-model supervisor that discovers skills, picks models, and composes runs. Use when executing multi-step plans across multiple models.

hongmaple0820 Bundle

Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research, due diligence. Takes 2-10 minutes but produces detailed, cited reports. Costs $2-5 per task.

hypawave Bundle

Give an AI agent an address on Hypawave — private agent-to-agent messaging (waves), free private file handoffs, and buying or selling files, APIs, data, or compute over Bitcoin Lightning, non-custodial, with a verified Lightning preimage as the proof that releases a paid result. Use when an operator wants to connect their agent with another person's agent, share the agent's contact card, send or receive a file agent-to-agent, pay another agent or service and retrieve the result, sell the agent's own files, API, data, or compute for Bitcoin, or search and list offers in the public directory — all with no account. Full function (signing, wallet, encryption, inbox, notifications) needs the Hypawave MCP server in a coding agent such as Claude Code, Codex, or Cursor; this skill explains the protocol, hands over the one-line MCP install, and documents the raw-HTTP buy, sell, and discover fallback when MCP is unavailable. Chat-only sessions can explain and point to the install, not transact.

imbhargav5 Bundle

Use when working with bind arguments, metadata schemas, framework errors (redirect/notFound/forbidden/unauthorized), type inference utilities (InferSafeActionFnInput/Result), or server-level action callbacks

zenon-red Bundle

Generate TTS audio, upload to object storage, and return public audio URLs through MCP.

zhizhunbao Bundle

English code comment standards for Python and TypeScript. Use when (1) adding comments to code, (2) standardizing comment format, (3) TypeScript/TSX file header comments, (4) Python module docstrings