@softaworks

commit-work guides staged creation of logically-scoped git commits with clear messages. covers change inspection, patch staging, message conventions, and verification before shipping.

naming-analyzer identifies and suggests improvements for variable, function, class, and constant names across multiple languages. covers convention violations, misleading identifiers, and vague naming patterns with language-specific guidance and refactoring priorities.

react-dev covers type-safe component development, hooks typing, react 19 patterns including server components and actions, generic components, and router integration with tanstack or react router v7.

professional-communication provides frameworks for structuring emails, team messages, and meetings. covers what-why-how organization, audience calibration, and jargon translation. aimed at developers writing to peers, managers, and non-technical stakeholders.

perplexity provides web search and conversational research across three modes (search, ask, researcher agent), with explicit routing rules to avoid overlap with context7, graphite, and nx mcps. defaults to constrained result limits for token efficiency.

mui covers v7 component patterns, sx prop styling, theme integration, and responsive design through concrete examples. includes layout, grid, typography, forms, and common ui patterns with best practice guidance.

ship-learn-next converts learning content into iterative implementation cycles, splitting goals into shippable reps that prioritize doing over studying. each rep includes concrete deliverables, reflection prompts, and progression to the next iteration.

requirements-clarity guides users through systematic clarification of ambiguous specs using a 100-point scoring rubric, iterating via focused questions until achieving ≥90 clarity before generating a structured prd.

lesson-learned extracts actionable software engineering principles from git history by analyzing diffs and commits, grounding observations in actual code changes rather than generic advice.

crafting-effective-readmes provides task-based guidance (create, add, update, review) matched to project type (oss, personal, internal, config), with templates and decision trees to surface audience needs before drafting.

database-schema-designer provides sql and nosql schema generation with normalization guidance, indexing strategies, and migration patterns. covers entity modeling, constraint definition, and optimization for oltp/olap workloads, though execution clarity varies.

writing-clearly-and-concisely distills strunk and elements of style into 18 principles for prose, avoiding ai-generated patterns and supporting subagent-based copy revision against reference files.

session-handoff creates transfer documents for ai agents between context windows. specifies mode selection (create vs resume) and proactive suggestions but lacks detailed execution steps and failure handling.

meme-factory wraps memegen.link to generate memes from 100+ templates. three trigger patterns (manual, direct params, nlp) support text encoding and platform-specific sizing, but lacks detailed procedures, error handling, and concrete examples.

web-to-markdown converts webpage urls to markdown by launching a local browser instance, extracting main content via readability, and rendering as cleaned markdown with optional yaml frontmatter.

backend-to-frontend-handoff-docs generates structured api documentation after backend work completes. it aims to provide frontend developers enough context to integrate without backend questions, but lacks concrete templates or worked examples.

feedback-mastery covers structured frameworks for difficult workplace conversations using preparation-delivery-follow-up and situation-behavior-impact models, with scenario guidance for performance issues and conflicts.

c4-architecture covers mermaid-based system documentation at multiple abstraction levels. lacks specificity on when to use it and fails to address common implementation friction.

frontend-to-backend-requirements establishes a communication pattern where frontend developers document data needs without prescribing implementation, writing artifacts to a standardized markdown location for backend review and negotiation.

game-changing-features guides strategic product thinking through a five-step workflow to identify high-leverage opportunities across massive, medium, and small effort scales. it frames thinking in terms of user value and competitive differentiation rather than incremental feature addition.

domain-name-brainstormer generates domain suggestions and claims to check availability, but lacks a working procedure, explicit api integrations, or failure handling. suitable only as a naming starting point.

datadog-cli provides log querying and metric debugging capabilities via command-line interface, but lacks actionable workflow documentation and assumes external expertise.

excalidraw skill documents the token-cost problem of reading excalidraw json files and advocates for subagent delegation, but lacks concrete procedural steps or recovery guidance.

React useEffect best practices from official docs. Use when writing/reviewing useEffect, useState for derived values, data fetching, or state synchronization.…

Structured approach to workplace conflicts, performance discussions, and challenging feedback using preparation-delivery-followup framework. Use when preparing…

Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin…

Interactive daily standup/meeting update generator. Use when user says 'daily', 'standup', 'scrum update', 'status update', 'what did I do yesterday', 'prepare…

Converts OpenAPI 3.0 JSON/YAML to TypeScript interfaces and type guards. This skill should be used when the user asks to generate types from OpenAPI, convert…

Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large…

This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want…

Manual-only skill for minimizing total codebase size. Only activate when explicitly requested by user. Measures success by final code amount, not effort. Bias…

Smart dependency management for any language. Auto-detects project type, applies safe updates automatically, prompts for major versions, diagnoses and fixes…

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses…

Create professional Marp presentation slides with 7 beautiful themes (default, minimal, colorful, dark, gradient, tech, business). Use when users request slide…

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized,…

Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill…

Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design…

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on…

Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams…

gepetto — an installable skill for AI agents, published by softaworks/agent-toolkit.

draw.io diagram creation, editing, and review. Use for .drawio XML editing, PNG conversion, layout adjustment, and AWS icon usage.

Create and evolve design systems with design tokens, component architecture, accessibility guidelines, and documentation templates. Ensures consistent,…

jira — an installable skill for AI agents, published by softaworks/agent-toolkit.