AI & ML

machina-sports Bundle

Construct and scaffold Machina agent-templates and connectors with correct YAML structure, then install them via MCP. Use when users ask to "create a template", "scaffold an agent", "init template", "build a new connector", "install template", "validate template", "analyze template", "trace agent", or "configure secrets".

mdhamoda Bundle

Administer MCP servers inside a Salesforce org — list standard MCP servers and their activation state, activate/deactivate them, register custom and external MCP servers, and pick the right MCP surface for a task. TRIGGER when the user says 'MCP server', 'activate MCP', 'standard MCP', 'headless-360', 'sobject-all', 'MCP servers in the org', asks which MCP tools an agent can reach, or asks to turn an org MCP server on/off. DO NOT TRIGGER for the local Salesforce DX MCP Server (@salesforce/mcp dev tooling), for rendering an Apex-invocable MCP tool's output (use platform-mcp-tool-widget-coordinate), or for agent/subagent authoring (use agentforce-generate).

merttcetn Bundle

Offload implementation, research, review, and parallel work to Cursor CLI subagents running cursor-grok-4.6-high-fast while keeping coordination in the current Codex session. Use when the user invokes $grok-subagent, Codex would otherwise spawn its own subagents, run a long coding/research pass, or the user mentions Cursor subagent, grok 4.6, grok 4.6 high fast, offload to Cursor, or saving Codex limit/quota. Do not use for tiny one-shot edits already in context, git commit/push, or when the user invoked $cursor-subagent-3rd, or requested a non-Grok model through Cursor.

merttcetn Bundle

Delegate tasks to user-selected third-party models through Cursor CLI, including GPT Sol/Terra/Luna, Claude Opus/Sonnet/Fable, Gemini, and other models available in the user's Cursor account. Use when the user invokes cursor-subagent-3rd or asks for Cursor agents with a non-Grok model, including Turkish requests such as 'Bu taskı cursor-subagent-3rd ile gpt sol agentları ile yap'. Grok delegation belongs to grok-subagent.

moorcheh-ai Bundle

Use this skill to interact with Moorcheh, the Universal Memory Layer for Agentic AI. Provides semantic search with ITS (Information-Theoretic Scoring), namespace management, text and vector data operations, and AI-powered answer generation (RAG). Use when building applications that need semantic search, knowledge bases, document Q&A, AI memory systems, or retrieval-augmented generation.

nicknisi Skill

Execute an implementation spec generated by ideation. Invokes scout agent for codebase exploration, builds components with feedback loops, then runs a verify-review-fix cycle with the reviewer agent before committing.

nig-sc Skill

How to run jobs on the NIG supercomputer (DDBJ / National Institute of Genetics, Japan) PERSONAL GENOME ANALYSIS zone — the security-hardened, NBDC-compliant division for controlled-access human (personal) genome data. Use this whenever the user works with individual human genotype/genome data on NIG/DDBJ, mentions the "個人ゲノム解析区画", SSL-VPN / FortiClient login to DDBJ, a `-pg` account, GPU genome analysis with Parabricks, or the L40S GPU nodes (`--partition=l40s`). This zone is a PHYSICALLY SEPARATE network from the general analysis zone: different login path (SSL-VPN), different accounts, different SLURM/partitions, node-lease model, and no shared public-DB layout. For open, non-personal-genome work use nig-general-analysis instead. Like that zone it uses `/usr/local/biotools` apptainer images for tools; the differences are access, scheduling, GPUs, and data handling.

noahseger Bundle

Use to model a system's behavior as domain events, extract an event model from existing code, design event-driven architectures, or document workflows as timelines of commands, events, and state views

null-inc Skill

Preserve the project's working memory for the next agent.

octoparse Bundle

Connect and authorize the Octoparse MCP server. Use when Octoparse tools are missing or unavailable, when a call fails with an authorization or 401/403 error, when the user asks to set up or reconnect Octoparse, or when another Octoparse skill cannot reach the service.

octoparse Bundle

Octoparse's web data collection, driven by an agent. Scrape business listings, leads, contacts, e-commerce products and prices, reviews, job postings, real-estate and travel listings, social media, directories, and search results across Google Maps, Google Search, Amazon, Temu, TikTok Shop, LinkedIn, Indeed, Yellow Pages, Zillow, Booking, and hundreds of regional sites in 8 languages. Also runs and exports the tasks a user already configured in their own Octoparse account. Use for lead generation, price monitoring, review analysis, competitor tracking, recruitment research, market research, re-running or exporting an existing Octoparse task, or any request to scrape, crawl, collect, or extract structured data from a website.

pipelex Skill

Automates the mthds-form release workflow: bumps the version in package.json, renames the CHANGELOG.md `[Unreleased]` section into a version heading, runs the full gate (checks, tests, build, and the bundle assertions), creates a `release/vX.Y.Z` branch, commits, pushes, and opens a PR to `main` — merging that PR is what publishes `@pipelex/mthds-form` to npm. Use whenever the user says "release", "cut a release", "bump the version", "prepare a release", "make a release", "ship it", "publish to npm", "create a release branch", or any variation of shipping a new version of this package, even if they do not name the package. The user can pass changelog content inline (e.g. "/release added a presentation seam on the controls"), which becomes the entry for this version.

pipelex Skill

Move this package's `mthds` floor — the types-only peer that supplies the MTHDS protocol wire types through `mthds/protocol` — to the latest version published on npm, or to a version the user names. It edits both sites (`peerDependencies` and `devDependencies`), refreshes `package-lock.json`, runs the gate, and records the change under `## [Unreleased]`. Use whenever the user says "bump mthds", "bump the mthds peer", "bump the mthds version", "update mthds", "mthds to latest", "raise the mthds floor", "adopt the new protocol types", "the peer is capped at 0.x", or any variation of moving this repo's upstream MTHDS dependency — including when they only say "bump the dependency" while talking about the protocol surface. This is NOT the package's own release version: for "cut a release", "publish", or "bump the version" meaning `@pipelex/mthds-form` itself, use the `release` skill instead.

quint-co Bundle

Quint language and CLI reference — the expert on Quint syntax, operators, types, `basicSpells`, the toolchain (typecheck/run/test/verify), and how to read simulation and counterexample output. Use when writing or debugging Quint (`.qnt`) files, fixing a typecheck/parse error, looking up an operator or idiom, analyzing an invariant violation or counterexample trace, or optimizing state-space exploration. For building a new model end-to-end from some source (including translating TLA+, or modeling code/requirements/an idea), use quint-modeling instead — it consults this reference for syntax as needed.

quint-co Bundle

Build a Quint model of a system, protocol, or algorithm. Use whenever the user wants to model, spec out, formally describe, model-check, or verify a system in Quint — e.g. "model this protocol in Quint", "spec out this design", "translate this TLA+", "formally check this Rust code" — even if they never say "specification." If the goal is to verify or model-check a design and no Quint model exists yet, writing it is the required first step, so start here. It generates the spec from whatever the user has — an idea, requirements, source code (Rust, Go, TypeScript, etc.), or an existing TLA+ spec — and walks the modelling flow (state, actions, invariants), adapting to the source. Also use this to **review or audit an existing Quint spec** — "review my .qnt", "is this model any good" — it carries the review checklist. For pure Quint syntax/CLI/debugging questions with no new model to build, use quint-lang instead.

iamlukethedev Bundle

Capture actionable user requests as persistent tasks, update task status as work progresses, and keep a shared task store in sync. Use when a user asks an agent to do work, check progress, block a task, complete a task, or manage the Kanban board.

not-compromised Skill

Open and control apps in an on-demand Hyprland desktop for browser and GUI tasks, with screenshots and input kept separate from the user's desktop.

nuanu-ai Bundle

Use for MagicPay payments, funding, Memory, agent email, account readiness, optional choices and human input, or payment recovery through remote MCP.

povvo Bundle

Use when Codex must apply Instrumented Monochrome to create, review, repair, or generate Web MCP identity, editorial, interface, motion, data, or visual-brand artifacts; do not infer product behavior or architecture from the Web MCP name.

pwrdrvr Bundle

Regression test the OpenClaw Codex App Server plugin against a live local OpenClaw instance in Telegram or Discord. Use when the user wants an end-to-end OCAS manual test pass, wants to verify binding, `/cas_resume` or `/cas_status` flags for model/fast/yolo, approvals, plan mode, review, compact, status-card controls, split default-vs-full-access permission behavior, stop-button interrupt handling, rename, or other slash-command behavior, or wants reproducible bug notes from a live chat integration run.

0x0funky Bundle

Generate and revise production-oriented 2D game maps with built-in image generation as the default visual asset source, choosing a visual model, runtime object model, collision model, art direction, and engine/export target. Use when Codex needs to create or integrate RPG maps, monster-taming maps, tactical arenas, battle backgrounds, side-scroller/parallax scenes, tilemaps, layered raster maps, clean HD hand-painted maps, pixel-inspired maps, prop packs, collision zones, walkable areas, or map previews.

elradarnocturno Skill

Use this skill when building applications with Gemini API hosted models, including Gemini and Gemma 4, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage (google-genai for Python, @google/genai for JavaScript/TypeScript, com.google.genai:google-genai for Java, google.golang.org/genai for Go), model selection, and API capabilities.

coder Skill

Sub-agent powered code reviews spanning correctness, tests, consistency, and fit

decocms Skill

Use when the user asks to update their MCP App to the latest template version, sync with upstream template, pull in template changes, upgrade the template, or migrate to a newer version of the MCP App template.

lstm-kirigaya Bundle

Skill Market 上传助手（给 AI Agent 用）

nwiizo Skill

Spawn a parallel coding-agent session in its own jj workspace using `jj_agent`. Use when starting a second (or Nth) agent on a different task without disturbing the current working copy. Invoke manually; creates a workspace directory on disk.

scylladb Bundle

Guides the design and structuring of AI agent skills for the Argus repository with multi-step phases, progressive disclosure, and dual-platform compatibility (GitHub Copilot and Claude Code / OpenCode). Use when creating new skills, reviewing existing skills, restructuring AI guidance into modular skill directories, editing SKILL.md files, or improving agent instructions.

solo-agent Bundle

Run the real fixed PM arithmetic case and retain submission evidence.

srombauts Skill

Default response behavior for AI coding agents: professional, factual, neutral tone with calibrated critical evaluation. Baseline for every task — implementation, code review, debugging, planning, research, evaluation, Q&A.

tzachbon Bundle

Use when the user wants to turn an idea, a notes dump, or a session transcript into a complete agent-ready local project, or to fold new input into a project that already exists. Triggers include "turn this into a project", "scaffold a project from this", "make a project out of this session/these notes", "set up a new repo for this", "extend an existing project with this", "add this to my project", "continue the project from these notes".

y-a-v-a Bundle

Cross-model code review with OpenAI Codex. A different model reviews the diff, findings are triaged by severity, and contested findings are reconciled with Codex before you act — so Claude-authored changes get reviewed without self-review bias.

yologdev Skill

Read and ingest into yopedia — a cited, agent-maintained wiki — over the remote MCP endpoint. Use it to save URLs/notes into your own yopedia content and to query the wiki for cited answers.

younes-io Bundle

Write and iteratively refine executable TLA+ specs (.tla) and TLC model configs (.cfg) from natural-language system designs; run TLC model checking; summarize pass/fail and counterexamples with explicit assumptions and bounds. Use when asked to design or validate a protocol/state machine, create or edit .tla/.cfg files, run TLC, or interpret TLC failures.

strandic Skill

Step-gated method for building one medium, structural feature with an agent, without slop — you clear every gate; the agent never self-certifies a step.

xvirobotics Skill

The meta-skill: create AI agent teams, individual agents, or custom skills for any project. Use when the user wants to generate a complete agent team, create a single agent, or create a single skill for Claude Code, Kimi, or Codex.

akiojin Skill

Unity Asset Management