Autoresearch Optimizer
An iterative agent loop that optimizes any prompt, config, or artifact by making one change at a time, scoring it against a metric, and keeping only the winners.
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
An iterative agent loop that optimizes any prompt, config, or artifact by making one change at a time, scoring it against a metric, and keeping only the winners.
Find the model-version coupling that breaks when you swap LLMs. Flags hardcoded model names and versions, deprecated or renamed parameters (the max_tokens to max_completion_tokens class of change), hardcoded token and context-window limits, response-format parsing tied to one model's output, tool-schema format coupling between providers, and hardcoded per-token cost constants. The patterns load from an editable model-rules table you update as new models ship.
Scaffolds a demo-website factory that turns a prospect URL into a branded demo site through a 6-step FastAPI pipeline.
Your headless Ollama box crashes at 3am and you find out hours later. OllamaWatch pings your Telegram the instant a model dies, the GPU runs out of memory, or the API hangs — with a fix hint in every alert. One Python file, no SaaS, no dashboards.
Before an agent acts on a plan, verify that the things it named actually exist. Checks each referenced file path, function or method, import or package, environment variable, and CLI command against your repo, and flags the ones that do not resolve. Catches the hallucinated function and the phantom package before the edit, not after the build breaks. Resolves Python and JavaScript/TypeScript.
A structured protocol for AI agents to orchestrate sub-agents with role contracts and disciplined handoffs.
Generates a single-file, JSON-backed Python task CLI that both humans and orchestrator agents can call, with recurrence and priorities.
The hard part of multi-agent work isn't spawning agents — it's deciding what deserves parallelism, what each agent needs to not duplicate work, and how failures cascade
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.
Paste any AI output. Get the production-ready prompt that made it.
Every orchestration topology — sequential, parallel, hierarchical, map-reduce, critic-actor — selected and designed for your exact workflow. Full system design with agent roles, interfaces, routing logic, and error paths.
Deploys MemPalace long-term agent memory on a Raspberry Pi, a memory palace with knowledge graph and diary, registered as an MCP server.
Professional X/Twitter automation for AI agents: Post, monitor, extract data, and manage engagement via 99 API endpoints.
Runs an ordered evidence-integrity gate over any AI draft — grade sources, ground claims, verify technical assertions, stress-test — then returns one PASS/REVISE/FAIL ship decision.
High-reliability Dutch content engine with a Claude-Gemini-Qwen fallback chain and template safeties.
Five compact skills for artifact intake, preflight review, test planning, session handoff, and local tool-candidate inspection.
Cost-aware execution planning for AI agents — estimate cost-vs-value before expensive steps, propose cheaper paths (cache, summarize once, downshift models), and track spend against a session budget with a PROCEED / OPTIMIZE / DEFER verdict.
Audit your online store to ensure it is discoverable and purchasable by autonomous AI shopping agents.
The complete Nex Prompt Booster Chrome extension (real shipped Manifest V3 source): turn short, lazy AI prompts into detailed, structured, expert-quality prompts instantly, right inside ChatGPT, Claude, Gemini, Perplexity and Grok, with no API calls. Ships the full extension plus the dev loop, customization guide, and Web Store packaging steps. No build step.
Production prompts grow by accretion — every failure gets another appended rule until the prompt is two thousand words of contradictions that the model navigates unpredictably
Workflow type routing (text2img/img2img/video), node selection tree, VRAM optimization, quality gates.
Audit any website for AI agent-readability and protocol compliance using the Agent Ready CLI.