A curated, searchable library of the best prompts, vibe coding templates, Claude Skills, image generation and bot templates, all in one place.
Cancel anytime
Five stars, from people using PromptLLM every day.
Security audit: supported static findings; qualified profiles add reproduction and repair candidates. Use when: "security audit", "threat model", "OWASP", "CSO review", "recheck a vulnerability".
Technical leadership guidance for engineering teams, architecture decisions, and technology strategy.
/cs:cto-review — CTO Forcing Questions skill. /cs:cto-review <plan> — Architecture and scaling interrogation. Tech debt, scaling cliffs, team scaling, build-vs-buy.
Build, measure, and evolve company culture as operational behavior — not wall posters. Covers mission/vision/values workshops, values-to-behaviors translation, culture code creation, culture health assessment, and cultural rituals by stage.
Customer Research skill — when the user wants to conduct, analyze, or synthesize customer research.
Monitors customer health, predicts churn risk, and identifies expansion opportunities using weighted scoring models for SaaS customer success.
Audit datasets for completeness, consistency, accuracy, and validity. Profile data distributions, detect anomalies and outliers, surface structural issues, and produce an actionable remediation plan.
Database Designer - POWERFUL Tier Skill skill. Use when the user asks to design database schemas, plan data migrations, optimize queries, choose between SQL and NoSQL, or model data relationships.
Database Schema Designer skill. Use when the user asks to create ERD diagrams, normalize database schemas, design table relationships, or plan schema migrations.
deal-desk skill. Use when reviewing a specific inbound deal before close — when sales has asked for a discount that exceeds AE authority, when the customer has redlined the MSA, when per-deal economics (margin after discount, multi-year payment shape, indemnity exposure) need to be quantified, or when discount…
/cs:freeze — Cooldown Lock on a Decision skill. /cs:freeze <decision> <days> — Lock a strategic decision for a cooldown period to prevent impulse reversal. Mirrors gstack's safety primitives for the business layer.
/cs:decide — Log the Decision skill. /cs:decide <memo> — Log a decision to two-layer memory via decision-logger. Approved memo becomes durable; raw transcripts kept for reference.
Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2).
/cs:post-mortem — Honest Retrospective skill. /cs:post-mortem <decision> — Honest retrospective on an executed decision, scored against original assumptions and dissent. Closes the strategic sprint loop.
Study companion and working knowledge base for the Deep Learning textbook, read free at deeplearningbook.org.
DeepRead skill. Use when the user asks to deeply read a book, article, PDF, or document set; extract claims and evidence; build a knowledge map; or learn through Feynman explanation and recall. Covers quick, deep, map, Feynman, and whole-book reading modes.
Run a disciplined, multi-source research investigation for a high-stakes question or decision — fan-out web search across many channels, parallel sub-agents, source triangulation (each claim backed by ≥3 independent sources), an adversarial review pass, and every source saved to its own file…
Deep Work — Time-Block the Day, Budget the Shallow skill. Use when someone wants to plan a deep work day, time-block their calendar or task list, budget or cut shallow work, protect focus hours, track deep-work sessions and streaks, run an end-of-day shutdown ritual, or says "/deep-work" or "/time-block".
Demo Video skill. Use when the user asks to create a demo video, product walkthrough, feature showcase, animated presentation, marketing video, or GIF from screenshots or scene descriptions. Orchestrates playwright, ffmpeg, and edge-tts MCPs to produce polished video content.
Audit and manage dependencies across multi-language projects. Identifies vulnerabilities, license conflicts, transitive dependency risks, and safe-upgrade paths.
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots.
Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview pages. Creates DESIGN.md as your project's design source of truth.
Design finalization: generates production-quality Pretext-native HTML/CSS. Works with approved mockups from /design-shotgun, CEO plans from /plan-ceo-review, design review context from /plan-design-review, or from scratch with a user description.
Designer's eye plan review — interactive, like CEO and Eng review. Rates each design dimension 0-10, explains what would make it a 10, then fixes the plan to get there.

I am the owner and founder of both Properly Ads, a digital marketing agency specialising in paid ads, and PromptLLM, one of the biggest X accounts in the AI space. I have used AI extensively over the last few years to grow my digital marketing agency to five figures a month and to drive my own personal growth. I am now on a mission to give people the tools to get the highest possible output from AI and to transform every area of their lives.
Have a question? Email me at sam@promptllm.co