New: UPI payments are live. Buyers in India can now pay for skills with UPI in INR -> Browse skills
THE AGENSI STORE
121 skills found
Produces a diagnosed and rewritten prompt — component-level failure analysis, structure fixes, few-shot examples, and a regression case set. Use when the user says "fix my prompt", "why does this prompt keep failing", "improve my system prompt", "reduce hallucinations in this prompt", or "my prompt isn't following instructions". Do not use when the request is choosing which model to use, not fixing wording.
Designs an MCP server's tool surface for an existing API — task-first tool consolidation, descriptions and schemas written as prompts, response curation, and auth patterns. Use when the user says design an MCP server, reduce my agent's tool count, or write MCP tool descriptions. Do not use when they want a general REST API or SDK, not an agent-facing MCP tool surface.
by Joker
AI product type routing, discovery framework, LLM app design (Prompt/RAG/Agent), metrics, ethics.
Produces a RAG system design, retrieval failure diagnosis, or institutional-memory schema — architecture decisions, hybrid search strategy, and a readiness checklist. Use when the user says "design our RAG system", "debug our retrieval accuracy", "fix RAG hallucinations", "choose a vector database", or "build an institutional memory schema". Do not use when the request is fine-tuning the base LLM itself.
by Al1as
Architect designed system degradation and choreographed failure sequences to prevent chaotic breakdowns.
Turns open-ended AI chats into guided, interactive menu systems for structured task navigation.
Produces a diagnosis of why a RAG system gives confident-but-wrong answers, or picks between vector search, knowledge graph, and structured/temporal retrieval. Use when the user says "why is our RAG hallucinating", "diagnose this failing query", "should we use a knowledge graph", "pick a retrieval architecture", or "design our memory layer". Do not use when the request is building a RAG system from zero.
Every RAG tutorial shows the same pipeline; almost none of it survives contact with your actual corpus
by SkillForge
Architect production-grade multi-agent systems with explicit contracts, idempotency, and self-healing reliability.
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.
by RC V
Transform business ideas into deployment-ready autonomous company blueprints for multi-agent frameworks.
by SkillForge
Force your AI agent to apply senior-level architectural judgment and design notes before writing any code.
by Shandra
Creates phased modernization plans for transforming monolithic applications into modular monoliths, service-oriented systems, or microservice-ready architectures without risky rewrites.
Design and write the eval suite for your LLM-powered feature — the metrics that match your failure modes, a golden dataset plan with starter cases, anchored rubrics, LLM-as-judge prompts with the known bias mitigations, and pass/fail gates wired for CI.
Architect reusable AI behavior presets with rigorous rules, activation phrases, and defined output structures.
by GTDataworks
Convert a repeatable workflow into a reusable agent skill or staged skillchain candidate.
by Shandra
Designs controlled multi-agent workflows with clear roles, contracts, validation gates, approval steps, memory boundaries, audit trails, error handling, and fallback behavior.
by SkillForge
Enforce senior-level architectural thinking by making your agent write a 5-line Design Note before coding.
by Echo Rose
Color Palette Pro - A Premium AI Agent Skill
Produces a coordinated five-skill workbench for any professional field — one coordinator, three specialists, one reviewer — plus a wiring guide showing how they hand off to each other. Use when the user says build a skill workbench, make a team of agent skills for my field, set up a coordinator plus specialists, or design how several skills should hand off. Do not use when the user wants one standalone skill rather than a coordinated set.
by Timoranjes
Transform your AI agent from a code generator into a senior architect that enforces clean design and SOLID principles.
Turns your agent into a rigorous survey methodologist that designs, reviews, and fixes questionnaires — question wording, response scales, sampling, and data quality.
by Shogun Labs
Everything needed to work with PowerPoint presentations programmatically