Mostafa Ahmed
- 36 skills
- 0 followers
- 1.2k repo stars
- 2 days ago last updated
- ▌ Minimalist · itsmostafa bundleUse before writing, editing, fixing, refactoring, or reviewing ANY code, including small routine changes you could make without help: those are exactly where over-building slips in. Keeps the change minimal: YAGNI, reuse what the codebase already has, stdlib and native platform features before custom code or new dependencies, shortest working diff. Also use when the user asks for the simplest way, invokes YAGNI, or complains about over-engineering or bloat. Not for non-coding requests.
- ▌ Evidence Review · itsmostafa bundleReview a code change against its spec and the repo's own conventions, and report only findings you have proven: reproduced bugs, unmet requirements, code nothing needs, and broken house rules, ending in a PASS or FIX verdict.
- ▌ Readme Marketer · itsmostafa bundleRewrites technical READMEs to improve conversion, user onboarding, and product marketing.
- ▌ Write Instructions · itsmostafa bundleWrite or rewrite instructions that must be followed exactly and checked: SOPs, runbooks, deployment and rollback plans, incident procedures, checklists, and multi-step plans or prompts for AI agents. Each step gets a precondition, a checkable result, and a failure path that ends safely. Use when the user asks for a procedure, runbook, SOP, step-by-step plan or agent instructions, or wants an existing procedure made verifiable, even if they don't name this skill.
- ▌ Writing Clearly And Concisely · itsmostafa bundleUse when writing or editing prose humans will read—blog posts, social media posts, documentation, READMEs, announcements, explanations, reports, commit messages, error messages, or UI text. Applies Steven Pinker's classic style and curse-of-knowledge remedies so readers outside your head can follow, and strips the hype and filler that make text read as AI-written.
- ▌ Qi CLI · itsmostafaGuide for using qi, a local knowledge search CLI for macOS and Linux. Use this skill when the user wants to index documents into a searchable knowledge base, search or retrieve from one, configure qi's collections or embedding providers (Ollama, OpenAI-compatible), choose between its search modes (BM25, hybrid, vector), or diagnose why qi search results look wrong — or on any mention of the qi CLI.
- ▌ Explain · itsmostafa bundleExplain any topic simply for a newcomer — a concept, a system, a process, or part of a codebase — and save it as an HTML page with compiled architecture, workflow, sequence, data-flow, and lifecycle diagrams. Use when the user types /explain <topic>.
- ▌ Taskfile · itsmostafaExpert guidance for Taskfile (taskfile.dev) — the YAML task runner. Use when creating, editing, debugging, or optimizing a Taskfile.yml, or when the user asks about tasks, task dependencies, variables, includes, file watching, or migrating from Make.
- ▌ Systems Thinking · itsmostafa bundleA rigorous cause-and-effect thinking discipline for reasoning about non-trivial problems, drawn from the Theory of Constraints Logical Thinking Process. Use it BEFORE proposing a fix, plan, or recommendation whenever a problem is more than a simple lookup or mechanical edit: debugging that isn't yielding, "why does X keep happening", root-cause or incident analysis, architecture and design decisions, tradeoffs and either/or conflicts ("should we do A or B"), evaluating whether a proposed solution will actually work, refactors, strategy, or any recurring/systemic issue. It helps you separate symptoms from root causes, find the one constraint that limits the outcome, validate every causal claim with eight logical tests, break conflicts instead of splitting the difference, and stress-test a solution for side effects before committing. Reach for it even when the user hasn't named a "method" — if you're about to explain a cause or recommend an action on a hard problem, run this first.
- ▌ Context Engineering · itsmostafa bundleStrategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.
- ▌ Pytorch · itsmostafa bundleBuilding and training neural networks with PyTorch. Use when implementing deep learning models, training loops, data pipelines, model optimization with torch.compile, distributed training, or deploying PyTorch models.
- ▌ Transformers · itsmostafa bundleLoading and using pretrained models with Hugging Face Transformers. Use when working with pretrained models from the Hub, running inference with Pipeline API, fine-tuning models with Trainer, or handling text, vision, audio, and multimodal tasks.
- ▌ Prompt Engineering · itsmostafaCrafting effective prompts for LLMs. Use when designing prompts, improving output quality, structuring complex instructions, or debugging poor model responses.
- ▌ Lora · itsmostafa bundleParameter-efficient fine-tuning with Low-Rank Adaptation (LoRA). Use when fine-tuning large language models with limited GPU memory, creating task-specific adapters, or when you need to train multiple specialized models from a single base.
- ▌ Rlhf · itsmostafa bundleUnderstanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.
- ▌ Qlora · itsmostafaMemory-efficient fine-tuning with 4-bit quantization and LoRA adapters. Use when fine-tuning large models (7B+) on consumer GPUs, when VRAM is limited, or when standard LoRA still exceeds memory. Builds on the lora skill.
- ▌ Agents · itsmostafaPatterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.
- ▌ Mlx · itsmostafa bundleRunning and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging Face models to MLX format, fine-tuning with LoRA/QLoRA on Apple Silicon, or serving models via HTTP API.
- ▌ Lambda · itsmostafa bundleCreate, configure, and manage AWS Lambda serverless functions for event-driven compute, including triggers, debugging, cold start optimization, and layers.
- ▌ Bedrock · itsmostafa bundleAccess AWS Bedrock foundation models for generative AI, including text generation, embeddings, and image generation, with CLI and Python examples.
- ▌ Cognito · itsmostafa bundleSet up and manage AWS Cognito user pools, identity pools, OAuth flows, and user authentication with CLI commands and Python SDK examples.
- ▌ Dynamodb · itsmostafa bundleDesign DynamoDB table schemas, write queries, configure indexes, manage capacity, and troubleshoot performance issues using AWS CLI and boto3 examples.
- ▌ Cloudwatch · itsmostafa bundleMonitor AWS resources and applications using CloudWatch logs, metrics, alarms, and dashboards with CLI and boto3 examples.
- ▌ API Gateway · itsmostafa bundleManage AWS API Gateway for creating, publishing, and securing REST, HTTP, and WebSocket APIs using CLI commands, SAM templates, and best practices.
- ▌ Eventbridge · itsmostafa bundleCreate and manage Amazon EventBridge event buses, rules, event patterns, and targets for event-driven architectures.
- ▌ Cloudformation · itsmostafa bundleManage AWS infrastructure as code with CloudFormation templates, stacks, change sets, and nested stacks.
- ▌ Step Functions · itsmostafa bundleDesign, build, and manage AWS Step Functions state machines for serverless workflow orchestration, including error handling, parallel execution, and integration with AWS services.
- ▌ Secrets Manager · itsmostafa bundleStore, retrieve, and automatically rotate credentials, API keys, and other secrets using AWS Secrets Manager.
- ▌ S3 · itsmostafa bundleManage AWS S3 buckets and objects: create buckets, upload/download files, configure lifecycle policies, set up static websites, manage permissions, and implement cross-region replication.
- ▌ Ec2 · itsmostafa bundleManage AWS EC2 virtual machines — instances, security groups, key pairs, AMIs, EBS volumes, Auto Scaling Groups, Spot Instances, Session Manager, placement groups, and instance lifecycle automation.
- ▌ Ecs · itsmostafa bundleDeploy and manage Docker containers on AWS ECS with Fargate or EC2, including task definitions, services, auto scaling, and troubleshooting.
- ▌ Eks · itsmostafa bundleManage Amazon EKS clusters, node groups, IRSA, add-ons, and deployments using AWS CLI and eksctl.
- ▌ Iam · itsmostafa bundleManage AWS Identity and Access Management for users, roles, policies, and permissions. Create IAM policies, configure cross-account access, set up service roles, troubleshoot permission errors, and enforce least-privilege security.
- ▌ Rds · itsmostafa bundleManage AWS RDS relational databases: provision instances, configure backups, manage replicas, troubleshoot connectivity, and optimize performance.
- ▌ Sns · itsmostafa bundleCreate and manage SNS topics, subscriptions, and message publishing for pub/sub messaging patterns.
- ▌ Sqs · itsmostafa bundleManage AWS SQS queues, send and receive messages, configure dead-letter queues, and integrate with Lambda using CLI commands and Python boto3 examples.