Make technology decisions for every capability your product needs — starting with what you already have, then evaluating what fits, then deciding what to build.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →Make technology decisions for every capability your product needs — starting with what you already have, then evaluating what fits, then deciding what to build.
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.
!`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."`
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.
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.
>-
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.
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
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
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.
>
>
Systematisch Dart-Treffer-Videos und Ground-Truth-Daten aufnehmen, um die Single-Cam Dart-Erkennung zu verbessern.
Persistent session memory for Ethereal. Maintains context between Cowork sessions so nothing gets lost. Updates CLAUDE.md, tracks open tasks, records decisions, and ensures session handoffs are clean. Use at START and END of every session.
Comprehensive Git workflow automation including branching strategies, pull request creation, code reviews, merge strategies, and release management. Use when Claude needs to help with Git operations, branching models (Git Flow, GitHub Flow), pull request creation, code reviews, merge conflicts, or release processes.
> Auto-generated skill from repository analysis
pinchtab-react-click-fix
Complete mastery of essential modern web development libraries and dependencies. Cover Next.js, React, TypeScript, Tailwind CSS, Firebase, Zustand, redux-toolkit, react-hook-form, Zod, shadcn/ui, lucide-react, Stripe, and more. Learn setup, integration patterns, advanced usage, performance optimization, troubleshooting, common pitfalls, and version management. Includes quick reference guides, in-depth tutorials, complete examples for e-commerce and SaaS, configuration files, type definitions, error handling, and production patterns. Master how libraries work together and solve real-world challenges.
>-
>
Run the AI Voice Analyzer on blog content to detect AI-sounding patterns and get actionable rewrite suggestions. Use when reviewing or improving blog articles before publishing.
Helps create vvvv gamma editor extensions — .HDE.vl file naming, Command node registration with keyboard shortcuts, SkiaWindow/SkiaWindowTopMost window types, docking with WindowFactory, and API access to hovered/selected nodes via VL.Lang Session nodes. Use when building editor plugins, custom tooling windows, or automating editor workflows.
>
This skill should be used when documenting significant technical decisions, reviewing past architectural choices, or establishing decision processes. It provides ADR templates and best practices.
>
Draft email and tweet for a new blog post. Reads the latest post from campedersen.com, generates Kit.com broadcast copy and a tweet, ready to paste.
gstack-open-gstack-browser
Increment the project version (SemVer) and consolidate the agent session changelog into a formal release entry in CHANGELOG.md
MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows
Every CLI in `src/pyishlib/` uses argparse subcommands — never flag-based
Compare multiple strategies or directions (long vs short vs both) on the same symbol. Generates side-by-side stats table.
Check SI notebooks in notebooks/manuscripts/ for deprecated API usage, hardcoded paths, stale parameter names, and compatibility with the current TEXAS package. Use after refactors or before paper submission.
InstaMolt shared package (@instamolt/shared) — constants, types, moderation prompts, and resilience utilities (CircuitBreaker, retryAsync) shared between Next.js and media server. Load when working on shared constants, moderation prompts, workspace packages, circuit breaker, retry logic, or cross-package imports.
>
Quick-fix mode for small targeted changes
Runs a strict-but-fair ICLR/CVPR/SIGGRAPH reviewer challenge on idea, roadmap, or full paper, with major-risk diagnostics and actionable repair paths. Use when the user wants high-pressure review questioning instead of brainstorming.