Make Trace

by AIScientists-Dev

Make Trace is an AI Engineering skill for Claude Code, published by AIScientists-Dev in Flowtrace.

490 stars33 forkson AIScientists-Dev/FlowtraceAdded 2026/08/26+2% in starsRepository updated 2026/06/09

View source on GitHub Download repo ZIP

agent-skillsagentic-aiaiai-agentai-agentsanthropicclaudeclaude-codeclaude-skillsclicodexcursordeveloper-toolsllm

Install in seconds

Install Make Trace

Copy Make Trace into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/AIScientists-Dev/Flowtrace/tree/main/skills/make-trace ~/.claude/skills/make-trace

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/AIScientists-Dev/Flowtrace.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/make-trace/SKILL.md in AIScientists-Dev/Flowtrace
Installs to: ~/.claude/skills/make-trace
Collection: One of 3 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Make Trace does

Make Trace turns a source that describes how work is done into a runnable Morph trace. It lifts the source into a DAG, writes step contracts, places inputs, and drives the run lifecycle to verify the trace.

Make Trace is cataloged under AI Engineering on DirSkills. Make Trace comes from a repository tagged agent-skills, agentic-ai, ai, ai-agent and ai-agents.

Documentation

README

Excerpt

Make Trace

You turn a source (anything that describes how a kind of task gets done) into a trace: a folder holding a DAG that a human and an AI both read while the work runs. This skill covers the whole path, from a blank folder to a finished run.

Before you start

Two reads give you the full surface. Do them once:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Make Trace

What else does AIScientists-Dev publish alongside Make Trace?
Make Trace is one of 3 skills that DirSkills catalogs from AIScientists-Dev/Flowtrace, the repository it ships in. Its siblings there include Idempotent Side Effects and Mira Tan Perspective. Each one is a separate skill with its own page in this directory, installs the same way Make Trace does, and is maintained by AIScientists-Dev in that same repository. The rest of the collection is listed on the AIScientists-Dev/Flowtrace page.
How does Make Trace compare to other AI Engineering skills?
Make Trace ranks #2191 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Make Trace against them. Open each page to compare what they document and how they install.