mouadja02
- 874 skills
- 0 followers
- 13 repo stars
- 5 days ago last updated
- ▌ Timestream Influxdb · mouadja02 bundleRetrieves authoritative guidance on Amazon Timestream for InfluxDB (managed InfluxDB 2, InfluxDB 2 Read Replica Clusters, InfluxDB 3 Core and Enterprise). Applicable to any InfluxDB-on-AWS request including engine selection, provisioning (Marketplace + AmazonTimestreamInfluxDBFullAccess/ConsoleFullAccess IAM), schema design (tags vs fields, cardinality, HTTP/sensor/metric data modeling), migration from LiveAnalytics, Processing Engine plugins, connectivity (port 8086 V2, port 8181 V3, VPC-only by default), and write/query errors.
- ▌ Azure Deployment Preflight · mouadja02 bundleBicep deployment preflight — syntax validation, what-if, permission checks before azd provision
- ▌ Filesystem Context · mouadja02 bundleThis skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.
- ▌ Mini Context Graph · mouadja02 bundleA persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph. Ingest documents once — the LLM writes wiki pages, extracts entities/relations into the graph, and stores raw content for evidence retrieval. Knowledge accumulates and cross-references; it is never re-derived from scratch.
- ▌ Image Manipulation Image Magick · mouadja02Process and manipulate images using ImageMagick. Supports resizing, format conversion, batch processing, and retrieving image metadata
- ▌ Microsoft Code Reference · mouadja02Look up Microsoft API references, find working code samples, and verify SDK code is correct
- ▌ Senior Data Engineer · mouadja02 bundleData engineering — pipelines, ETL/ELT, Python/SQL/Spark, Airflow, dbt, cloud DWH
- ▌ Tech Stack Evaluator · mouadja02 bundleTechnology stack evaluation and comparison with TCO analysis, security assessment, and ecosystem health scoring
- ▌ Gtm Enterprise Onboarding · mouadja02Four-phase framework for onboarding enterprise customers from contract to value realization
- ▌
- ▌ Openrouter Agent Migration · mouadja02 bundle> **Attribution:** Sourced from [OpenRouterTeam/skills](https://github.com/OpenRouterTeam/skills) by [OpenRouter](https://openrouter.ai).
- ▌ Qdrant Scaling Qps · mouadja02Use when Qdrant must handle more parallel queries per second and per-query latency is not the priority. Covers fewer, larger segments, quantization in RAM, and replication — the opposite tuning direction from latency.
- ▌ Content Humanizer · mouadja02 bundleMakes AI-generated content sound genuinely human — not just cleaned up, but alive
- ▌ Marketing Context · mouadja02 bundleCreate and maintain the marketing context document that all marketing skills read before starting
- ▌ Agile Product Owner · mouadja02 bundleAgile product ownership for backlog management and sprint execution. Covers user story writing, acceptance criteria, sprint planning, and velocity tracking
- ▌ Experiment Designer · mouadja02 bundleA/B and multivariate experiments — hypothesis, sample size, ICE priority, stats significance
- ▌
- ▌ React19 Source Patterns · mouadja02 bundleReference for React 19 source-file migration patterns, including API changes, ref handling, and context updates.
- ▌ Agentic Browser Automation · mouadja02 bundleBuild AI-powered browser agents that autonomously navigate, scrape, fill forms, and extract data from dynamic websites using LLM reasoning + Playwright
- ▌ Rich Claude Code Tui Clone · mouadja02 bundleUse when building a Python terminal UI inspired by Claude Code with Rich. Translates a detailed TypeScript/Ink-style visual reference into a staged Python architecture for logo, message stream, streaming Markdown, tools, diffs, prompt, footer, spinners, permissions, transcript mode, themes, accessibility, and tests. Separates Rich rendering from the input and widget responsibilities that require an application-owned event loop or an optional Textual layer.
- ▌ Agent Trajectory Diagnostics · mouadja02Use when diagnosing agent benchmarks or runtime failures from trajectories instead of aggregate pass rates. Builds shared action-observation decision landscapes, identifies productive cores and trap regions, profiles Access/Trap/Repair behavior, and designs conservative trap-triggered recovery experiments.
- ▌ Skill Lifecycle Optimization · mouadja02Use when improving, evolving, benchmarking, or maintaining agent skills over time. Treats skills as long-lived structured artifacts: execute tasks, diagnose trajectory evidence, accumulate textual momentum, patch at the correct abstraction layer, test per model and harness, canary changes, and roll back regressions.
- ▌ Openapi To Application Code · mouadja02Generate a complete, production-ready application from an OpenAPI specification
- ▌ Python Pypi Package Builder · mouadja02 bundleBuild, test, lint, version, publish Python library to PyPI — all build tool flavors
- ▌ Org Health Diagnostic · mouadja02 bundleCross-functional organizational health check combining signals from all C-suite roles. Scores 8 dimensions on a traffic-light scale with drill-down recommendations
- ▌ Managing Amazon Msk · mouadja02 bundleOperates Amazon MSK Provisioned clusters (Standard and Express brokers). MUST be used for ANY MSK Provisioned task — do not rely on training data for topics covered here, since Standard and Express emit different metrics and follow different patching models that training data routinely conflates. Covers performance, consumer lag, storage, and traffic shaping diagnosis; sizing and choosing Standard vs Express; Kafka client tuning; creating CloudWatch alarms, dashboards, monitoring, and cluster configurations; AND MSK maintenance, patching, version upgrades, and rolling-restart behavior. Triggers: MSK, Kafka on AWS, `kafka.*` or `express.*` instance types, AWS/Kafka CloudWatch namespace, alarms, dashboards, monitoring, consumer lag, partition replication, broker storage, MSK upgrades, patching, maintenance windows, SECURITY_PATCHING, BROKER_UPDATE, rolling restarts, unexpected broker reboots. Do NOT use for MSK Connect, MSK Serverless, or MSK Replicator.
- ▌ Querying AWS S3 · mouadja02Queries S3 object metadata, tracks bucket activity, audits object changes, searches annotations, and analyzes storage metrics using S3 Metadata system tables (journal, inventory, annotation) and S3 Storage Lens tables via Athena SQL. Applies when counting objects, finding recent uploads or deletions, identifying who wrote to a prefix, breaking down storage classes, finding objects by tag, searching annotation content, analyzing storage lens metrics, or enabling S3 Metadata tracking. Prefers system tables over raw S3 APIs (list-objects-v2, head-object) at scale. Trigger phrases: bucket activity, object count, who uploaded, track deletions, storage class breakdown, find by tag, search annotations, storage lens metrics, audit bucket changes.
- ▌ Appinsights Instrumentation · mouadja02 bundleInstrument a webapp to send useful telemetry data to Azure App Insights
- ▌ Update Avm Modules In Bicep · mouadja02Update Azure Verified Modules (AVM) to latest versions in Bicep files.
- ▌ Context Compression · mouadja02 bundleThis skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
- ▌ Context Degradation · mouadja02 bundleThis skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
- ▌
- ▌ Linkedin Post Formatter · mouadja02 bundleLinkedIn posts — Unicode bold/italic, visual separators, structured sections, hooks
- ▌ Senior Data Scientist · mouadja02 bundleSenior data scientist — stats modeling, causal inference, ML, Python/pandas/sklearn/PyMC
- ▌ Multimodal RAG Architecture · mouadja02 bundleUse when designing or auditing RAG over PDFs, images, tables, charts, equations, video frames, or heterogeneous documents where text-only chunking loses important evidence.
- ▌ Qdrant Monitoring Debugging · mouadja02Use when a Qdrant deployment misbehaves — slow queries, memory pressure, stuck optimizers, unhealthy shards, or failed replicas. Covers the metrics and telemetry endpoints to inspect and how to read them.
- ▌ Content Production · mouadja02 bundleFull content production pipeline — takes a topic from blank page to published-ready piece
- ▌ Power Platform Architect · mouadja02Use this skill when the user needs to transform business requirements, use case descriptions, or meeting transcripts into a technical Power Platform solution architecture, including component selection and Mermaid.js diagrams
- ▌ Update Specification · mouadja02Update an existing specification file for the solution, optimized for Generative AI consumption based on new requirements or updates to any existing code
- ▌ Framework Flutter Expert · mouadja02 bundleUse when the user asks to work on a Flutter or Dart project. Triggers on keywords Flutter, Dart, BLoC, Mobile App.
- ▌ Copilot Usage Metrics · mouadja02 bundleRetrieve and display GitHub Copilot usage metrics for organizations and enterprises using the GitHub CLI and REST API.
- ▌ Auto Memory Review · mouadja02Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics.
- ▌ Auto Memory Status · mouadja02Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations.
- ▌ Transloadit Media Processing · mouadja02Process media files (video, audio, images, documents) using Transloadit
- ▌ AWS Lambda Microvms · mouadja02 bundleBuilds, runs, debugs, and operates applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments running inside a container with up to 8 hr lifetimes. Applicable when workloads need strong isolation between tenants, isolated serverless compute, sandbox compute, or secure multi-tenant execution. Also suited for AI/agent code-execution sandboxes, interactive code playgrounds and notebooks (Jupyter, REPLs, dev environments running user-supplied code), reinforcement-learning environments, multi-tenant CI executors and build runners, sessionful game or simulation servers, or isolated security scanners. Also applicable when the workload needs long-lived sessions, a real port-listening server (gRPC, WebSocket, custom TCP protocols), state preserved across periods of inactivity (suspend/resume), container-level access (FUSE, eBPF, custom syscalls), or session-affine routing.
- ▌ Azure Architecture Autopilot · mouadja02 bundleDesign Azure infrastructure using natural language, or analyze existing Azure resources to auto-generate architecture diagrams, refine them through conversation, and deploy with Bicep. When to use this skill: - "Create X on Azure", "Set up a RAG architecture" (new design) - "Analyze my current Azure infrastructure", "Draw a diagram for rg-xxx" (existing analysis) - "Foundry is slow", "I want to reduce costs", "Strengthen security" (natural language modification) - Azure resource deployment, Bicep template generation, IaC code generation - Microsoft Foundry, AI Search, OpenAI, Fabric, ADLS Gen2, Databricks, and all Azure services
- ▌ Context Fundamentals · mouadja02 bundleThis skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.
- ▌ Context Optimization · mouadja02 bundleThis skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.
- ▌ Oo Component Documentation · mouadja02 bundleCreate or update standardized object-oriented component documentation using a shared template plus mode-specific guidance for new and existing docs
- ▌ Readme Blueprint Generator · mouadja02README.md generator — install, usage, API, contribution sections from project structure
- ▌ Cs Pricing Strategy · mouadja02 bundleDesign, optimize, and communicate SaaS pricing — tier structure, value metrics, pricing pages, and price increase strategy
- ▌ Power Bi Dax Optimization · mouadja02Comprehensive Power BI DAX formula optimization prompt for improving performance, readability, and maintainability of DAX calculations
- ▌ Creating Amazon Aurora DB Cluster With Instances · mouadja02 bundleCreates a complete Amazon Aurora database cluster with instances, handling cluster creation, instance provisioning, and Secrets Manager password management in the proper sequence. Use when setting up new Aurora MySQL or PostgreSQL clusters with production-ready configuration.
- ▌ Using Streamlit Markdown · mouadja02Covers all Markdown features in Streamlit including GitHub-flavored syntax plus Streamlit extensions like colored text, badges, Material icons, and LaTeX
- ▌ Creating Streamlit Themes · mouadja02Use when customizing a Streamlit app's look — theme config options, colors and fonts, light and dark handling, and per-app branding.
- ▌ Displaying Streamlit Data · mouadja02Use when rendering data in Streamlit — dataframes, tables, metrics, and charts. Covers choosing between st.dataframe, st.table, st.metric, and the built-in chart elements versus Plotly, Altair, or Matplotlib.
- ▌ Organizing Streamlit Code · mouadja02Use when deciding how to structure a Streamlit app's files — when to keep everything in one streamlit_app.py, when to split into modules, and how to separate data processing from UI code.
- ▌ Memory Usage Optimization · mouadja02Use when diagnosing Qdrant resident-memory pressure, page-cache confusion, optimization headroom, or RAM-versus-disk placement.
- ▌ Search Speed Optimization · mouadja02Use when diagnosing slow Qdrant queries, low search throughput, filtered-search regressions, or optimizer interference.
- ▌ Building Streamlit Chat UI · mouadja02Use when building a chat or conversational interface in Streamlit — st.chat_message and st.chat_input, streaming responses, and keeping history in session state.
- ▌ Improving Streamlit Design · mouadja02Use when a working Streamlit app looks rough — visual hierarchy, spacing, typography, and layout choices that make the app read as designed rather than default.
- ▌ Building Streamlit Dashboards · mouadja02Use when building a data dashboard in Streamlit — arranging metrics and charts, wiring filters and inputs, and structuring the page so reruns stay fast.
- ▌ Using Streamlit Session State · mouadja02Using st.session_state to manage state across Streamlit reruns
- ▌ Bmad Check Implementation Readiness · mouadja02 bundleValidate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness".
- ▌ Optimizing Streamlit Performance · mouadja02Use when a Streamlit app feels slow — caching with st.cache_data and st.cache_resource, reducing rerun work, fragments, and handling large dataframes.
- ▌ Setting Up Streamlit Environment · mouadja02Use when creating or fixing the Python environment for a Streamlit app — choosing between pip, poetry, conda, and uv, pinning to the latest Streamlit, and setting up an isolated environment before the app runs.
- ▌ Building Streamlit Multipage Apps · mouadja02Use when a Streamlit app needs more than one page — the pages directory, st.navigation and st.Page, and sharing state across pages.
- ▌ Connecting Streamlit To Snowflake · mouadja02Use when a Streamlit app must read from or write to Snowflake — st.connection, secrets handling, caching query results, and Streamlit in Snowflake considerations.
- ▌ Using Streamlit Custom Components · mouadja02Use when Streamlit's core API lacks a needed feature and a third-party community component may fill the gap — finding, installing, evaluating, and wiring up custom components.
- ▌ Configuring Vpc Endpoints For Private AWS Service Access · mouadja02 bundleConfigures VPC endpoints (interface and gateway) for private AWS service access using AWS PrivateLink. Use when setting up secure private connectivity to S3, DynamoDB, and other AWS services without internet gateway, NAT device, or public IP addresses. Covers endpoint creation, security groups, route tables, and DNS configuration.
- ▌ Indexing Performance Optimization · mouadja02Use when diagnosing slow Qdrant ingestion, delayed optimizer completion, long HNSW builds, or payload-index construction.
- ▌ Developing Applications On Managed Service For Apache Flink · mouadja02 bundleMANDATORY for Flink or Amazon Managed Service for Apache Flink (MSF) questions. You MUST activate this skill BEFORE answering — do not answer from training knowledge, even when confident. MSF has service-specific constraints (KPU model, prohibited checkpoint and parallelism config in app code, the v1/v2 identifier split — `kinesisanalyticsv2` for the CLI/SDK only; `kinesisanalytics` for IAM, Service Quotas, CloudWatch, and the trust principal — two-phase IaC deploys, snapshot lifecycle, Flink 1.x→2.x migration) that override generic Flink knowledge.
- ▌ Choosing Streamlit Selection Widgets · mouadja02Use when picking a Streamlit input widget for choosing among options — segmented_control, pills, selectbox, multiselect, radio, or feedback. Covers which to use when all options should stay visible versus hidden in a dropdown, and which older patterns are now anti-patterns.
- ▌ Building Streamlit Custom Components V2 · mouadja02 bundleBuilds bidirectional Streamlit Custom Components v2 (CCv2) using `st.components.v2.component`