Claude Devstudio

Map modernization opportunities in a legacy codebase — identify unsupported dependencies, architecture seams, and migration paths using strangler fig, adapter, and parallel-run patterns

Run a YC-style office hours session before writing code — six forcing questions that surface wrong premises, missing constraints, and better approaches so you build the right thing the first time.

Scan for exposed secrets/credentials/API keys

Show help for the session management system and available commands

List all past development sessions with summaries and timestamps

Connect to external tools via MCP (GitHub, databases, APIs)

Accessibility (a11y) compliance checking with WCAG 2.1 validation

Audit an AI/ML system for governance controls — bias risk, explainability, model risk management, data lineage, fairness metrics, and regulatory alignment (EU AI Act, NIST AI RMF)

Complete branch workflow with squash, rebase, and cleanup

Document debugging sessions with hypothesis tracking and knowledge base

License compliance checking and conflict detection

Generate TypeScript types and client SDKs from OpenAPI specs

Herd open pull requests through review, CI, and merge — surface aging PRs, trigger minimal-fix on CI failures, nudge for rebases, and escalate blocked ones. Designed to run with /loop 5m.

Design and implement Retrieval-Augmented Generation systems — chunking strategy, embedding selection, vector store setup, retrieval pipeline, re-ranking, and evaluation

Comprehensive security analysis with vulnerability detection and remediation tracking

Begin documented development session using Claude Code CLI's memory system

Organize and synchronize session directory structure based on project architecture

Enforce true RED/GREEN TDD workflow with fail-first testing methodology

Analyze test coverage and suggest tests for uncovered code

Mutation testing to verify test quality with Stryker, mutmut, or go-mutesting

Define behavioral contracts, run adversarial tests, and detect regressions for AI agents — invariants, edge cases, statistical analysis, and benchmark-production gap detection

Map and prioritize the riskiest assumptions behind a feature, product decision, or technical design — surface what would kill it if wrong, then propose the cheapest test for each

Bundle size analysis and optimization for Webpack, Vite, and esbuild

Implement caching strategies for HTTP, service workers, and memoization

Auto-generate changelogs from commit history

Report estimated context window utilization and flag when approaching the compaction threshold

Surface architectural deepening opportunities — find shallow modules and refactor them into deep ones using precise vocabulary (module, seam, adapter, depth, leverage, locality). Use when refactoring architecture, reducing coupling, or improving testability.

Create and maintain a CONTEXT.md domain glossary and ADRs for the project — establishes shared vocabulary between developers, domain experts, and AI. Use when starting a new project, refining domain language, or resolving terminology ambiguities.

Install a Claude Code PreToolUse hook that blocks dangerous git operations (force push, reset --hard, clean -f, branch -D, checkout ., restore .) before they execute. Use when setting up git safety hooks or preventing destructive git commands in Claude Code.

GraphQL schema validation and optimization with federation support

Infrastructure as Code generation for Terraform, CloudFormation, and Pulumi

Improve variable and function naming with semantic analysis

Proactive problem identification through code analysis and pattern detection

SQL/NoSQL query optimization with N+1 detection and index recommendations

Resume previous work from archived session with full context restoration

Generate TypeScript types from schemas/APIs

Generate configuration files for development tools

Restore work-in-progress context saved by /context-save — finds the most recent WIP commit on the current branch and unpacks it back to the working tree so you can resume exactly where you left off. Inspired by gstack's context-restore skill.

Manage multiple Claude instances for complex tasks with coordination

Convert Postman collections to automated tests with environment preservation

Run a structured onboarding interview to generate USER.md and PROJECT.md — capturing developer preferences, project constraints, access policies, and working style so every future agent session starts with full context.

Design, optimize, and evaluate prompts for LLM applications — system prompts, few-shot examples, chain-of-thought, structured outputs, and caching strategy

Generate comprehensive README files from code analysis

Strip multi-vendor AI provenance marks from files and text — invisible Unicode (Layer A), statistical text watermarks via rewrite (Layer B), and C2PA/EXIF/XMP/container metadata from PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Requires the watermarks-remover local service (Docker). Use when the user asks to strip watermarks, remove C2PA/Content Credentials, clean AI metadata, remove invisible Unicode, or runs /remove-ai-marks.

Detect AI-generated writing patterns in documents — reports filler openers, AI closers, hedge phrases, cliché transitions, template phrasing, AI vocabulary, rhetorical question-answer pairs, and overused intensifiers with a per-document AI-written percentage, then asks before removing anything.

Database schema validation and drift detection across environments

View active session status with progress and context information

Always-on ambient skill that captures decisions, patterns, entity mentions, and original thinking from the current conversation and writes them to agent memory. Run in parallel — never blocks the main response.

Detect AI-generated UI patterns in CSS and component files — reports side-tab accents, gradient text, glassmorphism, bounce easing, template scaffolding, and monoculture font choices, then asks before removing anything

Review LLM application code for context assembly quality, retrieval integration, prompt construction, output validation, cost controls, and failure handling

Database MCP server integration for PostgreSQL, MySQL, MongoDB

Root cause analysis with dependency tracing and call stack analysis

Comprehensive dependency security and license audit

Decompose a problem to its irreducible truths before proposing solutions — strip inherited assumptions, rebuild from fundamentals, surface the real constraint

Track build success rates and identify flaky tests from CI logs

Web security headers validation and configuration generation

Install Husky pre-commit hooks with lint-staged (Prettier), type checking, and test automation. Auto-detects package manager. Use when adding pre-commit hooks, setting up Husky, configuring lint-staged, or adding commit-time formatting and type checking.

Webpack/Vite/esbuild configuration optimization for build performance

Generate OpenAPI/Swagger documentation from code analysis

Auto-generate comprehensive API tests for REST and GraphQL endpoints with request/response validation