Agent Guardrails — Tiered HITL Governance for AI Agent Writes
by Ivan Fodjo
Deterministic tiered governance and human-in-the-loop guardrails for AI agent write-actions.
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
350 skills found
by Ivan Fodjo
Deterministic tiered governance and human-in-the-loop guardrails for AI agent write-actions.
Audit and optimize website visibility, reachability, and actionability for AI agents and LLM crawlers.
by Nex AI
Build and deploy a no-build, walkable 3D Three.js portfolio with interactive iframe stations and droid movement.
by PromptWagon
Creates local promotional campaign assets for small businesses, including seasonal offers, Google Business Profile-style posts, local social media captions, flyer copy, SMS copy, email snippets, window poster copy, WhatsApp messages, offer terms, urgency wording, CTAs, and campaign-readiness checklists. Helps local businesses promote timely offers clearly, ethically, and practically.
by Tyler
Turns your product facts into on-brand Shopify, Etsy, and Instagram copy — cloned from your own voice, built for apparel (sizing, variants, fit).
by Timoranjes
Teaches AI coding agents to enforce hard numeric quality thresholds on code complexity — cyclomatic complexity, cognitive complexity, coupling, and maintainability index — as deterministic CI/CD gates
by Shandra
Creates practical, market-ready chore chart printable specifications for children, families, roommates, and couples, including task lists, weekly routines, cleaning schedules, reward systems, allowance trackers, and fair rotation plans.
Turn a rough business description into a structured, investor-ready pitch deck. The narrative arc investors expect, every slide's headline and content, market sizing done honestly bottom-up, a traction slide framed for impact, a clear ask — plus an honest note on which slides are still weak, and never an invented number.
Find, verify, and rank active EU public procurement opportunities with official TED links and explainable bid/no-bid evidence.
by PromptWagon
Creates practical, non-technical AI incident response playbooks for businesses using AI tools, chatbots, agents, automations, copilots, and AI-enabled workflows, including wrong-output handling, privacy concerns, unsafe responses, escalation routes, containment actions, customer communication notes, recovery steps, evidence logs, and post-incident review templates.
by PromptWagon
Analyzes automation workflows, model calls, API usage, retries, triggers, batching, tool calls, storage usage, logging, third-party platform actions, and waste points to identify practical cost-saving opportunities, reduce avoidable spend, and create operational cost-control recommendations for AI automations and no-code workflows.
by PromptWagon
Creates trial onboarding flows, welcome emails, activation checklists, in-app guidance, tooltip copy, milestone prompts, product education sequences, upgrade nudges, trial expiry messages, and conversion-focused onboarding plans for SaaS teams, founders, product marketers, customer success teams, and growth teams.
Convert instructional videos into machine-readable, schema-validated specs without hallucinations or invented parameters.
by Summer
Automated factual verification using tiered official sources to eliminate hallucinations and circular reasoning.
by PromptWagon
Categorizes cancellation notes, exit surveys, support tickets, review comments, downgrade reasons, refund requests, customer interviews, and account closure notes into clear churn drivers, retention risks, user pain points, save opportunities, win-back angles, product fixes, support improvements, onboarding gaps, and stakeholder-ready retention action plans.
by PromptWagon
Scores and prioritizes LLM and AI use cases by business value, effort, risk, data readiness, process readiness, implementation complexity, stakeholder fit, governance needs, and expected operational impact, helping businesses create practical AI adoption roadmaps instead of pursuing random experiments.
Add WebMCP annotations to help AI agents navigate, search, and interact with your website forms.
by OnwireFlow
Makes your coding agent work like a senior developer: exact money, configurable rules, real audit trails, honest testing. Any stack, any country.
by PromptWagon
Turns customer reviews, survey responses, support tickets, user interviews, sales notes, cancellation reasons, feature requests, and open-ended feedback into clear product themes, pain points, user needs, feature opportunities, priority insights, action lists, and stakeholder-ready feedback reports for product teams, founders, SaaS teams, ecommerce teams, agencies, and customer success teams.
Check freight invoice lines against effective-dated rate rules, shipment facts, and approved accessorial evidence before payment review.
Identify and audit EU AI Act Article 50 transparency obligations for chatbots and AI-generated content.
A high-density structured response protocol for radical information compression and mandatory artifact generation.
Track LinkedIn metrics, analyze engagement rates, and manage post interactions via the Publora MCP server.
by Danejw
Anonymized resume screening and evidence-based ranking with full audit trails for compliant hiring.