54 boosters for "nsf" — open source, verified from GitHub, ready to install
"name": "nano-banana-2-skill-marketplace", "url": "https://github.com/kingbootoshi" "description": "AI image generation CLI powered by Gemini 3.1 Flash (default) and Gemini 3 Pro. Multi-resolution, aspect ratios, cost tracking, green screen transparency, reference images, style transfer.",
You are an expert in prompt engineering and systematic application of prompting frameworks. Help users transform vague or incomplete prompts into well-structured, effective prompts through analysis, dialogue, and framework application. When a user provides a prompt to improve, analyze across dimensi
You play the role of a director's assistant fluent in the 5-stage AI shortfilm prompt structure (first proven by Mx-Shell in Zombie Scavenger). When the user invokes this skill they want a prompt they can paste
检测和改写中文 AI 生成文本的完整工具链。可独立运行（统一 CLI 或独立脚本），也可作为 LLM prompt 指南使用。 所有脚本在 目录下，纯 Python，无依赖。 v3.0 所有阈值都基于 HC3-Chinese 300+300 人类/AI 样本的 Cohen's d 校准：
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
JN is a command-line ETL tool for data transformation using NDJSON as a universal format, enabling developers to filter, convert, and stream data across CSV/JSON/Excel/YAML formats with Unix pipes.
Transform a Vibes app into a multi-tenant SaaS with subdomain-based tenancy. Adds Clerk authentication, subscription gating, and generates a unified app with landing page, tenant routing, and admin dashboard.
"description": "Transform Claude Code into a structured development platform with 29 /sc: commands, 23 specialized agents, 7 behavioral modes, and MCP server integration", "name": "SuperClaude Team", "email": "support@superclaude.dev",
Trade on Lighter — a ZK-rollup perpetual futures and spot exchange. Scripts live in this skill's directory. Read commands use , write commands use . Every command prints structured JSON to stdout. Errors are always in JSON as . Commands use syntax mirroring the Lighter UI (e.g. , , ).
Transformation content is the highest-engagement format on social media. This skill generates precise Seedance 2.0 prompts that capture the full emotional arc of change: tension, reveal, payoff. Before generating prompts, establish: Show both states in rapid alternation — before/after/before — withi
Transform podcast audio into cinematic visual content using Seedance 2.0 on Higgsfield. This skill produces video prompts that replace static audiograms with storytelling-driven visual experiences built entirely from constructed imagery. The hook is the opening frame that stops the scroll. It must c
"name": "orchestrator", "description": "Autonomous Development Orchestrator - Transform ideas into production-ready applications through multi-agent pipeline. Spec → Plan → Tasks → 100% Working App.", "repository": "https://github.com/devsforge/orchestrator",
"name": "ralph-dev", "version": "0.4.10", "description": "Autonomous end-to-end development system - from requirement to production-ready code with zero manual intervention",
"description": "AI-assisted spec crafting through research, interviews, and multi-LLM review. Like Geppetto carved Pinocchio from wood, transform rough ideas into living implementation plans.", "name": "Leonardo Flores", "url": "https://github.com/leonardocouy"
"name": "paper-to-course", "description": "Transform any academic paper into an interactive HTML course, Markdown notes, and PPTX slides. Converts research papers into self-contained courses with formula breakdowns, literature timelines, comparison tables, ablation diagrams, method chats, and compre
Transforms rough prompts into production-ready LLM prompts using advanced techniques like Chain-of-Thought and RAG optimization. Ideal for developers, AI engineers, and teams building LLM applications who need to craft effective prompts across Claude, GPT, Llama, and other models.
Obvec transforms Obsidian vaults into AI-searchable knowledge bases using Cloudflare Vectorize and serverless Workers, enabling developers and knowledge workers to query their notes with AI-powered semantic search through Claude.
Provides a Memory Bank framework for AI agents to maintain project context across sessions through structured Markdown documentation. Useful for teams using Copilot who need persistent, organized project knowledge.
Allyson MCP Server is an AI-powered SVG animation generator that integrates with Claude to transform static SVG files into animated components using Framer Motion, enabling developers to quickly add motion graphics to their projects without manual animation coding.
This booster provides Copilot instructions for automating content curation and SEO-optimized article generation from trending topics, targeting content creators and marketers.
Editor is an AI writing coach that transforms rough drafts into polished content by optimizing clarity, readability, and voice consistency. Ideal for content creators, marketers, and developers who need to elevate their written output.
The plan-generator transforms high-level product requirements into executable project blueprints (genesis.xml files) with structured task DAGs and agent assignments. It's invaluable for cofounders and product teams who need to bridge strategic vision with concrete execution plans.
visual-storyteller transforms data and concepts into compelling visual narratives, infographics, and presentations. Ideal for marketers, product teams, and communicators who need to engage stakeholders through compelling visual content.
This MCP server transforms linear AI reasoning into structured, auditable thought graphs using DAG (directed acyclic graph) representations, enabling developers to visualize and verify AI decision-making processes with full traceability.
