Make technology decisions for every capability your product needs — starting with what you already have, then evaluating what fits, then deciding what to build.

Embed claude-sub-proxy as an internal service within another project. Minimal footprint — 4 JS files + config, running on localhost with no external exposure.

Performs comprehensive deep analysis of entire codebase and deployment pipeline to identify issues in production environment. Conducts systematic investigation across architecture, authentication, file connections, deployment, CI/CD, and stability.

The GMSH Agent is a specialized AI module for finite element mesh generation and manipulation. It provides automated mesh generation, quality assessment, optimization, and integration with engineer...

name: frontend-design

Track progress, update plan statuses, manage Claude Tasks, generate reports, coordinate docs updates. Use for project oversight, status checks, plan completion, task hydration, cross-session continuity.

!`gh issue view $ARGUMENTS --json title,body,comments,labels,assignees 2>/dev/null || echo "ERROR: Could not fetch issue $ARGUMENTS. Check the issue number and try again."`

pm agent

Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.

Run a comprehensive code review on recent changes using the code-reviewer and security-reviewer agents

Train or retrain a credit scoring model. Use when the user asks to train, retrain, fine-tune, or calibrate a model, or when new training data is available.

Use when onboarding developers to an unfamiliar codebase, documenting a complex architectural flow across multiple files, or creating guided walkthroughs for code reviews. Generates VSCode CodeTour JSON files with progressive disclosure — starting from high-level architecture and drilling into implementation details. Domain: Documentation, Onboarding. Level: Intermediate. Tags: code-tour, onboarding, walkthrough, documentation, progressive-disclosure, vscode.

/home/aryaniyaps/web-projects/moodle-proctor/.claude/skills/gstack/plan-design-review/SKILL.md

Use when working with gRPC services, protobuf definitions, Protocol Buffers, streaming RPCs, interceptors, or gRPC client configuration in .NET. Provides domain-specific rules layered on top of base architectural standards.

Analyze Figma designs for code implementation readiness and design-code parity. Use when working with Figma URLs, analyzing component designs, or checking token consistency.

>-

Creates or updates `docs/<artifactId>.md` based on the existing project

Push changes to remote. Use this whenever the user wants to push, deploy, or publish changes.

Guide for using the `arc42-mcp-server` MCP server to create and maintain architecture documentation following the proven [arc42 template](https://arc42.org/). The server provides 6 tools, supports 11

End-of-session wrap-up. Updates docs, runs lint/tests, builds productivity report, and commits — all aligned with Documents/Process/DefinitionOfDone.md. Use as the last step before opening a PR.

Discover functions that block the main thread, then micro-audit each for internal optimization opportunities

>

Design phase rules for /designer command. Load at /designer startup (step 0). Covers spec quality, design checklist, approach evaluation criteria.

Canonical GitHub issue execution route after plan approval — strengthened resource intelligence, TDD-first implementation, targeted validation, adversarial review, delegation controls for Claude agent teams, GitHub progress posting, future-issue capture, and commit/push with closeout discipline.

Proactive code review. When the user completes a meaningful coding task or asks for a review, invoke /rrr automatically — but only if this project has opted in.

Run the proofreading protocol on project files. Checks grammar, typos, consistency, and academic writing quality. Produces a report without editing files.

Sync all bank pipelines and reconcile balances against YNAB

Wrapper skill: backfill Fireflies transcript summaries into matching meeting notes for a caller-provided day window.

설계를 순서가 있고 원자적이며 독립적으로 검증 가능한 태스크 단위로 분해합니다.

Guide to working effectively with Claude Code CLI.

Develop lightweight Flask APIs with routing, blueprints, database integration, authentication, and request/response handling. Use when building RESTful APIs, microservices, or lightweight web services with Flask.

Audit SpawnForge code for changes that block future multiplayer networking. Use when modifying state management, entity systems, or the command pipeline — flags non-deterministic state, client-authoritative patterns, and unsyncable mutations.

Orchestrates Story tasks. Prioritizes To Review -> To Rework -> Todo, delegates to ln-401/402/403/404. Sets Story to To Review when all tasks Done. Metadata-only loading.

Audit and refactor CSS to comply with Game Loopers design system and BEM methodology

- **Category**: compute

Scrape unread articles from a Feedly category, extract music tracks, search YouTube, and render results as an HTML page with embedded video players.

workflow-team

Guide for creating custom Claude Code slash commands with proper structure, argument handling, frontmatter configuration, and best practices. Use when the user wants to create slash commands, custom commands, reusable prompts, or mentions creating/designing/building commands.

Create a release for CodeCompress following Gitflow conventions, Semantic Versioning, and .NET version management. Handles version bumps in Directory.Build.props, CHANGELOG generation, and PR creation.

Full project audit orchestration - Architecture + Security + Code Quality → consolidated report → optional remediation. Use when user invokes /audit command, for pre-release health checks, when onboarding to an unfamiliar codebase, for periodic project quality reviews, or before/after a major architectural change. Covers scope detection, severity aggregation, report format, health scoring, and remediation routing.

Use when building a HISAT2 graph-based index from reference sequences for splice-aware RNA-seq alignment, optionally incorporating SNPs, haplotypes, splice sites, or exon annotations.

>

CLI command patterns for the autopilot CLI using Command, CLI, and argparse. Use when adding commands, subcommands, or modifying global flags.

>

Analiza el chat de WhatsApp exportado en la carpeta Chat/ y genera un reporte visual HTML

>