Claude Skills by paulasilvatech

Generate technology-agnostic blueprints for comprehensive copilot-instructions.md files that make GitHub Copilot follow exact project versions, architecture, code quality, documentation, testing, and versioning conventions discovered from the codebase. Use this skill when the user asks for configuration variables, wants to create copilot-instructions.md, or needs repository-specific GitHub Copilot coding guidance.

Analyze a repository and generate Project_Folders_Structure_Blueprint.md with detected technologies, folder purposes, naming conventions, file placement patterns, navigation guidance, build outputs, and optional structure templates. Use this skill when the user asks for a project folder structure blueprint, repository organization map, architecture directory guide, monorepo or microservices structure analysis, or file placement conventions.

Generate technology-agnostic project workflow analysis blueprints that document end-to-end application flows, files, classes, entry points, service layers, data access, error handling, async processing, sequence diagrams, testing patterns, and implementation templates. Use this skill when the user asks to list all files/classes in a workflow, document representative workflows, map an API-to-database flow, or create an implementation-ready workflow blueprint.

Generate a comprehensive README.md blueprint by analyzing repository documentation, .github/copilot files, copilot-instructions.md, architecture notes, technology stack, workflow, standards, tests, and exemplars. Use when asked to create or refresh a developer-focused README.

Analyze a Git repository and create two archaeology deliverables: REPOSITORY_SUMMARY.md with technical architecture and THE_STORY_OF_THIS_REPO.md with a narrative from commit history. Use when asked to summarize a repo, explain its architecture, inspect git history, identify contributors, or tell the story of repository evolution.

Generate a technology stack blueprint by analyzing codebase languages, frameworks, dependencies, versions, licenses, conventions, usage patterns, tooling, infrastructure, and diagrams. Use this skill when the user asks for a stack blueprint, architecture technology inventory, implementation-ready tech map, dependency and convention documentation, or guided development baseline.

Build a concise map of files relevant to a requested code change before implementation. Use when the user asks to identify affected files, plan changes, map dependencies, find tests, locate reference patterns, or assess risk before editing.

Create a concrete, evidence-backed plan before a multi-file refactor. Use this skill when the user asks to plan, sequence, scope, or safely execute a refactor across multiple files, when hidden coupling is likely, or when implementation should wait for confirmation after a plan.

Identify the minimum files, symbols, configuration, tests, and prior context GitHub Copilot needs before answering a codebase question. Use this skill when the user asks what context is needed, what files to provide, or wants a context checklist before asking an implementation, debugging, review, or architecture question.

Discover and integrate third-party APIs with the context-matic MCP server using fetch_api, ask, model_search, endpoint_search, add_guidelines, add_skills, and update_activity. Use this skill when the user asks to integrate a third-party API, add an API client or SDK, implement features with an external API, or work with PayPal, Twilio, or another third-party API.

Guided onboarding tour for the context-matic MCP server. Use this skill when the user asks what ContextMatic can do, wants a first-time tour, asks to show available APIs, asks how to use the context-matic server, or wants live model_search and endpoint_search demonstrations before integration.

Convert Excel .xlsx workbooks to Markdown with the bundled script so spreadsheet contents can be read, summarized, searched, extracted, compared, charted, or analyzed. Use whenever the user references a spreadsheet, workbook, budget, export, tracker, .xlsx file, or a folder of workbooks; invoke sibling converters for mixed .pdf, .docx, and .xlsx sets.

Convert PDF .pdf documents to Markdown with the bundled script so reports, papers, invoices, forms, contracts, scanned documents, and folders of PDFs can be read, summarized, searched, extracted, compared, or analyzed. Use whenever a user references a PDF; invoke sibling converters for mixed .pdf, .docx, and .xlsx sets.

Convert Word .docx documents into Markdown with extracted images using the bundled script. Use this skill when a user asks to read, summarize, review, compare, analyze, extract data from, or batch-process Word documents, resumes, reports, contracts, or proposals, including mixed folders that also require sibling PDF or Excel conversion skills.

Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal. Use when a user wants Skills for a multi-step workflow, asks which Skills fit a project, needs an installed-Skill audit or conflict check, has low Skill recall, wants indirect helpers such as humanizers or compliance checks, or wants a project-specific Skill Stack with controlled installation. Search local Skills, registries, GitHub, and OpenCLI; compare adoption, verified fit,...

Help users install and use John Papa's ai-ready skill as the up-to-date source for making repositories AI-ready with AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and stack-specific guidance. Use when the user asks to make a repo ai-ready, set up AI config, prepare for AI contributions, or install ai-ready.

Refine a rough task request into a high-quality markdown prompt by clarifying scope, deliverables, constraints, context, and success criteria, then copy the final prompt to the clipboard with Joyride. Use when the user asks to improve, boost, rewrite, or polish a prompt without writing code. Requires Joyride.

Interactive training for the GitHub Copilot CLI through guided lessons, quizzes, scenario challenges, a final exam, and on-demand reference for slash commands, shortcuts, modes, agents, skills, MCP, and configuration. Use when the user says "cliexpert", asks to learn the Copilot CLI, wants a quiz, scenario, challenge, cheat sheet, or final exam.

Use this skill when someone wants to learn GitHub Copilot CLI from scratch. Offers interactive step-by-step tutorials with separate Developer and Non-Developer tracks, plus on-demand Q&A. Just say "start tutorial" or ask a question! Note: This skill targets GitHub Copilot CLI specifically and uses CLI-specific tools (ask_user, sql, fetch_copilot_cli_documentation).

Author current GitHub Copilot agents, instructions, and VS Code prompts in this repository. Use when asked to create or update a known primitive type with repository governance, dated evidence, canonical sources, templates, synchronization, and type-specific validation.

Use GitHub Copilot Spaces to provide project-specific context to conversations. Use this skill when users mention a "GitHub Copilot space", want to load context from a shared knowledge base, discover available spaces, or ask questions grounded in curated project documentation, code, and instructions.

Retrieve and display GitHub Copilot usage metrics for organizations and enterprises using the GitHub CLI, REST API, and bundled scripts. Use when the user asks about Copilot usage, adoption, active users, acceptance rates, suggestions, chat interactions, per-user breakdowns, organization metrics, enterprise metrics, or usage on a specific date.

Polish an AI agent prompt file for end-user use by preserving frontmatter, encoding, markdown structure, and intent while improving clarity, organization, grammar, and instruction quality. Use when the user asks to finalize, refine, or review an agent prompt from the current role before delivery.

Generate GitHub Copilot migration and code-evolution instructions by comparing branches, commits, tags, or releases and extracting transformation rules. Use when the user is doing framework upgrades, architecture refactors, technology migrations, dependency updates, pattern changes, API changes, obsolete pattern avoidance, and preserving project conventions during future code modifications.

Bootstrap a complete GitHub Copilot customization for a repository, including .github/copilot-instructions.md, scoped instruction files, reusable skills, custom agents, and optional copilot-setup-steps.yml. Use this skill when the user asks to set up GitHub Copilot for a new project, create Copilot instructions/skills/agents, adapt awesome-copilot examples, or configure Coding Agent setup steps for a technology stack.

Adopt or review repository-level harness engineering for GitHub Copilot and coding agents. Use when users want durable agent instructions, guardrails, regression checks, drift checks, failure memory, or adoption reports that prevent repeated AI coding-agent mistakes in a target repository.

Install and configure Language Server Protocol servers for GitHub Copilot CLI code intelligence, including go-to-definition, find-references, hover, and type information. Use when the user asks to set up LSP, install a language server, configure Java or TypeScript LSP, fix /lsp status, or enable deeper code understanding in Copilot CLI.

Merge mature lessons from a domain memory instruction file into the matching long-lived instruction file while preserving applyTo coverage and removing merged memory sections. Use when the user invokes /memory-merger, asks to merge domain memories, consolidate instruction memories, or move workspace/user memory into instructions.

Create hybrid GitHub Copilot skills for Microsoft technologies using Microsoft Learn MCP tools or the mslearn CLI. Use this skill when the user asks to create a skill for Azure, .NET, Microsoft 365, VS Code, Bicep, Semantic Kernel, a Microsoft SDK, an Azure service, a framework, or a Microsoft REST API.

A 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. Use this skill when |--------|---------|-------------|; | `skill.ingest_with_content(doc_id, title, source, raw_content, entities, relations)` | Full RAG ingest...

Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for any LLM model inside a chat interface — NOT the API. Use this skill whenever the user wants to write, rewrite, optimize, improve, sharpen, or polish a prompt for chat. Trigger phrases include "rewrite this prompt", "make this a better prompt", "optimize this prompt", "turn this into a prompt", "help me prompt this", "draft a prompt that...", "I want to ask...", or whenever the user...

Transform lessons learned into domain-organized memory instructions for global or workspace scope. Use this skill when the user says /remember, asks to save a workflow lesson, records repeated mistakes, documents shortcuts or commands, discovers effective workflows, or wants durable VS Code memory instructions.

Create, audit, repair, and improve GitHub Copilot Agent Skills for VS Code, GitHub Copilot CLI, and GitHub Copilot cloud agent. Use when a user asks to create a skill, generate a SKILL.md, convert a workflow into a reusable skill, audit an existing skill, fix skill loading issues, optimize a skill description, validate frontmatter, or add references/scripts/assets to a skill package.

Compress responses with disciplined expert shorthand while preserving exact technical literals, code, commands, paths, identifiers, versions, flags, and quoted errors. Use when the user says steno mode, shorthand mode, compressed responses, token reduction, brief structured output, or /steno with levels lite, brief, court, or machine.

Run the local vardoger CLI to analyze GitHub Copilot CLI conversation history and write personalized instructions into ~/.copilot/copilot-instructions.md. Use this skill when the user asks to personalize my copilot, analyze my copilot history, tailor Copilot to me, run vardoger, update my Copilot instructions from history, or make Copilot learn my style.

Create, migrate, audit, and validate flat GitHub Copilot plugins and marketplaces with direct agents, skills, hooks, extensions, MCP configuration, canonical source ownership, and isolated runtime tests. Use when adding a plugin, repairing a manifest, packaging existing primitives, or refreshing marketplace governance.

Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.

Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model, coordinate system, measurement units, export workflows, and scripting best practices.

Write FreeCAD Python scripts, macros, parametric FeaturePython objects, Part/Mesh/Sketcher geometry, PySide GUI tools, Coin3D/Pivy scenegraph code, workbench commands, and CAD automation. Use when asked to create FreeCAD models, automate geometry, convert mesh and solid data, script FEM/Path/TechDraw, or debug FreeCAD Python API tasks.

Build web-based game engines and games with HTML5 Canvas, WebGL, SVG, CSS, and JavaScript. Use when creating 2D or 3D games, implementing game loops, physics, collision detection, sprites, tilemaps, controls, audio, multiplayer with WebRTC or WebSockets, optimization, or publishing workflows.

Process and manipulate images using ImageMagick. Supports resizing, format conversion, batch processing, and retrieving image metadata. Use when working with images, creating thumbnails, resizing wallpapers, or performing batch image operations.

Capture public HTTP(S) webpages as local PNG, JPEG, or PDF artifacts through Latchshot. Use when the user needs screenshots, website thumbnails, full-page captures, PDFs, QA reports, archives, or social previews. Do not use for private or authenticated pages, raw HTML extraction, scraping, CAPTCHA bypass, arbitrary browser actions, or local-file capture.

Generate or edit images through OpenRouter with the `google/gemini-3-pro-image-preview` model. Use when prompt-only image generation, single-image edits, multi-image compositing, 1K/2K/4K output, or troubleshooting `OPENROUTER_API_KEY`, `uv`, and saved MEDIA files is requested.

Use PDFtk Server from the command line to merge, split, rotate, encrypt, decrypt, fill forms, flatten forms, watermark, stamp, extract metadata, burst pages, repair PDFs, attach or extract files, collate scans, and manipulate PDF files. Use when asked for pdftk commands or PDF command-line operations.

Detect synthetic or manipulated audio, image, video, and text with Resemble AI; trace audio synthesis sources; apply or detect watermarks; verify speaker identity; and inspect media intelligence. Use this skill when checking deepfakes, fake detection, synthetic media, authenticity, provenance, AI-written text, voice verification, watermarking, source tracing, or whether media is real or fake.

Author and debug Rhinoceros 3D RhinoScript, RhinoPython, RhinoCommon, C# Script Editor, and command macro automation. Use when asked to write .rvb, .vbs, or .py Rhino scripts; manipulate geometry, layers, blocks, documents, viewports, undo, redraw, or Rhino 8 Script Editor workflows; or use rhinoscriptsyntax, scriptcontext, and Rhino.* namespaces.

Write, review, refactor, explain, and optimize Slang shaders and C++ engine integration for graphics pipelines, compute shaders, tessellation, ray tracing, parameter blocks, generics, interfaces, capabilities, autodiff, cross-compilation, and shader portability. Use when the user mentions Slang, .slang files, slangc, SPIR-V, HLSL, GLSL, Metal, CUDA, shader stages, or modern shader language features.

Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS/MP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.

Create or review ASP.NET Minimal API endpoints with typed results, DTO validation, endpoint groups, filters, ProblemDetails, and OpenAPI documentation. Use this skill when asked to add Minimal APIs, document endpoints with Swagger/OpenAPI, use .NET 9 built-in OpenAPI, or design request and response types.

Review, design, and fix C# async code using Task, Task<T>, ValueTask<T>, cancellation, ConfigureAwait, async streams, and TAP conventions. Use when the user asks for C# async best practices, deadlock fixes, async method naming, parallel awaits, or replacing .Wait(), .Result, and async void.