Prompts
Community-contributed AI prompts, with the source credited on each one.
Stage 1: Build (command)
Generate an optimized Dockerfile for the current project. Steps 1. Detect Project Type - Read package.json, pyproject.toml, go.mod, Cargo.toml, or equivalent to determine the language and framework. - Identify the build
K8S Manifest (command)
Generate Kubernetes manifests for deploying the current application. Steps 1. Analyze the project to determine deployment requirements: - Read Dockerfile for container configuration, exposed ports, health checks. - Read
Monitor (command)
Set up monitoring, alerting, and observability for the application. Steps 1. Analyze the application to determine monitoring needs: - Web server: response times, error rates, request volume. - Database: query performance
Api Docs (command)
Generate API documentation from route definitions and handlers. Steps 1. Detect the web framework in use (Express, Fastify, FastAPI, Gin, Actix, etc.). 2. Scan for route definitions: - Express/Fastify: app.get(), router.
Doc Gen (command)
Generate documentation from the codebase for the specified scope. Steps 1. Determine Scope - If a specific file or module is provided, document that. - If no scope is given, identify the most important public-facing modu
Project Memory (command)
Update the project's CLAUDE.md memory bank with current session learnings. Steps 1. Read the existing CLAUDE.md (project root) or create one if it does not exist. 2. Analyze the current session to extract: - Decisions ma
Developer Onboarding Guide (command)
Generate an onboarding guide for new developers joining the project. Steps 1. Scan the project root for configuration files to determine the tech stack: - package.json, tsconfig.json, pyproject.toml, Cargo.toml, go.mod.
Project Codemap (command)
Update the project codemap to reflect the current state of the codebase. Steps 1. Scan Project Structure - Run find . -type f -not -path '/node_modules/' -not -path '/.git/' -not -path '/dist/' -not -path '/__pycache__/'
Changelog (command)
Generate a changelog from git history since the last tag or a specified reference point. Steps 1. Find the latest tag: git describe --tags --abbrev=0 2/dev/null || echo "initial". 2. Get all commits since that tag: git l
Commit (command)
Analyze the currently staged changes (git diff --cached) and generate a conventional commit message. Steps 1. Run git diff --cached --stat to see which files changed. 2. Run git diff --cached to read the actual changes.
Fix Issue (command)
Fix a GitHub issue by number: read the issue, create a branch, implement the fix, and open a PR. Steps 1. Fetch the issue details using gh issue view <number --json title,body,labels,assignees. 2. Parse the issue body to
Pr Create (command)
Create a pull request with a structured description based on the current branch's changes. Steps 1. Run git log main..HEAD --oneline to see all commits on this branch. 2. Run git diff main...HEAD --stat to see all change
Pr Review (command)
Review a pull request by number: fetch the diff, analyze changes, and post review comments. Steps 1. Fetch PR details: gh pr view <number --json title,body,files,additions,deletions,commits. 2. Get the full diff: gh pr d
Release (command)
Create a tagged release with auto-generated release notes from recent commits. Steps 1. Run git log --oneline $(git describe --tags --abbrev=0 2/dev/null || git rev-list --max-parents=0 HEAD)..HEAD to list commits since
Worktree (command)
Set up git worktrees for parallel development on multiple branches simultaneously. Steps 1. Verify the current repository is not a bare clone: git rev-parse --is-bare-repository. 2. List existing worktrees with git workt
Cleanup (command)
Find and remove dead code, unused imports, and unreachable branches. Steps 1. Detect the language and available tooling: - TypeScript/JavaScript: Use tsc --noEmit for unused locals, eslint with no-unused-vars. - Python:
Dead Code (command)
Find and remove dead code from the codebase. Steps 1. Unused Imports - Run the linter with unused import detection: - TypeScript: tsc --noUnusedLocals --noUnusedParameters --noEmit - ESLint: Check for no-unused-vars, no-
Extract (command)
Extract a function, component, or module from existing code into its own unit. Steps 1. Identify the code block to extract from the argument (file path and line range, or description). 2. Read the target file and analyze
Rename (command)
Rename a symbol (variable, function, class, file) across the entire codebase. Steps 1. Accept the old name and new name from the argument. 2. Determine the symbol type: - Variable, function, or class name. - File or dire
Simplify (command)
Simplify code to improve readability and maintainability. Steps 1. Reduce Nesting - Convert nested if/else chains to early returns (guard clauses). - Replace nested loops with flatMap, reduce, or helper functions. - Extr
Audit (command)
Perform a security audit of the codebase covering common vulnerability categories. Steps 1. Dependency Vulnerabilities - Run the package manager's audit: npm audit, pip audit, cargo audit, govulncheck ./.... - List criti
Csp (command)
Generate Content Security Policy headers for a web application. Steps 1. Scan the project for frontend assets and their sources: - JavaScript files: inline scripts, external CDN scripts, dynamic imports. - CSS files: inl
Dependency Audit (command)
Audit project dependencies for known vulnerabilities and outdated packages. Steps 1. Detect the package manager and run the native audit command: - npm: npm audit --json - pnpm: pnpm audit --json - yarn: yarn audit --jso
Hardening (command)
Apply security hardening measures to the codebase. Steps 1. HTTP Security Headers Add or verify these headers in the web server or middleware configuration: - Content-Security-Policy: Restrict script sources, disable inl
