New: Skill bounties are live. Post a request, fund the bounty, and creators compete for 7 days to build it -> See open bounties
THE AGENSI STORE
16 skills found
by loreto
Published AI benchmarks measure brains in jars. They test models in isolation or within a single reference harness — and then attribute all performance to the model. This skill teaches you to decompose agent performance into its two actual components: model capability and harness multiplier. The result is evaluations that predict real-world behavior instead of benchmark theater.
by loreto
Evaluates AI coding agent platforms across five structural dimensions that determine real-world performance independently of model quality, so teams select on architectural fit rather than benchmark scores.
by 聊言青
A multi-stage, evidence-grounded academic review agent modeled on the AAAI-26 AI Review Pilot research.
by Aman Garg
Stop burning expensive model tokens on repetitive subtasks. This skill delegates mechanical work to cheaper models and writes handoff snapshots so you never lose context switching between sessions.
Bridge OpenCode to the Agensi marketplace to discover and install AI agent skills via MCP.
by Rapa Canola
Intelligently delegate tasks to Claude, Codex, or Gemini based on cost, model strengths, and rate limits.
Quickstart guide to connect your AI agent to the Agensi marketplace via Model Context Protocol (MCP).
Drive a browser from your agent without the token bloat. Batches navigate/click/type into one call, stays logged in with persistent sessions, and feeds the model compact DOM snapshots instead of giant HTML, so multi-step flows like logins, form-filling, and scraping behind auth stay fast and cheap. Runs on the uBrowser MCP server.
by LocoLoboZ
Orchestrate independent reviews, adversarial audits, and multimodal analysis via secondary models and external tools.
by Nex AI
Maintain 100% uptime with an automated LLM fallback chain that routes from high-tier APIs to local models.
by Nex AI
Scaffold a multi-model 6-step pipeline to automatically turn prospect URLs into live, branded demo websites.
Design the right team of specialized AI subagents for your project and get the definition files written properly — precise delegation triggers, focused system prompts, least-privilege tools, and the right model tier for each job. Includes a template, orchestration patterns, and a complete sample team.
Turn Claude into a court. One brain, a dozen free workers. King makes your agent the orchestrator, not the laborer — it plans the task, delegates the heavy lifting to a fleet of free-tier LLMs, cross-checks their work, and hands you a single verified answer better than any one model could give. You keep the judgment; the free models burn the tokens. Now with a guided first-run wizard that gets you set up in minutes.
by Shogun Labs
Battle-tested prompting patterns to eliminate LLM output drift. Sandwich structure, few-shot examples, history limits, retry, and token caps — 6 composable layers for production-grade agent reliability.
A defensive catalog of ~39 agent security attack patterns across every surface — injection, tool abuse, exfiltration, memory poisoning, multi-agent trust, retrieval poisoning — each with a detection signal, a concrete defense, and a severity. Nine reference files plus a threat-model worksheet. For hardening agents you own.
by Shandra
Architect professional AI SaaS interfaces, generation workflows, and implementation-ready UI specifications.Designs professional interfaces for AI applications, including chat workspaces, prompt composers, file uploads, multimodal inputs, templates, model controls, generation states, result previews, output controls, version history, projects, credits, usage limits, settings, safety states, responsive behavior, accessibility, analytics, experimentation, and developer handoff.