How real projects brief GitHub Copilot, from .github/copilot-instructions.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Noi1rCopilot instructionsNoi1r/beamer-skill/.github/copilot-instructions.md
devils-advocate [file]` | Challenge slide design with 5-7 pedagogical questions | | `visual-check [file]` | PDF→image systematic visual review for overflow/layout issues | | `validate [file]` | Structural validation against constraints | | `extract-figures
Tantalor93Copilot instructionsTantalor93/dnspyre/.github/copilot-instructions.md
stack pulls in many indirect dependencies. Image-format support (PNG, JPEG, SVG, PDF) is provided via these libraries without external binaries. - **Windows builds**: `system_nameserver_windows.go` provides a Windows-specific implementation
iic-jkuCopilot instructionsiic-jku/analog-circuit-design/.github/copilot-instructions.md
circuit design course (JKU 336.009). Built with Quarto for multi-format publishing (HTML website + PDF), containing theoretical content, Python-based MOSFET sizing calculations, and Xschem/ngspice circuit simulations using
new-usemameCopilot instructionsnew-usemame/Calibre-Web-NextGen/.github/copilot-instructions.md
access ## File Format Support **Import formats** (27 total): epub, mobi, azw, azw3, azw4, pdf, txt, cbz, cbr, cb7, cbc, fb2, fbz, docx, html, htmlz
SamMorrowDrumsCopilot instructionsSamMorrowDrums/remarkable-mcp/.github/copilot-instructions.md
Dependencies - `mcp` - Model Context Protocol SDK - `requests` - HTTP client - `rmscene` - Native `.rm` parser - `pymupdf` - PDF and SVG rendering - `Pillow` - Image processing - `markdown-it-py` - Markdown parsing - `ebooklib` and `beautifulsoup4` - EPUB
OWASPCopilot instructionsOWASP/cornucopia/.github/copilot-instructions.md
exceeding limits before processing - **Content-Type Validation**: - Validate file extension against allowlist (e.g., `.jpg`, `.pdf`, `.docx`) - Check magic bytes match expected file type (first few bytes of file) - Use specialized
docling-projectCopilot instructionsdocling-project/docling-java/.github/copilot-instructions.md
Docling](https://github.com/docling-project), an IBM Research project for AI-based document processing (PDF, DOCX, PPTX, images, audio, etc.). The project is published to Maven Central under the `ai.docling` group
growerpCopilot instructionsgrowerp/growerp/.github/copilot-instructions.md
based real-time messaging with `growerp_chat` package - **File Handling**: Image picker, file picker, PDF generation (`printing`, `pdf` packages) - **Localization**: Built-in support for multiple locales including Buddhist Era calendars
cortex-worksCopilot instructionscortex-works/cortex-scout/.github/copilot-instructions.md
list_visible`, `verify_value` - browser/session control: `tabs`, `resize`, `handle_dialog`, `file_upload`, `fill_form`, `pdf_save`, `screenshot`, `snapshot` - diagnostics/state: `trace_start`/`trace_stop`/`trace_export`, `console_tap`/`console_dump`, `network
timothywarner-orgCopilot instructionstimothywarner-org/ab900/.github/copilot-instructions.md
server IDs - ab900buddy-context7 -- Context7 (M365 PowerShell and Graph API syntax) - ab900buddy-markitdown -- MarkItDown (PDF and Office doc conversion) - ab900buddy-mslearn -- Microsoft Learn MCP (@microsoft/learn-cli); provides microsoft_docs_search, microsoft
u9401066Copilot instructionsu9401066/pubmed-search-mcp/.github/copilot-instructions.md
Tool | Purpose | |------|---------| | `get_article_figures` | Get structured figure metadata (label, caption, image URL) and PDF links from a PMC Open Access arti | ### 研究編年史 *研究演化脈絡：持久化、可版本比對、證據支撐的時序主軸與分支投影* | Tool | Purpose | |------|---------| | `build
Intersect-Collaborations-LLCReads credentialsCopilot instructionsIntersect-Collaborations-LLC/research-workflow-assistant/.github/copilot-instructions.md
search, add, tag, export, notes, annotations, attachments) - **zotero-local-server**: Access local Zotero data: PDF text/annotation extraction, full-text keyword search across stored PDFs, and optional Better BibTeX integration - **prisma
ShieldNet-360Reads credentialsCopilot instructionsShieldNet-360/secure-vibe/dist/copilot-instructions.md
redirect and scheme bypasses, parsers that fetch on their own (XXE, SVG, HTML-to-PDF), cloud metadata, and keeping the response from becoming an oracle. Use when fetching a client
sanialesReads credentialsCopilot instructionssaniales/ai-lesson-planner/.github/copilot-instructions.md
course scaffolding). - Lesson artifacts live under `lessons/lesson-{number}-{id}/.lesson/artifacts/` with `highlights/`, `discourse/`, `slides/`; PDF output is `lessons/lesson-{number}-{id}/SLIDES.pdf`. - Use templates from `.lesson/templates/` (`HIGHLIGHTS.md`, `DISCOURSE.md`, `SLIDES.md`, `.lesson-config.json
Google CloudCopilot instructionsGoogleCloudPlatform/next-26-keynotes/genkey/data-cloud-demo/copilot-instructions.md
centralized around "Froyo", a brand of frozen yoghurt offering multiple flavors. - **Documentation**: Raw PDF documents detailing flavors and ingredients are stored in Google Cloud Storage at `gs:// `. ## 2. Execution & Data
fabioc-alohaReads credentialsCopilot instructionsfabioc-aloha/spotify-skill/.github/copilot-instructions.md
ADVANCED_SKILL_EXAMPLES.md`: 1. **API Wrapper Skills** (Spotify example) - External service integration 2. **Document Processing** - DOCX, PDF, XLSX manipulation 3. **Code Generation** - Framework boilerplate and scaffolding 4. **Business Logic** - Company processes
SoFarSoGoodyaCopilot instructionsSoFarSoGoodya/math-history-paper/.github/copilot-instructions.md
narratives, numerical values). 4. Course requirements (summary): 50 pages total (cover excluded), page numbers, PDF, and at least 5 references with a healthy mix of primary sources and reliable secondary
sbroenneCopilot instructionssbroenne/skillpm/.github/copilot-instructions.md
typescript-best-practices": "^1.3.0" } } ``` All dependencies resolve transitively through npm. ### SKILL.md format ```yaml --- name: pdf-processing description: Extract text and tables from PDF files, fill forms, merge documents. license: Apache
Microsoft AzureReads credentialsCopilot instructionsAzure/multi-agent-doc-research/.github/copilot-instructions.md
endpoint, deployments) - `AZURE_AI_SEARCH_*` (for document search) - `AZURE_DOCUMENT_INTELLIGENCE_*` (for PDF processing) - `BING_API_KEY` (optional, for web search) ## Deployment ### Azure Container Apps (Bicep) ```bash cd infra ./deploy.sh
MicrosoftCopilot instructionsmicrosoft/ai-cheatcode/.github/copilot-instructions.md
HTML email** (`issues/the_cheat_code_issue_NNN.html`) — primary format, 600px max-width, inline CSS, Outlook-compatible 2. **PDF** (`issues/the_cheat_code_issue_NNN.pdf`) — rendered from HTML via Chrome headless, attached to Engage posts 3. **Viva Amplify content** (`viva
Repository-wide instructions for GitHub Copilot, kept in .github/copilot-instructions.md.
How to build and test, the project's structure, and the conventions Copilot should follow in suggestions and reviews.
No. Copilot's coding agent also reads AGENTS.md, so many projects keep the shared rules there.
Open a file to see its discussion. Reports from people and their agents are coming.
