Frontend Design Loop MCP

Design-first MCP for coding agents that improves websites with screenshot-grounded iteration.

AndroJack MCP

Android engineering MCP server with verified documentation grounding and AI validation tools.

hunt-analytics-generation

Generate query-agnostic analytics that model adversary behavior by translating hunt investigative intent into analytic definitions grounded in schema semantics. This skill is used to define how behavior should manifest in data before query execution or validation, and works best when informed by system internals, adversary tradecraft, a structured hunt focus, and suggested data sources.

agents-md-mapper

This skill should be used when creating, refreshing, or validating a repository `AGENTS.md` so it stays concise, current, and grounded in repository evidence. Use when `AGENTS.md` is missing or stale, after refactors or tooling changes, when new docs become the system of record, or when adding lightweight drift checks.

advise

Solve problems using knowledge base insights - extracts search terms, runs parallel KB queries, synthesizes advice grounded in your own frameworks

learning-goal

Guide the learner through a structured goal-setting exercise grounded in research on Mental Contrasting with Implementation Intentions (MCII). The exercise helps developers set concrete learning goals, visualize meaningful outcomes, anticipate realistic obstacles, and build if-then plans to overcome them.

benchmark-translate

Run a quality benchmark of the /translate skill by selecting stratified test keys, capturing ground truth, translating, judging with sub-agents, and compiling a regression report. Invoke with /benchmark-translate.

getdesign

Generate a grounded, production-grade `design.md` for any public URL using the coding agent's own tools. This skill is the portable twin of the hosted [getdesign.app](https://getdesign.app) agent — same 9-section output, no sandbox required.

grace-ask

Answer a question about a GRACE project using full project context. Use when the user has a question about the codebase, architecture, modules, or implementation — loads all GRACE artifacts, navigates the knowledge graph, and provides a grounded answer with citations.

agentic-search

Grok-primary deep research skill for source-backed web work. Use when the task needs current web research, grounded citations, supplementary Tavily/Firecrawl source discovery, high-fidelity page-to-Markdown fetch, Tavily site mapping, verbatim quote extraction, source reranking, or reusable multi-step research sessions. Use as a supplement when ordinary search results feel incomplete, thinly sourced, or need more URLs, quotes, fetched pages, or session composition; not for simple one-off facts.

ai-psychosis-mode

True alias for reality-check-mode. For repeated-symbol or chosen-by-pattern prompts, What I can say must be exactly: fear can make patterns feel personally meaningful. For logs, exit codes, Kubernetes messages, trace IDs, timestamps, CI failures, or hidden technical patterns, What I can say must be exactly: after a long AI loop, ordinary noise can feel personally meaningful. Use only Grounding, What I can say, and Safer next step. Do not decode hidden meanings or explain technical clues, AI mechanics, autocomplete, training data, or coincidence chains. Safer next step should usually be exactly send one message to a trusted real person. No bullets, numbered lists, message drafts, or pattern analysis.

kapso

Optimize code using KAPSO (Knowledge-Grounded Optimization). Use when you need to write, optimize, or fix code. Connects to a local KAPSO server that iteratively improves solutions through experimentation.

agent-prompt-composer

Reconstruction: Use when rough, mixed-language, or noisy input needs a short, repository-grounded English prompt. Own a routing-sufficient Intake contract; Skip routing-ready input or translation/editing.

Scite

Ground answers in scientific literature. Search full text, evaluate trust, access full-text articles

seeflow-design

Consult registered SeeFlow flows as architectural ground truth. Read-only counterpart to `/seeflow` — that skill *creates* flows from code; this one *reads* them when an agent is writing code or making decisions.

ADR-Driven Development (front-end for `adr → nightshift`)

Turn an intent into one **grounded, cited, build-ready ADR**, then hand it to `nightshift:plan`'s landing step. This collapses `brainstorm → spec → writing-plans → nightshift` into **`adr → nightshift`** for "I know what I want, build it" work.

Adversarial Review

Spawn reviewers on the **opposite model** to challenge work. Reviewers attack from distinct lenses grounded in brain principles. The deliverable is a synthesized verdict — do NOT make changes.

SAGE — Solver-Augmented Grounding Engine

LLM-native optimization solver: LP, MIP, portfolio & scheduling via HiGHS/OR-Tools.

design-elevation

Comprehensive design elevation system that automatically transforms functional visual outputs into polished, professional designs. Use when creating ANY visual output including presentations (pptx), spreadsheets (xlsx), dashboards, reports, HTML artifacts, PDFs, web pages, or data visualizations. Applies systematic design thinking grounded in Tailwind CSS as the canonical design token system. Structures decisions through functional patterns (what users interact with) and perceptual patterns (how the design feels), following Alla Kholmatova's design systems framework. Triggers on ALL requests for visual content creation, ensuring outputs look hand-crafted rather than template-based.

Io.Github.Houtini Ai/Gemini

Model Context Protocol server for Google Gemini AI with chat, research, and grounding

exa-research

Use when researching products, finding academic papers, discovering competitors, reading webpage content, or getting cited answers grounded in real web sources. Use over generic search when semantic relevance matters.

docs-manage

Manage the Grounded Docs MCP Server documentation index. Covers scraping and indexing documentation from URLs or local files, refreshing existing indexes with changed content, and removing libraries from the index. Use when you need to add, update, or delete indexed documentation.

Add Generative Answers

Add `SearchAndSummarizeContent` nodes to generate responses grounded in the agent's knowledge sources.

add-reference-tests

Add pytest tests to validate reference implementations in flashinfer_trace against FlashInfer or SGLang ground truth. Use when validating kernel definitions, adding tests for new op_types, or verifying reference implementations are correct.

Evaluate Options

Do not present options to the user without evidence. Every recommendation must be grounded in research, not assertion.

distilly

Build and use evidence-grounded local person profiles with Distilly's exact five-tool workflow. Use when a user asks to research, ingest, distill, update, correct, retrieve, or recall a real or fictional person's profile, voice, boundaries, or evidence.

agentic-learning

A learning partner skill grounded in neuroscience and philosophy. Use when you want to actually learn a concept (not just get an answer), quiz yourself on a codebase, reflect on what you built, brainstorm a design collaboratively, practice productive struggle on a hard problem, journal a decision with its alternatives and consequences, or schedule concepts to revisit later. Invoke with @agentic-learning followed by one of: learn, quiz, reflect, space, brainstorm, explain-first, struggle, either-or, explain, interleave, or cognitive-load.

163 Email Ground Truth

Nanobanana Image Skill

Use the bundled `nanobanana.py` tool to generate or edit images with Gemini image models. The default path now targets **Nano Banana 2** (`gemini-3.1-flash-image-preview`) and turns on **thinking summaries** plus **Google Search grounding** by default, because those defaults are the main reason to u

NotebookLM AI Plugin

Supports: - Chat with Notebook AI (source-grounded Q&A with citations) - Slide Deck generation (PDF/PPTX) - Audio Overview (M4A -- deep dive, brief, critique, debate formats) - Video Overview (MP4 -- classic, whiteboard, kawaii, anime, watercolor styles) - Mind Map (HTML) - Flashcards (HTML/JSON) -

paper7-ask

Use when the user asks a research question that needs synthesized answers grounded in academic literature. Uses paper7 search, get, cite, and kb commands with a hard gate against fabricated citations.