@mohammadhprp/system-prompt 0.10.1

package/framework/mcps/excalidraw/install.md

@@ -0,0 +1,92 @@
+# Excalidraw MCP Installation
+
+## Requirements
+
+- An MCP-compatible AI client that supports MCP Apps (interactive HTML interfaces).
+- No API key or authentication needed for the remote server.
+
+## Configuration
+
+Excalidraw MCP can be used remotely or run locally.
+
+### Remote (recommended)
+
+| Field | Value |
+| --- | --- |
+| Server name | `excalidraw` |
+| Transport type | Streamable HTTP |
+| URL | `https://mcp.excalidraw.com` |
+
+### Config file examples
+
+Use the examples in [`configs/`](./configs/) as client-specific starting points:
+
+| Client | Example | Typical location |
+| --- | --- | --- |
+| OpenCode | [`configs/opencode.json`](./configs/opencode.json) | OpenCode MCP configuration. |
+
+### OpenCode
+
+Copy [`configs/opencode.json`](./configs/opencode.json) into your OpenCode project root or user config directory and restart the OpenCode agent.
+
+### Local (build from source)
+
+Clone and build the repository:
+
+```bash
+git clone https://github.com/excalidraw/excalidraw-mcp.git
+cd excalidraw-mcp
+pnpm install && pnpm run build
+```
+
+Add to your MCP config:
+
+```json
+{
+  "mcpServers": {
+    "excalidraw": {
+      "command": "node",
+      "args": ["/path/to/excalidraw-mcp/dist/index.js", "--stdio"]
+    }
+  }
+}
+```
+
+### For clients that only support local stdio servers
+
+Use the [mcp-remote](https://www.npmjs.com/package/mcp-remote) bridge:
+
+```json
+{
+  "mcpServers": {
+    "excalidraw": {
+      "command": "npx",
+      "args": ["-y", "mcp-remote", "https://mcp.excalidraw.com"]
+    }
+  }
+}
+```
+
+## Verification
+
+After configuring and restarting your AI client, try:
+
+```
+Draw an architecture diagram showing a user connecting to an API server which talks to a database using excalidraw
+```
+
+## Updating
+
+For the remote server: no update steps needed — the latest version is always available at `https://mcp.excalidraw.com`.
+
+For local builds: pull the latest changes and rebuild.
+
+## Uninstalling
+
+Remove the `excalidraw` MCP entry from AI client configuration files.
+
+## Common Issues
+
+- **Diagram not rendering**: ensure your AI client supports MCP Apps (interactive HTML interfaces). Some older clients may not support this format.
+- **Remote server unreachable**: check that `https://mcp.excalidraw.com` is accessible from your network. Try the local build as a fallback.
+- **Local build fails**: ensure pnpm is installed (`npm install -g pnpm`) and Node.js LTS is available.

package/framework/mcps/excalidraw/troubleshooting.md

@@ -0,0 +1,67 @@
+# Excalidraw MCP Troubleshooting
+
+## Diagram not rendering
+
+**Problem**
+
+The `draw` tool runs but no diagram appears in the chat.
+
+**Cause**
+
+The AI client may not support MCP Apps (interactive HTML interfaces). Standard text-only MCP clients cannot render interactive diagrams.
+
+**Fix**
+
+- Check if your client supports MCP Apps. Claude Desktop and Codex CLI support it; some other clients may not.
+- Try a simpler diagram description to rule out parsing issues.
+- As a fallback, ask the agent to describe the diagram in text or ASCII art.
+
+## Remote server unreachable
+
+**Problem**
+
+The client reports that `https://mcp.excalidraw.com` is unreachable.
+
+**Cause**
+
+Network connectivity issue or the server is temporarily down.
+
+**Fix**
+
+- Run `curl https://mcp.excalidraw.com` to test connectivity.
+- Check for proxy or firewall rules blocking the connection.
+- Fall back to the local build (see [install.md](./install.md)).
+
+## Local build fails
+
+**Problem**
+
+`pnpm install` or `pnpm run build` fails.
+
+**Cause**
+
+Missing dependencies or Node.js version mismatch.
+
+**Fix**
+
+- Ensure pnpm is installed: `npm install -g pnpm`.
+- Ensure Node.js LTS is installed (v18+).
+- Run `pnpm install --frozen-lockfile` for a clean install.
+- Check the `dist/index.js` file exists after build — this is the server entry point.
+
+## Diagram content is wrong
+
+**Problem**
+
+The diagram doesn't match what you asked for.
+
+**Cause**
+
+The description was ambiguous or too vague for the rendering engine.
+
+**Fix**
+
+- Be more specific: include component names, positions, relationships, and directional flow.
+- Break complex diagrams into multiple smaller requests.
+- Use the interactive viewer to adjust elements after rendering.
+- Example: instead of "draw a system diagram", say "draw a system with a React frontend, a Node.js API server, and a PostgreSQL database connected with arrows from frontend to API and API to database".

package/framework/mcps/figma-mcp-go/README.md

@@ -0,0 +1,51 @@
+# Figma MCP Go
+
+## Overview
+
+Figma MCP Go is an open-source Figma MCP server with full read/write access via a Figma plugin bridge. It does not use the Figma REST API, so there are no rate limits and no API token required. It exposes 73 tools for reading and writing Figma documents, styles, variables, components, prototypes, and more.
+
+Official source:
+
+- [GitHub: vkhanhqui/figma-mcp-go](https://github.com/vkhanhqui/figma-mcp-go)
+
+## Features
+
+- No Figma API token required.
+- No rate limits — free plan friendly.
+- Read and write live Figma data via plugin bridge — 73 tools total.
+- Full design automation: styles, variables, components, prototypes, and content.
+- Built-in design prompts: `read_design_strategy`, `design_strategy`, and more.
+- Export tools: screenshots, PDFs, and design tokens.
+
+## Supported AI Clients
+
+Figma MCP Go works with any MCP-compatible AI client. The server is started via `npx` and communicates over stdio.
+
+- OpenCode
+
+## When to Use
+
+Use Figma MCP Go when an AI coding agent needs to read or modify Figma designs directly.
+
+Good fits:
+
+- Converting designs to code.
+- Updating text, colors, or layouts across Figma frames programmatically.
+- Extracting design tokens, styles, or variable definitions.
+- Automating component creation, renaming, or restructuring.
+- Generating screenshots or PDF exports of frames.
+
+Avoid using it as a generic MCP outside Figma-related workflows.
+
+## Requirements
+
+- Node.js and npm available on `PATH` (for `npx`).
+- A Figma desktop app to install and run the companion plugin.
+- An AI client that supports local stdio MCP servers.
+
+## Related Skills
+
+Relevant skills in this repository:
+
+- [`backend-engineer`](../../skills/backend-engineer/SKILL.md): generating UI code from designs.
+- [`backend-best-practices`](../../skills/backend-best-practices/SKILL.md): backend best practices for API design, testing, and debugging.

package/framework/mcps/figma-mcp-go/capabilities.md

@@ -0,0 +1,190 @@
+# Figma MCP Go Capabilities
+
+## What It Can Do
+
+73 tools total across read, write, export, and prompt categories.
+
+### Write — Create
+
+| Tool | Description |
+| --- | --- |
+| `create_frame` | Create a frame with optional auto-layout, fill, and parent |
+| `create_rectangle` | Create a rectangle with optional fill and corner radius |
+| `create_ellipse` | Create an ellipse or circle |
+| `create_text` | Create a text node (font loaded automatically) |
+| `import_image` | Decode base64 image and place it as a rectangle fill |
+| `create_component` | Convert an existing FRAME node into a reusable component |
+| `create_section` | Create a Figma Section node to organise frames on a page |
+
+### Write — Modify
+
+| Tool | Description |
+| --- | --- |
+| `set_text` | Update text content of an existing TEXT node |
+| `set_fills` | Set solid fill color (hex) on a node |
+| `set_strokes` | Set solid stroke color and weight on a node |
+| `set_opacity` | Set opacity of one or more nodes |
+| `set_corner_radius` | Set corner radius — uniform or per-corner |
+| `set_auto_layout` | Set or update auto-layout (flex) properties on a frame |
+| `set_visible` | Show or hide one or more nodes |
+| `lock_nodes` | Lock one or more nodes to prevent accidental edits |
+| `unlock_nodes` | Unlock one or more nodes |
+| `rotate_nodes` | Set absolute rotation in degrees on one or more nodes |
+| `reorder_nodes` | Change z-order |
+| `set_blend_mode` | Set blend mode on one or more nodes |
+| `set_constraints` | Set responsive constraints on one or more nodes |
+| `move_nodes` | Move nodes to an absolute x/y position |
+| `resize_nodes` | Resize nodes by width and/or height |
+| `rename_node` | Rename a node |
+| `clone_node` | Clone a node, optionally repositioning or reparenting |
+| `reparent_nodes` | Move nodes to a different parent |
+| `batch_rename_nodes` | Bulk rename nodes via find/replace, regex, or prefix/suffix |
+| `find_replace_text` | Find and replace text across all TEXT nodes |
+
+### Write — Delete
+
+| Tool | Description |
+| --- | --- |
+| `delete_nodes` | Delete one or more nodes permanently |
+
+### Write — Prototype
+
+| Tool | Description |
+| --- | --- |
+| `set_reactions` | Set prototype reactions (triggers + actions) on a node |
+| `remove_reactions` | Remove all or specific reactions from a node |
+
+### Write — Styles
+
+| Tool | Description |
+| --- | --- |
+| `set_effects` | Apply drop shadow / blur effects directly on a node |
+| `create_paint_style` | Create a named paint style with a solid color |
+| `create_text_style` | Create a named text style |
+| `create_effect_style` | Create a named effect style |
+| `create_grid_style` | Create a named layout grid style |
+| `update_paint_style` | Rename or recolor an existing paint style |
+| `apply_style_to_node` | Apply an existing local style to a node |
+| `delete_style` | Delete any style by ID |
+
+### Write — Variables
+
+| Tool | Description |
+| --- | --- |
+| `create_variable_collection` | Create a new local variable collection |
+| `add_variable_mode` | Add a new mode to an existing collection |
+| `create_variable` | Create a variable in a collection |
+| `set_variable_value` | Set a variable's value for a specific mode |
+| `bind_variable_to_node` | Bind a variable to a node property |
+| `delete_variable` | Delete a variable or an entire collection |
+
+### Write — Pages
+
+| Tool | Description |
+| --- | --- |
+| `add_page` | Add a new page to the document |
+| `delete_page` | Delete a page by ID or name |
+| `rename_page` | Rename a page by ID or current name |
+
+### Write — Components & Navigation
+
+| Tool | Description |
+| --- | --- |
+| `navigate_to_page` | Switch the active Figma page |
+| `group_nodes` | Group two or more nodes into a GROUP |
+| `ungroup_nodes` | Ungroup GROUP nodes |
+| `swap_component` | Swap the main component of an INSTANCE node |
+| `detach_instance` | Detach component instances to plain frames |
+
+### Read — Document & Selection
+
+| Tool | Description |
+| --- | --- |
+| `get_document` | Full current page tree |
+| `get_metadata` | File name, pages, current page |
+| `get_pages` | All pages (IDs + names) — lightweight |
+| `get_selection` | Currently selected nodes |
+| `get_node` | Single node by ID |
+| `get_nodes_info` | Multiple nodes by ID |
+| `get_design_context` | Depth-limited tree with detail level |
+| `search_nodes` | Find nodes by name and/or type |
+| `scan_text_nodes` | All text nodes in a subtree |
+| `scan_nodes_by_types` | Nodes matching given type list |
+| `get_viewport` | Current viewport center, zoom, and visible bounds |
+
+### Read — Styles & Variables
+
+| Tool | Description |
+| --- | --- |
+| `get_styles` | Paint, text, effect, and grid styles |
+| `get_variable_defs` | Variable collections and values |
+| `get_local_components` | All components + component sets |
+| `get_annotations` | Dev-mode annotations |
+| `get_fonts` | All fonts used on the current page |
+| `get_reactions` | Prototype/interaction reactions on a node |
+
+### Export
+
+| Tool | Description |
+| --- | --- |
+| `get_screenshot` | Base64 image export of any node |
+| `save_screenshots` | Export images to disk |
+| `export_frames_to_pdf` | Export multiple frames as a single multi-page PDF |
+| `export_tokens` | Export design tokens as JSON or CSS |
+
+### MCP Prompts
+
+| Prompt | Description |
+| --- | --- |
+| `read_design_strategy` | Best practices for reading Figma designs |
+| `design_strategy` | Best practices for creating and modifying designs |
+| `text_replacement_strategy` | Chunked approach for replacing text across a design |
+| `annotation_conversion_strategy` | Convert manual annotations to native Figma annotations |
+| `swap_overrides_instances` | Transfer overrides between component instances |
+| `reaction_to_connector_strategy` | Map prototype reactions into interaction flow diagrams |
+
+## What It Cannot Do
+
+- It cannot work without the Figma desktop plugin running inside an open file.
+- It does not use the Figma REST API, so it cannot read files or projects without the plugin bridge.
+- It cannot access Figma team libraries, shared styles, or remote variables outside the current file.
+- It cannot replace human review for destructive operations like deleting nodes or bulk renaming.
+- It cannot export SVGs or vector files directly; exports are limited to images and PDFs.
+
+## Best Practices
+
+- Keep the Figma plugin running in the file being edited.
+- Prefer `get_document` or `get_design_context` to understand the structure before making changes.
+- Use `search_nodes` to find specific elements by name rather than traversing the full tree.
+- Use `batch_rename_nodes` and `find_replace_text` for bulk changes instead of per-node operations.
+- Verify destructive operations (`delete_nodes`, `delete_style`, `delete_variable`) before executing.
+- Run exports (`save_screenshots`, `export_frames_to_pdf`) to disk for durable artifacts.
+- Keep the plugin version in sync with the MCP server version.
+
+## Common Workflows
+
+### Understand a Figma design
+
+1. Ask the agent to call `get_metadata` to learn file and page structure.
+2. Call `get_document` or `get_design_context` on the relevant page.
+3. Call `get_styles`, `get_variable_defs`, and `get_local_components` for design system details.
+4. Ask the agent to use the `read_design_strategy` prompt for guidance.
+
+### Convert a design to code
+
+1. Select the target frame in Figma.
+2. Ask the agent to call `get_selection` and `get_node` on the selected frame.
+3. Export the frame with `get_screenshot` for visual reference.
+4. Use the structure and styles to generate matching code.
+
+### Update text across a design
+
+1. Use `find_replace_text` or `scan_text_nodes` to locate all text nodes.
+2. Use `set_text` to update individual nodes or `batch_rename_nodes` for bulk operations.
+3. Ask the agent to use the `text_replacement_strategy` prompt for large text replacement tasks.
+
+### Export design tokens
+
+1. Call `get_variable_defs` to retrieve variable collections and values.
+2. Call `get_styles` to retrieve paint, text, and effect styles.
+3. Use `export_tokens` to generate JSON or CSS output.

package/framework/mcps/figma-mcp-go/configs/opencode.json

@@ -0,0 +1,9 @@
+{
+  "mcp": {
+    "figma-mcp-go": {
+      "type": "local",
+      "enabled": true,
+      "command": ["npx", "-y", "@vkhanhqui/figma-mcp-go"]
+    }
+  }
+}

package/framework/mcps/figma-mcp-go/install.md

@@ -0,0 +1,74 @@
+# Figma MCP Go Installation
+
+## Requirements
+
+- Node.js and npm available on `PATH`.
+- Figma desktop app.
+- An MCP-compatible AI client.
+
+## Installation
+
+### 1. Install the Figma plugin
+
+1. Download the latest `plugin.zip` from the [releases page](https://github.com/vkhanhqui/figma-mcp-go/releases).
+2. In Figma Desktop: **Plugins → Development → Import plugin from manifest**.
+3. Select `manifest.json` from `plugin.zip`.
+4. Run the plugin inside any Figma file.
+
+### 2. Configure your AI client
+
+Add the MCP server to your client configuration.
+
+## Configuration
+
+| Field | Value |
+| --- | --- |
+| Server name | `figma-mcp-go` |
+| Command | `npx` |
+| Args | `-y`, `@vkhanhqui/figma-mcp-go` |
+
+### Config file examples
+
+Use the examples in [`configs/`](./configs/) as client-specific starting points:
+
+| Client | Example | Typical location |
+| --- | --- | --- |
+| OpenCode | [`configs/opencode.json`](./configs/opencode.json) | OpenCode MCP configuration. |
+
+### OpenCode
+
+Copy [`configs/opencode.json`](./configs/opencode.json) into your OpenCode project root or user config directory and restart the OpenCode agent. The server will start automatically when the agent needs it.
+
+## Verification
+
+Run the MCP server command directly:
+
+```bash
+npx -y @vkhanhqui/figma-mcp-go
+```
+
+Then verify from your AI client:
+
+- The `figma-mcp-go` MCP server is listed.
+- The server starts without errors.
+- Tools such as `get_document`, `get_selection`, or `create_frame` are visible to the agent.
+- The Figma plugin shows a connected status.
+
+## Updating
+
+```bash
+npx -y @vkhanhqui/figma-mcp-go@latest
+```
+
+Update the Figma plugin by re-importing from the latest `plugin.zip`.
+
+## Uninstalling
+
+1. Remove the `figma-mcp-go` MCP entry from AI client configuration files.
+2. Remove the Figma plugin: **Plugins → Development → Manage plugins → remove figma-mcp-go**.
+
+## Common Issues
+
+- **Server starts but no tools are available**: confirm the Figma plugin is running in an open Figma file.
+- **Client cannot find the server**: confirm the config is in the location used by that client and the server name is `figma-mcp-go`.
+- **Plugin not listed**: use **Import plugin from manifest** rather than searching the plugin store.

package/framework/mcps/figma-mcp-go/troubleshooting.md

@@ -0,0 +1,99 @@
+# Figma MCP Go Troubleshooting
+
+## Server won't start
+
+**Problem**
+
+The AI client reports that `figma-mcp-go` failed to start.
+
+**Cause**
+
+The client cannot run `npx`, Node.js is not installed, or the npm package is unavailable.
+
+**Solution**
+
+- Run `npx -y @vkhanhqui/figma-mcp-go` manually to verify the server starts.
+- Check Node.js is installed: `node --version && npm --version`.
+- Check network access if the package has not been cached locally.
+- Ensure the config file contains the correct command and args.
+
+## Figma plugin not connecting
+
+**Problem**
+
+The MCP server starts but reports no Figma connection.
+
+**Cause**
+
+The Figma plugin is not running, not imported, or not open in a file.
+
+**Solution**
+
+- Confirm the plugin was imported via **Plugins → Development → Import plugin from manifest**.
+- Run the plugin inside the Figma file you want to edit.
+- Verify the plugin shows a connected status after running.
+
+## No tools available
+
+**Problem**
+
+The AI client shows the server is running but no tools are listed.
+
+**Cause**
+
+The server started without a Figma connection, or the plugin bridge failed to initialise.
+
+**Solution**
+
+- Restart the Figma plugin.
+- Restart the MCP server.
+- Ensure the Figma file is open and the plugin is running in that file.
+
+## Configuration errors
+
+**Problem**
+
+The MCP server is not listed, or the client ignores the config file.
+
+**Cause**
+
+The config file is in the wrong location, the JSON is invalid, or the client expects a different configuration wrapper.
+
+**Solution**
+
+- Validate the JSON with `python -m json.tool <file>` or another JSON parser.
+- Confirm the client-specific config location in the client's documentation.
+- Keep the server name as `figma-mcp-go`.
+- Use the official command `npx` and args `-y`, `@vkhanhqui/figma-mcp-go`.
+
+## Version mismatch
+
+**Problem**
+
+Some tools are missing or behave differently than documented.
+
+**Cause**
+
+The MCP server version and the Figma plugin version are out of sync.
+
+**Solution**
+
+- Update both the server and plugin to the latest version.
+- Re-download `plugin.zip` from the latest release and re-import into Figma.
+- Clear the npm cache: `npm cache clean --force` and retry.
+
+## Export tools fail
+
+**Problem**
+
+`save_screenshots` or `export_frames_to_pdf` fail with file system errors.
+
+**Cause**
+
+The server process does not have write permission to the target directory.
+
+**Solution**
+
+- Provide an absolute path to a writable directory.
+- Check filesystem permissions on the target directory.
+- Use `get_screenshot` (base64 output) instead when disk writes are not required.

package/framework/mcps/github-mcp/README.md

@@ -0,0 +1,51 @@
+# GitHub MCP
+
+## Overview
+
+The GitHub MCP Server connects AI tools directly to GitHub. Browse code, manage issues and PRs, analyze commits, monitor Actions workflows, and automate development workflows through natural language.
+
+Official source:
+
+- [GitHub: github/github-mcp-server](https://github.com/github/github-mcp-server)
+
+## Features
+
+- Repository browsing — read files, search code, explore directory trees, analyze commits.
+- Issue & PR management — create, update, comment, review, and merge pull requests.
+- CI/CD intelligence — monitor workflow runs, analyze build failures, manage releases.
+- Code Analysis — examine security findings, review Dependabot alerts, understand code patterns.
+- Team collaboration — access discussions, manage notifications, analyze team activity.
+
+## Supported AI Clients
+
+GitHub MCP officially documents setup for Claude Code, VS Code, GitHub Copilot, Cursor, Windsurf, Zed, and OpenCode.
+
+- OpenCode
+
+## When to Use
+
+Use GitHub MCP when an AI coding agent needs direct access to GitHub.
+
+Good fits:
+
+- Browsing repository code, commits, and branches.
+- Creating, reviewing, and merging pull requests.
+- Managing issues, labels, and milestones.
+- Monitoring Actions workflows and debugging CI failures.
+- Analyzing Dependabot alerts and code scanning results.
+- Managing GitHub releases and gists.
+
+Avoid using it outside of GitHub-related workflows.
+
+## Requirements
+
+- A GitHub Personal Access Token with appropriate scopes (`repo` for private repos, `read:org` for org access).
+- An MCP-compatible AI client that supports remote HTTP MCP servers.
+
+## Related Skills
+
+Relevant skills in this repository:
+
+- [`code-review`](../../skills/code-review/SKILL.md): reviewing pull request diffs.
+- [`backend-best-practices`](../../skills/backend-best-practices/SKILL.md): backend best practices for testing, debugging, and security review.
+- [`pull-request`](../../skills/pull-request/SKILL.md): preparing and submitting pull requests.