instruction layer auditor
by Roy Yuen
Audit and de-conflict complex agent instruction stacks to fix inconsistent behavior and logic bloat.
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
16 skills found
by Roy Yuen
Audit and de-conflict complex agent instruction stacks to fix inconsistent behavior and logic bloat.
An adversarial senior engineer review gate that audits AI-written code for security gaps and logic errors before shipping.
Find the unit tests that pass without testing anything. Flags tests with no assertions, trivial existence-only checks (toBeDefined, assertIsNotNone), tests that assert the exact value they just mocked, snapshot-only tests, tautological assertions (expect(true).toBe(true)), empty placeholders, and over-mocked tests with more setup than assertions. Works on Jest/Vitest and pytest/unittest.
Hardens AI prompts and agent workflows against logic errors, tool-misuse, and prompt injection.
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.
by Al1as
A high-ticket offer diagnostic engine that identifies structural conversion leaks and pricing logic failures.
Adversarially audit your agent hooks before you trust them. Catches command injection, secret leakage, over-broad matchers, destructive actions, and blocking-logic mistakes in pre/post-tool-use, prompt, and stop hooks — with a PASS or REVISE verdict and severity-ranked fixes.
by PromptWagon
Creates optimized Etsy shop sections, category names, collection descriptions, buyer navigation copy, section strategy, product grouping logic, seasonal section ideas, SEO-friendly browsing labels, shop-structure audits, and marketplace-readiness recommendations for Etsy sellers and digital product shops.
by heyhridyansh
A rigorous production-readiness auditor that identifies logic defects, security risks, and test gaps in code changes.
by PromptWagon
Reviews document sets, source quality, chunking logic, metadata, retrieval coverage, citation traceability, answer grounding, source gaps, stale content, duplicate content, and failure patterns for RAG knowledge-base chatbots. Helps AI, product, support, governance, and engineering teams diagnose common and costly RAG quality problems before deployment or after incidents.
by PromptWagon
Creates ethical upsell funnels for digital products, including order bumps, one-click upsells, downsells, thank-you pages, checkout copy, post-purchase offers, email follow-ups, bundle logic, offer positioning, buyer journey notes, and funnel audit recommendations to help creators increase average order value without misleading buyers.
by PupLogic
Automated WCAG 2.1 AA accessibility auditor that computes contrast ratios and provides code-level fixes.
A third-party skill is instructions your agent will trust. Review it before you install it. Structured security auditing for third-party skills to detect injection, exfiltration, and hidden malicious logic.
by PromptWagon
Reviews SaaS, subscription, digital product, membership, service, and ecommerce pricing pages for confusing tiers, weak value framing, unclear plan differences, missing FAQs, missing risk reducers, poor upgrade logic, hidden objections, unclear billing terms, weak plan comparison copy, and customer decision friction.
by PromptWagon
Audits course outlines, lessons, modules, learner activities, assessments, outcomes, handouts, learning flow, learner support, accessibility, completion logic, and publishing readiness for gaps, weak alignment, unclear objectives, missing practice, assessment issues, and improvement opportunities before a course is published, sold, or delivered.
by Jiangdongbo
Audit AI-generated drafts for hallucinations, logical errors, and factual inaccuracies with quantified scoring.