Library
87,246 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
formify-skills
SkillsAI agent skills for SMB e-signing and document workflows — build fillable PDF forms, send contracts for electronic signature, verify signers with BankID or an ID scan, and track everything after the send. Works with Claude, ChatGPT, Codex, Cursor and ~25 agents via MCP.
git clone https://github.com/formify-e-sign/formify-skills.git -
TheDrummer: Skyfall 36B V2
ModelsSkyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.
thedrummer/skyfall-36b-v2 -
IA-QA — 152 QA & Dev Tools for AI Agents
MCP servers152 free QA tools for agents: injection scan, evals, RAG, web audits. Smaller packs: /mcp/{pack}.
-
Mistral: Ministral 3 3B 2512
ModelsThe smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
mistralai/ministral-3b-2512 -
Pirate Ship MCP Server and API by Cotlet
MCP serversPirate Ship small business shipping labels MCP server: get rates, buy labels in bulk, import orders.
pirate-ship-api-mcp@1.0.3 -
Broken Link Checker (Apify actor)
MCP serversApify actor via Apify's MCP server (Apify token needed): dead links on a page or small site.
-
valcraft
SkillsAgent skills for spec-driven development. An automated agentic delivery loop coordinates planning, implementation, and cross-agent code reviews. Requirements, plans, and decisions live in ordinary project files with project-wide IDs linked from commits and PRs, reducing manual handoffs and repeated explanations while keeping session context small.
git clone https://github.com/valzav/valcraft.git -
whenship
SkillsWhen will it ship, honestly? A tiny planner for small teams: live what-if Gantt, deadline risk and realistic dates. Works in the browser and inside Claude.
git clone https://github.com/HamedShams/whenship.git -
ShotAPI MCP Server
MCP serversScreenshot and HTML render MCP server for AI agents
-
OpenRouter: Fusion
ModelsFusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...
openrouter/fusion -
Creative Branding Strategist
PromptsYou are a creative branding strategist, specializing in helping small businesses establish a strong and memorable brand identity. When given information about a business's values, target audience, and industry, you…
-
The greedy Cat
PromptsArt Style: 2D classic cartoon animation, bright warm colors, exaggerated expressions, smooth animation Characters: Consistent characters - orange chubby cat with green eyes sleeping. Small brown mouse with big ears…
-
5dive
Agents & frameworksRun your own AI team from your phone. Claude Code, Codex and more on your own server: shared tasks, always-on agents, a small composable bash core. MIT. An open-source alternative to Grok Bot and OpenAI Dots.
git clone https://github.com/5dive-ai/5dive.git -
Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...
cohere/command-r7b-12-2024 -
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
nvidia/nemotron-3-nano-30b-a3b -
The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...
mistralai/ministral-14b-2512 -
Painterly board game box cover illustration for a cozy cooperative trading game about airship merchants. Three small wooden airships with patched canvas balloons in mustard, teal and rust drift between floating…
-
Venice: Uncensored
ModelsVenice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...
cognitivecomputations/dolphin-mistral-24b-venice-edition -
{ "role": "Food safety consultant who builds clear, auditable allergen information for small restaurants and cafes", "task": "Turn my menu and recipe notes into a single strict JSON allergen package: a dish-by-allergen…
-
Code Review taste
Prompts# Code Review taste of a staff engineer - Keep pull requests small enough to review in one sitting, ideally under 400 changed lines; split refactors from behavior changes. Confidence: 0.90 - Write a PR description that…
-
Serverless Functions taste
Prompts# Serverless Functions taste of a cloud backend engineer - Keep each function small and focused on one trigger, but group closely related HTTP routes in one handler to cut cold starts. Confidence: 0.80 - Initialize SDK…
-
Neovim Config taste
Prompts# Neovim Config taste of a minimalist terminal-first developer - Write the whole config in Lua, starting from a single init.lua that requires small modules under lua/config and lua/plugins. Confidence: 0.90 - Use…
-
Meta: Llama 3.2 1B Instruct
ModelsLlama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...
meta-llama/llama-3.2-1b-instruct -
low risk to uplift income
PromptsAct as a practical career strategist and financial risk advisor. ## Objective Help me take **small, low-risk, high-upside actions** to improve income and growth, and ensure I **consistently execute them using an…
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.