Prompt Engineering Engine
by Joker
Model selection matrix (MJ/Flux/SD), composition rules, 3-level quality gates, 10 style recipes.
New: UPI payments are live. Buyers in India can now pay for skills with UPI in INR -> Browse skills
THE AGENSI STORE
631 skills found
by Joker
Model selection matrix (MJ/Flux/SD), composition rules, 3-level quality gates, 10 style recipes.
Messy, insecure, unfixable — that's what AI builds without architecture. This file is the architecture: 10 years of senior judgement on rendering, caching, security and SEO, so your agent builds it right from day one.
Generate a spec-compliant llms.txt (and optional llms-full.txt) for your site or repo so AI agents and crawlers can navigate it. Curates the pages that matter, writes the exact llmstxt.org structure — single H1, blockquote summary, and link sections in the precise format agents parse — then validates the format and tells you where to put it. The honest version: a low-cost, machine-readable surface for the agentic web, not an overhyped SEO trick.
Scaffold a secure, spec-compliant MCP server from a description of the tools you want to expose. Sets up the official SDK (TypeScript or Python/FastMCP), defines tools/resources/prompts with strict JSON Schema, wires the right transport (stdio or Streamable HTTP), adds OAuth 2.1 for remote, and hardens against the MCP-specific footguns — prompt injection via tool output, token passthrough, over-broad scopes, command/path/SSRF injection, leaked secrets — before it ships. Returns a runnable skeleton plus a security checklist. Built by someone who's shipped production MCP servers.
by Scotty W
337+ professional-grade tools for finance, networking, SEO, and development in a single MCP server.
Optimize your website's architecture and content to be discovered, indexed, and cited by AI agents and LLMs.
Every RAG tutorial shows the same pipeline; almost none of it survives contact with your actual corpus
A retrieval architect that diagnoses why RAG returns confident-but-wrong answers, picks the right context architecture (RAG vs knowledge graph vs structured/temporal retrieval) instead of defaulting to vector search, and designs the institutional-memory schema embeddings throw away.
by zoninmane
Deploy 6 battle-tested multi-agent orchestration patterns to eliminate agent laziness and boost output quality.
by Timoranjes
Teaches AI coding agents to stop repeating the same mistakes by maintaining a structured LEARNINGS.md file that captures failure patterns, converts them into guardrails, and feeds them back into CLAUD
Architectural strategist that converts flat prompts into structured, multi-file ChatGPT Skill blueprints.
by Al1as
A high-discipline decision-governance layer to prevent AI agents from acting on poor evidence or conflicting goals.
Stop your agent citing papers that don't exist. Verifies every reference against live PubMed & Crossref — flags fabricated, mismatched, and retracted citations.
by Al1as
Map the geometry of system failures to transform edge-case chaos into structured architectural governance.
by SkillForge
Architect production-grade multi-agent systems with explicit contracts, idempotency, and self-healing reliability.
Score and optimize any website for AI agent-readability using the Agent Ready REST API.
by Timoranjes
Teaches AI coding agents to generate production-quality Playwright end-to-end tests from page analysis, user stories, or existing code. Covers selector strategy, test structure patterns, flakiness prevention, and CI integration — for QA engineers and solo devs tired of AI-generated tests that break on first run.
by Roy Yuen
Secure encrypted secret management with automated health checks, expiration tracking, and rotation reminders.
by RC V
Transform business ideas into deployment-ready autonomous company blueprints for multi-agent frameworks.
by Ryan lyell
Intelligently audit your repo and workflow to recommend, install, or create custom AI agent skills.
by Timoranjes
Teaches AI coding agents to perform deep research and data extraction from Chinese-language web sources including Baidu, Xiaohongshu (RedNote), WeChat, Zhihu, Weibo, and Chinese government portals. Ha
by Kenny Shaw
Transcribe video links into clean text, timeline transcripts, SRT, or VTT subtitles using the Videosays CLI. Supports YouTube, TikTok, Douyin, and Xiaohongshu workflows for AI agents.
by Roy Yuen
Transform high-level goals into autonomous Plan-Build-Run-Learn iteration loops with persistent workspace learning.
by Kaymue
Diagnose broken RAG systems. 8 failure categories: chunking, embeddings, retrieval, reranking, hallucination. Recall@k measurement.