🧠 AI Memory Optimizer
Drastically reduce RAG costs and latency while improving retrieval accuracy through advanced memory architecture.
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
81 skills found
Drastically reduce RAG costs and latency while improving retrieval accuracy through advanced memory architecture.
A direct, structured coaching skill to clear mental fog, define high-leverage goals, and build 90-day action plans.
Audit local dbt SQL and YAML for missing model tests, source freshness and test gaps, likely-key coverage, missing model descriptions, SELECT *, and raw table references. Get severity-ranked findings plus starter tests YAML for model/key gaps without running dbt or querying a warehouse.
by Joker
Scraper architecture routing, anti-scraping strategies, data extraction, storage, compliance.
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.
by Nex AI
Deploy a self-hosted, private RAG system with pgvector, Ollama, and a Telegram interface for your personal notes.
Enforce strict Red-Green-Refactor discipline to build robust, test-driven software with 100% meaningful coverage.
by Nex AI
Deploy a structured, long-term memory palace for AI agents on Raspberry Pi via MCP and ChromaDB.
An adversarial reviewer for AI-written code changes. It pressure-tests a pull request or diff for untested branches, silent behavior changes, missing edge cases, over-confident code that only looks right, and weak tests, then returns a PASS / REVISE / BLOCK verdict before the change merges.
by Liam Romanis
Deep audit and detection of the Dirty Frag (CVE-2026-43284/43500) Linux privilege escalation exploit chain.
Transform fragile AI prototypes into resilient, enterprise-ready production agents with professional hardening tools.
by Nex AI
Controleert een voorraadlijst op plausibiliteit via een Python-script: negatieve aantallen, waarde-afwijkingen, verkoopprijs onder kostprijs (LOCOM-signaal) en trage rotatie.
by Nex AI
Zet een conclusie of dossiernota om in een concept-pleitnota voor mondeling gebruik: spreekbare structuur, tijdsindeling, kernzinnen en antwoorden op verwachte vragen van de rechter.
by Nex AI
The complete Nex Price Radar Chrome extension (real shipped Manifest V3 source): track price history across Amazon, Bol.com, Coolblue, AliExpress, Zalando and more, and see at a glance whether the current price is high, low, or average. Reads prices locally from the page, stores history in the browser, makes no external API calls. Ships the full extension plus the dev loop, customization guide, and Web Store packaging steps. No build step.
An adversarial reviewer for Dockerfiles and container builds. It flags root users, image bloat, unpinned or cache-busting layers, leaked secrets, and missing hardening, then returns a PASS / FIX / BLOCK verdict — before you build or push the image.
Design, diagnose, and optimize high-performance RAG systems with an engineering-first framework.
by Nex AI
Stelt een reactieve perslijn op bij een incident of gevoelig dossier: kernlijn, Q&A met lastige vragen, houding-statement en interne afspraken over wie wat zegt.
by Nex AI
Structureert een schadeclaim in een concept-begrotingsoverzicht: per schadepost het bedrag, de berekeningswijze en het bewijsstuk: met interesten-aanzet en zwakke-plekken-analyse.
by Joker
AI product type routing, discovery framework, LLM app design (Prompt/RAG/Agent), metrics, ethics.
by Nex AI
Deploy conversion-optimized, single-file websites for garages and auto shops with built-in AutoRepair SEO schema.
by Nex AI
Organiseert de opvolging van parlementaire en raadsinstrumenten: antwoorden analyseren, toezeggingen registreren, herinneringsvragen en politieke verzilvering: in een concept-opvolgregister.
by Joker
Cloud platform routing, architecture pattern decisions, compute/storage/network selection, cost optimization.
Adversarial memory audit to remove PII, stale facts, and injected instructions from agent storage.
by Shandra
Audits fragile Zapier, Make, n8n, Airtable, Google Sheets, CRM, webhook, API, and script automations for failure points, data-loss risks, weak logging, missing retries, and risky dependencies.