Now open worldwide. Creators in every country can onboard and sell agent skills on Agensi -> Start selling
THE AGENSI STORE
4069 skills found
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 Nex AI
Schrijft een concept-opiniestuk voor krant of nieuwssite namens een politicus: scherpe stelling, persoonlijke insteek, onderbouwing en voorstel: binnen de woordlimiet van het medium.
by Nex AI
Stelt een concept-aanvraagbrief/-mail op waarmee een architect aannemers uitnodigt om te bieden op een project: met projectinfo, in te dienen stukken, biedingsregels en deadline.
by Nex AI
Structureert de intake van een nieuwe cliënt of zaak bij een advocatenkantoor: conflictcheck-protocol, intakefiche, eerste risico-inschatting en opdrachtafbakening.
by Nex AI
Structured interrogation strategist for lawyers: generates evidence-linked question lists and inconsistency fiches.
by Joker
6 AI tool type routing, 5-dimension review, Top5 templates, free alternatives matrix, scene matching.
by Nex AI
Automated mechanical check of notarial deeds for consistency in names, dates, amounts, and template placeholders.
by Joker
Model selection matrix (MJ/Flux/SD), composition rules, 3-level quality gates, 10 style recipes.
Generates complete 13-part specifications for client welcome packets and onboarding kits for any service profession.
Generate complete Etsy-ready and KDP-optimized product specifications for college study planners in one click.
Define a distinctive, consistent brand voice and transform generic copy into high-impact, personality-driven content.
Transform your professional experience into a structured, four-phase roadmap for changing industries or roles.
by Eric Pi
Systematic root cause analysis skill to find and fix the source of bugs, not just the symptoms.
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.
A pay-per-call gateway for AI agents to discover, preflight, and execute paid API requests with unified settlement.
by Al1as
Architect designed system degradation and choreographed failure sequences to prevent chaotic breakdowns.
Stop leaving your AI startup exposed to malicious users trying to steal your proprietary system prompts or bypass your paywalls. The AI Prompt Injection Defense Shield is an automated code review agent that deeply analyzes your Next.js or Python backend, instantly detecting insecure LLM input fields, un-sanitized API data streams, and weak prompt boundaries. By automatically generating the exact copy-paste code patches required to harden your AI wrapper against the latest OWASP top 10 LLM vulnerabilities, this skill allows solo developers and indie hackers to confidently launch their SaaS without the fear of massive, unexpected API billing spikes or catastrophic data leaks.
by SkillForge
Design bulletproof Windows desktop automations using pywinauto, UIA, and resilient fallback strategies.
by Ryan lyell
A cognitive reasoning protocol and Markdown-based local memory system for high-stakes AI development and strategy.
Review a database schema, queries, or migration for the mistakes that get expensive in production — bad table design, missing or wrong indexes, slow and N+1 queries, SQL injection, and migrations that lock or break prod. Engine-aware (PostgreSQL, MySQL, SQLite, SQL Server), it runs an ordered review and returns a PASS/REVIEW/BLOCK verdict with prioritized fixes. Schema mistakes are the most expensive kind — this catches them before they ship.
Find the LLM integration code that will not survive a provider being pulled or going down. Flags single-provider lock-in with no alternative, calls with no failover branch, missing timeouts, retries with no limit or backoff, no degraded-mode default, and hardcoded endpoints with no alternate. This is about the model going away, not the model declining.
Produces a verification plan that proves a code change actually works — observable "working" definitions, evidence-over-inference checks, evidence trail. Use when the user says "verify this works", "is it actually done", "prove the fix works", "did the fix actually work", or "definition of done for this change". Do not use before the change is written — use structured-impl-planner instead.
Safely capture and inspect test emails in a staging environment without sending to real recipients.
by Nex AI
Vat aangeleverde nieuwe wetgeving, KB's of rechtspraak samen tot een concept-cliëntenalert of kantoornieuwsbrief: wat verandert, voor wie, vanaf wanneer, welke actie.