softaworks

59 mods across 1 repository, 2.6k stars between them.

softaworks/agent-toolkit

Skill Claude CodeCodex

Create and evolve design systems with design tokens, component architecture, accessibility guidelines, and documentation templates. Ensures consistent, scalable, and accessible UI across products.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: pass 36 tokens original MIT

softaworks/agent-toolkit

Skill Claude Code

Structured approach to workplace conflicts, performance discussions, and challenging feedback using preparation-delivery-followup framework. Use when preparing for tough conversations, addressing conflicts, giving critical feedback, or navigating sensitive workplace discussions.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: pass 47 tokens original MIT

softaworks/agent-toolkit

Skill Claude CodeCodex

Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: pass 46 tokens original MIT

draw-io

28

softaworks/agent-toolkit

Skill Claude CodeCodex

For diagrams used in Quarto slides, specify defaultFontFamily in mxGraphModel tag.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: warn 33 tokens original MIT

excalidraw

29

softaworks/agent-toolkit

Skill Claude CodeCodex

Use when working with .excalidraw or .excalidraw.json files, user mentions diagrams/flowcharts, or requests architecture visualization - delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits).

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: pass 69 tokens original MIT

feedback-mastery

30

softaworks/agent-toolkit

Skill Claude Code

Navigate difficult conversations and deliver constructive feedback using structured frameworks. Covers the Preparation-Delivery-Follow-up model and Situation-Behavior-Impact (SBI) feedback technique. Use when preparing for difficult conversations, giving feedback, or managing conflicts.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: pass 51 tokens original MIT

softaworks/agent-toolkit

Skill Claude CodeCodex

Document frontend data needs for backend developers. Use when frontend needs to communicate API requirements to backend, or user says 'backend requirements', 'what data do I need', 'API requirements', or is describing data needs for a UI.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: pass 54 tokens original MIT

softaworks/agent-toolkit

Skill Claude CodeCodex

Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact features, or says 'what would make this 10x better', 'product strategy', or 'what should we build next'.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: pass 61 tokens original MIT

gemini

33

softaworks/agent-toolkit

Skill Claude CodeCodex

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 context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.

not rated 2.6k +14 7mo ago A Socket: warnSnyk: pass 53 tokens copy · 100% MIT

gepetto

34

softaworks/agent-toolkit

Skill Claude CodeCodex

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

not rated 2.6k +14 7mo ago A Socket: passSnyk: warn 35 tokens copy · 100% MIT

humanizer

35

softaworks/agent-toolkit

Skill Claude Code

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 Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…

not rated 2.6k +14 7mo ago A Socket: passSnyk: pass 111 tokens copy · 83% MIT

jira

36

softaworks/agent-toolkit

Skill Claude CodeCodex

Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.

not rated 2.6k +14 7mo ago A Socket: passSnyk: warn 67 tokens copy · 100% MIT

lesson-learned

37

softaworks/agent-toolkit

Skill Claude CodeCodex

Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to extract principles from recent work.

not rated 2.6k +14 7mo ago A Socket: passSnyk: pass 64 tokens copy · 100% MIT

marp-slide

38

softaworks/agent-toolkit

Skill Claude CodeCodex

Create professional Marp presentation slides with 7 beautiful themes (default, minimal, colorful, dark, gradient, tech, business). Use when users request slide creation, presentations, or Marp documents. Supports custom themes, image layouts, and "make it look good" requests with automatic quality improvements.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: warn 64 tokens original MIT

meme-factory

39

softaworks/agent-toolkit

Skill Claude CodeCodex

Generate memes using the memegen.link API. Use when users request memes, want to add humor to content, or need visual aids for social media. Supports 100+ popular templates with custom text and styling.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: warn 47 tokens original MIT

mermaid-diagrams

40

softaworks/agent-toolkit

Skill Claude CodeCodex

Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes…

not rated 2.6k +14 7mo ago A Socket: passSnyk: pass 143 tokens copy · 100% MIT

mui

41

softaworks/agent-toolkit

Skill Claude CodeCodex

Material-UI v7 component library patterns including sx prop styling, theme integration, responsive design, and MUI-specific hooks. Use when working with MUI components, styling with sx prop, theme customization, or MUI utilities.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: pass 48 tokens original MIT

naming-analyzer

42

softaworks/agent-toolkit

Skill Claude CodeCodex

Suggest better variable, function, and class names based on context and conventions.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: warn 20 tokens original MIT

softaworks/agent-toolkit

Skill Claude CodeCodex

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 schema to TS, create API interfaces, or generate TypeScript types from an API specification.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: pass 60 tokens original MIT

perplexity

44

softaworks/agent-toolkit

Skill Claude CodeCodex

Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7) or workspace questions.

not rated 2.6k +14 7mo ago A Socket: passSnyk: warn 59 tokens copy · 100% MIT

plugin-forge

45

softaworks/agent-toolkit

Skill Claude Code

Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: pass 54 tokens original MIT

softaworks/agent-toolkit

Skill Claude Code

Guide technical communication for software developers. Covers email structure, team messaging etiquette, meeting agendas, and adapting messages for technical vs non-technical audiences. Use when drafting professional messages, preparing meeting communications, or improving written communication.

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: pass 48 tokens original MIT

qa-test-planner

47

softaworks/agent-toolkit

Skill Claude CodeCodex

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

not rated 2.6k +14 7mo ago A Socket: warnSnyk: pass 34 tokens copy · 100% MIT

react-dev

48

softaworks/agent-toolkit

Skill Claude CodeCodex

This skill should be used when building React components with TypeScript, typing hooks, handling events, or when React TypeScript, React 19, Server Components are mentioned. Covers type-safe patterns for React 18-19 including generic components, proper event typing, and routing integration (TanStack Router, React…

not rated 2.6k +14 7mo ago A Socket: passSnyk: passSkillSpector: pass 66 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: