Ship agent workflows in 30 seconds. Browse 2,000+ expert-built and security scanned skill -> Browse skills
THE AGENSI STORE
38 skills found
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.
Diagnose and fix context-window problems in your agent setup. Inventories everything that loads — memory files, skills, MCP tool definitions, hooks — estimates where the budget goes, maps your symptoms to causes, and prescribes concrete trims, restructures, and session habits, rewriting the files where that's the fix.
by Corey Jacobs
This skill allows for focused tool trace receipts to help debug and fine tune Agents
Design the right team of specialized AI subagents for your project and get the definition files written properly — precise delegation triggers, focused system prompts, least-privilege tools, and the right model tier for each job. Includes a template, orchestration patterns, and a complete sample team.
Turn an error, stack trace, and logs into a structured root-cause diagnosis — reconstructed failure, ranked hypotheses with evidence, the most likely cause, and the cheapest next diagnostic or fix. The disciplined pass a senior engineer runs, instead of scattershot guess-and-check.
Red-team your own AI agent for prompt-injection and tool-misuse vulnerabilities before it ships — then fix them. Maps your attack surface, generates a defensive test plan with the safe behavior expected for each case, and gives a prioritized mitigations list. Defensive use only.
Draft the AI documentation the EU AI Act expects — model cards, AI-use disclosures, transparency notices, risk-tier worksheets, and technical-doc skeletons. Counsel-ready drafts from a regulated-industry documentation professional, with templates included.
Before you send proprietary or sensitive data to an AI vendor, assess the risk. Classifies what's actually your moat versus regulated, contractual, or harmless data, maps the real exposure vectors by vendor tier, lists the questions to get in writing, and gives a send / send-with-controls / keep-in-house recommendation per data type.
by Shandra
Creates and optimizes YouTube titles, descriptions, tags, hashtags, pinned comments, thumbnail text ideas, and viewer-focused video positioning.
by PromptWagon
Creates practical, repeat-use YouTube descriptions, chapters, CTAs, links, pinned comments, SEO keyword notes, resource sections, affiliate/sponsor disclosure placeholders, and publishing checklists for creators, educators, businesses, podcasters, and content teams.
by PromptWagon
Turns one blog post, video, podcast, product, newsletter, offer, lesson, or long-form idea into Instagram posts, carousels, Reels, Stories, captions, hooks, CTAs, content calendars, and repurposing workflows for creators, small businesses, coaches, consultants, educators, and digital product sellers.
by PromptWagon
Creates Instagram carousel content packages for coaches, creators, consultants, educators, small businesses, and digital product sellers, including carousel slide structures, hooks, slide-by-slide copy, captions, CTAs, design briefs, visual direction, content angles, repurposing notes, and publishing checklists.
by PromptWagon
Creates Pinterest traffic assets and strategy for digital products, Etsy listings, blog posts, templates, printables, prompt packs, and creator shops. Generates pin titles, descriptions, board ideas, SEO keywords, pin text overlays, content angles, posting plans, CTA copy, and traffic-focused optimization notes.
by Timoranjes
Teaches AI coding agents to detect when they're stuck in a repeating action loop (same file edit, same tool call, same error pattern) and break out before burning tokens. Uses a three-layer detection