Skill Health Scanner
Instantly diagnose any skill or prompt and get a clear, prioritized report on what’s wrong and how to fix it — across any agent.
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
14 skills found
Instantly diagnose any skill or prompt and get a clear, prioritized report on what’s wrong and how to fix it — across any agent.
by Roy Yuen
A high-precision pre-coding gate that detects conflicting requirements and prevents agents from making wrong assumptions.
The default MCP server is an API wrapper that dumps forty endpoint-shaped tools on the model and hopes — and the model gets confused, picks the wrong tool, and produces garbage that looks like a tool call
Schema mistakes are the most expensive kind — code refactors in days, but a wrong table design holds your data hostage for years
An adversarial pre-send gate that reviews any email or chat message and returns a structured SEND/REVISE/HOLD verdict — flagging unclear asks, unintended tone, buried action items, and missing context, with the exact text quoted and a fix for each.
Auth is where one wrong early decision becomes a security incident with your name on it — JWTs chosen for sessions because a tutorial used them, refresh token rotation implemented wrong, RBAC bolted on after the fact
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.
Check your app for the security mistakes that leak data before you launch, explained in plain English. Flags API keys and secrets sitting in your code, a committed .env file, data with no login protecting it, database tables anyone can read, debug mode left on, wide-open sharing (CORS), hardcoded admin passwords, and public storage buckets. Built for non-technical founders shipping AI-built apps: every finding tells you what is wrong, why it matters, and how to fix it.
A retrieval architect that diagnoses why RAG returns confident-but-wrong answers, picks the right context architecture (RAG vs knowledge graph vs structured/temporal retrieval) instead of defaulting to vector search, and designs the institutional-memory schema embeddings throw away.
by Shandra
Automates repetitive e-commerce support for order tracking, shipping explanations, returns, exchanges, refunds, damaged items, wrong items, missing items, and escalation routing.
Run this on your plan, spec, or prompt before any work starts. It surfaces the decisions you never made, names what an agent would silently assume for each, ranks them by the cost of a wrong guess, and hands back a short list of choices to make now — plus the gaps that are safe to leave open.
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.
A deep reference library of production agent patterns — orchestration, context, tool design, failure and recovery, oversight, and evaluation. Every pattern states when it applies, when it's the wrong answer, what it costs, and the failure it prevents. Seven reference files, not a checklist.
Check normalized iCalendar events for floating times, DATE mismatches, missing boundaries, sequence errors, and recurrence evidence.