Systematic Bug Debugger
Stop guessing and start solving with hypothesis-driven debugging for complex, intermittent, and production-only bugs.
Ship better AI in 30 seconds. Browse 2,000+ expert-built and security scanned skills -> Browse skills
THE AGENSI STORE
180 skills found
Stop guessing and start solving with hypothesis-driven debugging for complex, intermittent, and production-only bugs.
by Joker
7-type AIGC routing, LLM selection, prompt engineering, content QC, monetization paths, 2026 trends.
Design, diagnose, and optimize high-performance RAG systems with an engineering-first framework.
by Joker
OCR routing (Tesseract/PaddleOCR/EasyOCR/API), preprocessing, post-processing, batch processing, 2026 insights.
The migration ran instantly in staging and locked a 40-million-row table in production for nine minutes — because staging had 400 rows
by Joker
Governance framework, data quality, metadata, compliance, data lineage, 2026 trends.
Hardens AI prompts and agent workflows against logic errors, tool-misuse, and prompt injection.
Build an implementation-ready analytics tracking plan from your product questions, stack, and consent constraints.
by Nex AI
Generate structured architectural technical specifications and draft 'lastenboeken' from project descriptions.
by Joker
Model selection matrix (MJ/Flux/SD), composition rules, 3-level quality gates, 10 style recipes.
by Corey Jacobs
Run a buyer-readiness check before publishing an AI agent skill package.
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.
by Nex AI
Manage multiple Postgres versions and extensions on one Linux box with a port registry and unified backups.
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 Timoranjes
Expert-level SQL tuning and performance auditing for PostgreSQL, MySQL, SQLite, and SQL Server.
by Corey Jacobs
Convert a repeatable workflow into a reusable agent skill or staged skillchain candidate.
by Dan Timms
Transform raw transcripts into role-specific action plans for Engineering, Sales, Product, and Leadership.
by Kaymue
Pre-merge PR quality gate. 40+ checks: diff size, tests, security, conventional commits, breaking changes, reviewer routing.
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.
Write and review the docs AI agents actually read — AGENTS.md for your repo and llms.txt for your site. Drafts them from scratch or audits existing ones for completeness, clarity, and wasted context, with a PASS or REVISE verdict.
by Al1as
Map the geometry of system failures to transform edge-case chaos into structured architectural governance.
Architectural strategist that converts flat prompts into structured, multi-file ChatGPT Skill blueprints.
by SkillForge
Force your AI agent to apply senior-level architectural judgment and design notes before writing any code.