Suggest Awesome Github Copilot Prompts
Discover GitHub Copilot prompts from awesome-copilot that fit your repo, skip duplicates you already have, and flag local copies that are behind upstream.
Overview
Suggest Awesome GitHub Copilot Prompts is an agent skill most often used in Build (also Operate) that recommends awesome-copilot prompt files for your repository, skips duplicates, and identifies outdated local copies.
Install
npx skills add https://github.com/github/awesome-copilot --skill suggest-awesome-github-copilot-promptsWhat is this skill?
- 7-step workflow: fetch awesome-copilot catalog, scan `.github/prompts/`, diff against raw GitHub upstream, then match to
- Uses `#fetch` on README.prompts.md and per-file raw URLs to mark prompts up-to-date, outdated, or missing locally
- Ranks suggestions with match scores, relatedness notes, and install commands (`./prompts/<name>.prompt.md`)
- Surfaces update recommendations when local prompt tools, descriptions, or body content diverge from awesome-copilot
- Output tables separate new prompts to add versus existing prompts that need a refresh
- 7-step Process workflow from catalog fetch through match and recommend
- Compares local `.github/prompts/` files to awesome-copilot via raw GitHub URLs
Adoption & trust: 6.8k installs on skills.sh; 34.6k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You rely on GitHub Copilot prompts but do not know which awesome-copilot files fit your stack, which you already have, or which checked-in copies are behind upstream.
Who is it for?
Repositories that use or plan `.github/prompts/` and want a guided pass over the awesome-copilot catalog matched to tech stack and chat context.
Skip if: Teams that do not use GitHub Copilot prompt files, cannot reach GitHub to fetch awesome-copilot, or want fully bespoke prompts with no community catalog sync.
When should I use this skill?
Suggest relevant GitHub Copilot prompt files from the awesome-copilot repository based on current repository context and chat history, avoiding duplicates with existing prompts in this repository, and identifying outdate
What do I get? / Deliverables
You get ranked tables of new prompts to add, clear install paths under `./prompts/`, and an update list when local files diverge from the awesome-copilot versions.
- Table of recommended new awesome-copilot prompts with match scores, relatedness, and `./prompts/<file>` install commands
- Table of outdated local prompts with differences versus upstream and update recommendations
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build because the skill wires Copilot prompt files into `.github/prompts/` as part of how the product is developed with AI assistants. Agent-tooling is the right subphase: it curates third-party Copilot prompt assets and compares them to what is already checked into the repository.
Where it fits
Bootstrap `.github/prompts/` on a TypeScript monorepo by pulling ranked awesome-copilot files for testing and PR workflows.
After adopting a new framework, re-run matching so suggested prompts cover the updated stack described in CONTRIBUTING and recent chat.
Quarterly hygiene: diff every local prompt against raw.githubusercontent.com and queue updates where awesome-copilot changed tools or descriptions.
How it compares
Use this curated discovery-and-diff workflow instead of manually scrolling README.prompts.md and guessing which files are missing or stale.
Common Questions / FAQ
Who is suggest-awesome-github-copilot-prompts for?
Solo and indie builders (and small teams) who ship with GitHub Copilot and want awesome-copilot prompts aligned to their repo without duplicate or outdated files in `.github/prompts/`.
When should I use suggest-awesome-github-copilot-prompts?
During Build when you are setting up or expanding Copilot prompts for a new stack; during Operate when you want a periodic sync against awesome-copilot; or after chat/context shifts (e.g., new framework work) to refresh recommendations.
Is suggest-awesome-github-copilot-prompts safe to install?
It instructs the agent to fetch public GitHub URLs and read your local prompt folder—review permissions and the Security Audits panel on this Prism page before enabling network-heavy runs in sensitive repos.
SKILL.md
READMESKILL.md - Suggest Awesome Github Copilot Prompts
# Suggest Awesome GitHub Copilot Prompts Analyze current repository context and suggest relevant prompt files from the [GitHub awesome-copilot repository](https://github.com/github/awesome-copilot/blob/main/docs/README.prompts.md) that are not already available in this repository. ## Process 1. **Fetch Available Prompts**: Extract prompt list and descriptions from [awesome-copilot README.prompts.md](https://github.com/github/awesome-copilot/blob/main/docs/README.prompts.md). Must use `#fetch` tool. 2. **Scan Local Prompts**: Discover existing prompt files in `.github/prompts/` folder 3. **Extract Descriptions**: Read front matter from local prompt files to get descriptions 4. **Fetch Remote Versions**: For each local prompt, fetch the corresponding version from awesome-copilot repository using raw GitHub URLs (e.g., `https://raw.githubusercontent.com/github/awesome-copilot/main/prompts/<filename>`) 5. **Compare Versions**: Compare local prompt content with remote versions to identify: - Prompts that are up-to-date (exact match) - Prompts that are outdated (content differs) - Key differences in outdated prompts (tools, description, content) 6. **Analyze Context**: Review chat history, repository files, and current project needs 7. **Compare Existing**: Check against prompts already available in this repository 8. **Match Relevance**: Compare available prompts against identified patterns and requirements 9. **Present Options**: Display relevant prompts with descriptions, rationale, and availability status including outdated prompts 10. **Validate**: Ensure suggested prompts would add value not already covered by existing prompts 11. **Output**: Provide structured table with suggestions, descriptions, and links to both awesome-copilot prompts and similar local prompts **AWAIT** user request to proceed with installation or updates of specific prompts. DO NOT INSTALL OR UPDATE UNLESS DIRECTED TO DO SO. 12. **Download/Update Assets**: For requested prompts, automatically: - Download new prompts to `.github/prompts/` folder - Update outdated prompts by replacing with latest version from awesome-copilot - Do NOT adjust content of the files - Use `#fetch` tool to download assets, but may use `curl` using `#runInTerminal` tool to ensure all content is retrieved - Use `#todos` tool to track progress ## Context Analysis Criteria 🔍 **Repository Patterns**: - Programming languages used (.cs, .js, .py, etc.) - Framework indicators (ASP.NET, React, Azure, etc.) - Project types (web apps, APIs, libraries, tools) - Documentation needs (README, specs, ADRs) 🗨️ **Chat History Context**: - Recent discussions and pain points - Feature requests or implementation needs - Code review patterns - Development workflow requirements ## Output Format Display analysis results in structured table comparing awesome-copilot prompts with existing repository prompts: | Awesome-Copilot Prompt | Description | Already Installed | Similar Local Prompt | Suggestion Rationale | |-------------------------|-------------|-------------------|---------------------|---------------------| | [code-review.prompt.md](https://github.com/github/awesome-copilot/blob/main/prompts/code-review.prompt.md) | Automated code review prompts | ❌ No | None | Would enhance development workflow with standardized code review processes | | [documentation.prompt.md](https://github.com/github/awesome-copilot/blob/main/prompts/documentation.prompt.md) | Generate project documentation | ✅ Yes | create_oo_component_documentation.prompt.md | Already covered by existing documentation prompts | | [debugging.prompt.md](https://github.com/github/awes