Graph Max
Turn any hand-drawn workflow graph into a working multi-agent script. Draw the graph in any tool (whiteboard, paper, Excalidraw, napkin), photograph or screenshot it, send it to a coding agent with a single prompt, and get a running orchestration script back. The skill teaches graph literacy — how to draw nodes, edges, fan-outs, feedback loops, and decision gates so the coding agent can implement them faithfully. Use when someone has a workflow in their head but no code, wants to orchestrate multiple agents, or asks "how do I wire these steps together?
Install
npx skills add sidneyswift/skills --skill graph-maxgit clone --depth 1 https://github.com/sidneyswift/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/graph-max ~/.claude/skills/graph-maxPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Graph-Max ## Overview Most workflows live in someone's head as a vague sequence. They stay there because turning them into code feels like a big jump. Graph-max eliminates that jump entirely: 1. Draw the workflow as a graph. 2. Send the image to a coding agent: *"Write a code mode script that implements this workflow. Run it with \<your inputs\>."* 3. There is no step 3. The graph is the spec. The coding agent reads the topology — nodes, edges, fan-outs, loops, decision gates — and writes an orchestration script that runs the whole thing. No framework, no boilerplate, no intermediate abstraction. Just a picture and a prompt. This skill teaches you how to draw graphs that coding agents can implement faithfully, and how to prompt for the result. ## When to use - "I have a workflow but no code" - "How do I orchestrate multiple agents?" - "I want to wire these steps together" - "How do I build a pipeline with reviewers / validators / loops?" - "I drew this on a whiteboard, can you implement it?" - "I need a multi-step agent workflow" - Any variant of "I know the process, I just need it automated" ## Graph vocabulary A coding agent can implement any graph, but it needs to understand what each element means. Use this vocabulary consistently. ### Nodes (the boxes) Every box is a step that does one thing. Label it with what it does, not how: | Shape | Meaning | Example | |---|---|---| | Rounded rectangle | Processing step | "Worker", "Planner", "Summarizer" |
Details
- Skill name
graph-max- Repository
- sidneyswift/skills
- Path
graph-max/SKILL.md- Repo updated
- 9 November 2026
FAQ
What does the Graph Max skill do?
Turn any hand-drawn workflow graph into a working multi-agent script. Draw the graph in any tool (whiteboard, paper, Excalidraw, napkin), photograph or screenshot it, send it to a coding agent with a single prompt, and get a running orchestration script back. The skill teaches graph literacy — how to draw nodes, edges, fan-outs, feedback loops, and decision gates so the coding agent can implement them faithfully. Use when someone has a workflow in their head but no code, wants to orchestrate multiple agents, or asks "how do I wire these steps together?
How do I install the Graph Max skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add sidneyswift/skills --skill graph-max. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Graph Max popular?
It lives in sidneyswift/skills, which has 9 GitHub stars and 1 forks.
Related skills
Design Inspiration
9sidneyswift/skills
Break through design blocks by systematically mining curated inspiration sources. When you're stuck on UI, brand, layout, or visual direction, this skill walks you through nine high-signal design galleries — each covering a different design surface — to find patterns, steal structure, and restart your creative momentum. Use when someone is stuck, needs visual references, wants to explore design directions, or asks "what should this look like?
Design Visual Experiences
9sidneyswift/skills
Create or refine original digital visual experiences where art direction, motion, interaction, or spatial behavior is central. Use for expressive interfaces, interactive explainers, creative coding, and visual films; translate relevant references into implementation decisions and inspect the delivered result.
Ecosystem Mapping
9sidneyswift/skills
Take a core solution or transformation and map every friction point around it into a compounding product ecosystem — instead of building standalone products. Walks the user through identifying their core transformation, mapping friction points (before, during, after), spotting two-sided market opportunities, and designing products that strengthen each other. Use when someone has a working solution but is stuck on "what's next," wants to expand beyond a single product, or is thinking about leverage and ecosystem strategy.
Handoff Spec
9sidneyswift/skills
Produces a single markdown handoff document for a stateless successor agent (possibly on a different platform or session) to pick up in-progress work with zero conversation context. Combines a stable Goal/Spec section with a point-in-time Handoff Status section covering what's done, out-of-scope work, remaining required work, nice-to-haves, what's live in production, what's merged but not deployed, and what's still in progress. Use when the current agent is running low on usage credits, context, or tokens; when the user says things like "I'm running out of credits/usage", "we need to hand this
Gpt 56 Prompting
10Archive228/lab-skills
Operating procedure for prompting the GPT-5.6 model family (gpt-5.6-sol/terra/luna) in agentic work: outcome-first prompts with explicit stopping conditions, autonomy and approval boundaries, tool routing, Programmatic Tool Calling, multi-agent (beta), reasoning effort and verbosity settings, and safe migration from GPT-5.5/5.4. Use whenever writing or revising system/developer prompts for GPT-5.6, wiring its tools, tuning reasoning.effort or text.verbosity, or debugging over-asking, over-stopping, or tool-loop behavior on these models.
Humanizer Kill Gpt
9kargnas/skills
Runs a cross-language cleanup for writing tells shared by large frontier LLMs, not only GPT: English source constructs that survive other language translation and language-surface translationese. Use only when the user asks to remove AI/GPT tells from text (de-GPT, GPT 티, AI 티, 번역체 GPT, 자폐 말투 — colloquial shorthand for rigid or over-complete model prose, not a claim about autism).
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.