academic-research
This skill should be used for academic paper search, literature reviews, and research synthesis. Combines Exa MCP (research_paper category, arxiv.org filtering) with arxiv-mcp-server for paper discovery, download, and deep analysis. Use when searching for papers, conducting literature reviews, analyzing research trends, or synthesizing findings across multiple papers.
advise
Solve problems using knowledge base insights - extracts search terms, runs parallel KB queries, synthesizes advice grounded in your own frameworks
adversarial-swarm-analysis
Analyze an open question by casting 3-5 deliberately conflicting expert roles, running them in parallel and blind to each other, sharpening them in a debate round, attacking their consensus with a devil's advocate, then synthesizing a verdict that preserves disagreement instead of averaging it. Use for decisions, strategy, idea generation, hypothesis triage, experiment post-mortems, or any question where a single lens would return "it depends".
Nallely System Prompt for Local LLMs
You are an assistant specialized in Nallely, a modular reactive Python framework for patching signal-processing modules (neurons) together, like a modular synthesizer for control systems. You can interact with a running Nallely session via two WebSocket protocols.
collab
Gemini and Codex collaboratively brainstorm solutions, building on each other's ideas across rounds. Agent synthesizes the best ideas into a plan.
Roundtable
Multi-model AI debates: GPT-4o, Claude, Gemini & 200+ models discuss, then synthesize insight.
E2E driving: CLI control of the live Obsidian GUI
Every action is a synthesized user event (pointer, keyboard, input, file-picker change) on the real DOM â never a service shortcut â so a scripted run exercises exactly what a human's clicks would. Round trips are 1â10ms. Full docs: "CLI E2E driving" in docs/development.md.
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 â do NOT make changes.
self-learning
Autonomous skill generator that learns new technologies from the web. Use when, users want to learn about a new library/framework/tool, need to create a skill for an unfamiliar technology, want to research and document a technology's usage patterns, or invoke with `/learn <topic>`. This skill uses web search and browser tools to discover, extract, and synthesize documentation into a reusable skill.
langfuse-docs
We built an AI agent skill that synthesizes GitHub issues, support tickets, and meeting notes into a weekly digest, and used Langfuse to monitor and improve it.
agent-fanout
Use this skill when the user asks to "fan out agents", "spawn agents", "use an agent team", "parallel agents", "delegate to subagents", "act as team lead", "orchestrate implementation", "fan out teammates", or when a task decomposes into 2+ independent work items (parallel exploration, one implementer per issue, a multi-lens PR review panel). Covers the basic mechanics of spawning, briefing, supervising, and synthesizing subagents and teammates, plus the hard cap on fleet size.
swmm-anywhere
**Synthesize a plausible SWMM drainage network from public data (OSM streets + DEM) when no real pipe-network data exists.**
u-he Preset Randomizer
Generate, randomize, explain, and manage u-he synthesizer presets via the Model Context Protocol.
create-smartfolder
Turn a folder hierarchy into a SmartFolder â a tiered navigation-and-knowledge layer over the real files, so people and future Claude sessions can operate in it with full context and synthesized knowledge without opening every file. Use whenever the user asks to create, build, or convert a folder into a SmartFolder, "smartfolder-ize" a directory, add a CLAUDE.md / README / synthesis layer over files, reorganize an archive or document repository so Claude can navigate it, or review, upgrade, or extend existing SmartFolder scaffolding â even if they never say "SmartFolder" but describe wanting a folder of records made self-describing, navigable, or Claude-ready. Also use when asked to organize or reorganize a folder without a scheme the user has already chosen, so deciding it requires understanding the contents: look first, then offer this method rather than assuming it. Not for file operations already specified â renaming to a stated pattern, moving named files, de-duplicating.
codealive-context-engine
Semantic code search and AI-powered codebase Q&A across indexed repositories. Use when understanding code beyond local files, exploring dependencies, discovering cross-project patterns, planning features, debugging, or onboarding. Queries like "How does X work?", "Show me Y patterns", "How is library Z used?". Provides search (fast, returns file locations and descriptions) and chat-with-codebase (slower, costs more, but returns synthesized answers).
agent-council
Collect and synthesize opinions from multiple AI agents. Use when users say "summon the council", "ask other AIs", or want multiple AI perspectives on a question.
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.
Goosetown Orchestrator
Decompose, dispatch, synthesize. Don't build â make sure the right things get built, in the right order, with the right context. The user knows what needs to exist; you know how to coordinate building it. Keep the whole picture legible: who's doing what, why, and what's been learned so far.