Social Media Quality Gate — Pre Publish Checker for X, note, LinkedIn, Brain
by Shogun Labs
Automated quality checker that runs before publishing to any social platform or content site
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
141 skills found
by Shogun Labs
Automated quality checker that runs before publishing to any social platform or content site
by PromptWagon
Builds paid community launch packages for creators, coaches, educators, consultants, and digital product sellers, including community positioning, member promise, rules, onboarding flow, content calendar, engagement prompts, launch posts, pricing placeholders, sales copy, FAQs, moderation notes, retention ideas, and launch checklists.
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.
by PromptWagon
Turns model test results, prompts, outputs, benchmarks, scoring notes, evaluation datasets, failure examples, comparison results, and reviewer observations into clear model evaluation reports with findings, recommendations, evidence gaps, deployment considerations, and repeatable evaluation documentation for AI teams.
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.
Your skill works today. Will it work after the next model update? Build the harness that answers with numbers. Builds a standalone regression test harness with mechanical grading to verify skill behavior after model or code updates.
by Jose Luis
Moderate toxic language, detect personal data leaks, and audit domain security configurations via MCP.
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.
Diagnose and recover Windows-based local AI projects, Python APIs, and Ollama model servers.
by PromptWagon
Creates support-ready handover packs for AI workflows, automations, agents, chatbots, integrations, and client delivery projects, including handover notes, dependency maps, operating instructions, failure modes, maintenance checklists, escalation routes, change logs, access notes, monitoring guidance, and client-friendly support documentation.
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.
Audit LLM spend to find recoverable waste in prompt caching, model routing, and token usage.
Audit and design behavioral-based moderation systems for communities to stop AI spam without relying on text detectors.
by Shandra
Creates complete, scalable UI component systems for modern web applications, covering design tokens, buttons, cards, forms, navigation, modals, tables, tabs, alerts, badges, tooltips, pricing cards, responsive behavior, accessibility, documentation, testing, governance, and developer handoff.
Compare two XLSX versions for formulas replaced by values, formula-family drift, broken references, new cycles, and workbook-control changes.
by Shandra
Creates complete, conversion-aware marketplace interfaces for buyers, sellers, guests, vendors, and operators. Covers homepage architecture, taxonomy, search, autocomplete, filters, sorting, listing cards, seller profiles, reviews, saved items, comparison, messaging, multi-seller checkout, bookings, quote requests, seller onboarding, inventory, orders, payouts, trust, moderation, accessibility, analytics, QA, and developer handoff.
by Shandra
Creates structured, secure, scalable admin-panel interfaces for user and organization management, roles, permissions, data tables, filters, saved views, bulk actions, settings, audit logs, billing, subscriptions, reports, moderation, support operations, responsive behavior, accessibility, analytics, and implementation-ready developer handoff.
by heyhridyansh
Plans evidence-based, staged migrations from JavaScript or loose TypeScript to strict mode while preserving runtime safety.
Reconcile provider bills, usage events, model prices, retries, and customer allocation into deterministic AI cost findings.
Make an agent give the essential fact, immediate next action, and principal risk before any optional detail.
by Jose Luis
Execute and manage loan amortization calculations with persistent session state via MCP.