All Skills

Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).

Compare multiple alternatives using explicit criteria, weighted scoring, and tradeoff analysis. Use when choosing between options, evaluating alternatives, or making decisions.

Start a local Anvil blockchain for development

Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.

Bootstrap new Swift Package Manager projects with consistent defaults and fast setup. Use when creating a new Swift package (library, executable, or tool), scaffolding package structure, applying standard platform/version defaults, initializing git, running first-step validation, or when the user asks to customize bootstrap defaults in this skill.

'Generate conventional commit messages from staged changes with correct

Complete operational workflow for implementer agents (Codex, Gemini, etc.) making code changes and writing tests. Defines the Code Change Loop, Test Writing Loop, and Issue Filing process with circuit breakers, severity levels, and escalation rules. Includes bundled scripts for specialist-review (code review) and test-review-request (test audit) that delegate to Claude CLI. Use this skill when starting any implementation task.

Structure what you're building and why now. Use when organizing products into capability blocks, creating bet backlogs, building roadmaps, or writing solution briefs. Part of the Modern Product Operating Model collection.

Consult Claude specialist agents during implementation for codebase understanding, pattern checking, security review, debugging help, and more. Use this skill whenever you're unsure about conventions, stuck on a failure, or need expert input before writing code. Does not replace the formal review gates in agent-loops — this is for mid-implementation consultation.

Update CLAUDE.md with learnings, preferences, or project context. Use when user says "update claude.md", "add to claude.md", or wants to persist something.

A simple skill for testing basic functionality. Use when you need to test the skillet CLI.

Reads and analyzes source code files or project structures, identifies bugs, and suggests structural architectural or security improvements.

Automatically generate NIH 2023-compliant Data Management and Sharing

Start AI-powered product research tasks on dupe.com. Kick off deep product research with archetype-based personas, track progress, and get comprehensive reports with product recommendations, pricing, and editorial articles. Use when the user wants to research, compare, or find the best products in a category.

Generate logic for handling mutually exclusive argument groups with clear error messages and validation in CLI applications.

'Use this skill BEFORE resource-intensive operations. Establish baselines

Integrate ora spinners with consistent styling, promise handling, and status updates for CLI progress feedback.

Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.

Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment documentation.

Assistente especializado para escrita de ficção científica jovem adulta (YA - Young Adult) com foco em crimes digitais, segurança online e questões tecnológicas para adolescentes. Incorpora técnicas de worldbuilding digital, construção de personagens adolescentes autênticos, arcos de protagonismo juvenil e precisão técnico-jurídica sobre crimes cibernéticos no Brasil (LGPD, Marco Civil da Internet, Estatuto da Criança). Usar quando o usuário precisar desenvolver personagens, plotar capítulos, criar diálogos jovens, construir o mundo digital da narrativa, pesquisar crimes virtuais reais para embasar a ficção, revisar consistência narrativa, criar sinopses e pitches editoriais. Disparar ao ver: "ficção", "YA", "jovem adulto", "personagem adolescente", "capítulo do livro", "crime digital", "história", "roteiro", "narrativa", "worldbuilding digital".

Cross-reference GitHub, Linear, Slack, and PostHog with bidirectional sync for team briefs

Guidance on when to ask clarifying questions vs proceed with standard

Assign labels or categories to items based on characteristics. Use when categorizing entities, tagging content, identifying types, or labeling data according to a taxonomy.

Check codebase compatibility with target framework versions and generate migration paths