Is the Make Trace skill free?

Yes. The skill itself is free from AIScientists-Dev/Flowtrace. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Make Trace SkillProof Score?

7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Make Trace?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Make Trace with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Make Trace

Lift any runbook, SKILL.md or chat log into a runnable Flowtrace DAG and drive the full run lifecycle

by AIScientists-Dev · AIScientists-Dev/Flowtrace

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.6/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 1763951

The skill files install cleanly, but every command it teaches (init, validate, run, reply, serve) depends on a flowtrace binary that must be built from source with Rust + Node - and the build fails outright without a cargo toolchain (scripts/install.sh aborted at 'cargo: command not found'). Because the binary could not be built in this environment, the actual deliverable - a runnable trace - was unmeasured, so no output delta over baseline could be shown. The SKILL.md itself is unusually thorough and honest about this multi-minute build cost.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 4/5

What Make Trace does

Turns a source that describes how a task gets done into a Flowtrace trace: a folder holding a DAG with a per-step contract that both a human and an agent read while the work runs. Requires the flowtrace CLI binary, built from Rust + Node. Use when someone wants to make a trace from a source.

How to install Make Trace

git clone https://github.com/AIScientists-Dev/Flowtrace.git
mkdir -p ~/.claude/skills
cd Flowtrace && cp -r skills/make-trace ~/.claude/skills/make-trace

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Make Trace

/make-trace Lift any runbook, SKILL.md or chat log into a runnable Flowtrace DAG and drive the full run lifecycle

It also activates on plain-language prompts like these:

Turn this deployment runbook into a runnable step-by-step DAG
Lift this chat log describing our process into a trace I can rerun
Convert our SKILL.md workflow into a DAG with per-step contracts

Frequently asked questions

Is the Make Trace skill free?: Yes. The skill itself is free from AIScientists-Dev/Flowtrace. SkillProof publishes the install command and an independent test verdict at no cost.
Does Make Trace work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. The skill files install cleanly, but every command it teaches (init, validate, run, reply, serve) depends on a flowtrace binary that must be built from source with Rust + Node - and the build fails outright without a cargo toolchain (scripts/install.sh aborted at 'cargo: command not found'). Because the binary could not be built in this environment, the actual deliverable - a runnable trace - was unmeasured, so no output delta over baseline could be shown. The SKILL.md itself is unusually thorough and honest about this multi-minute build cost.
What is the Make Trace SkillProof Score?: 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Make Trace?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Make Trace with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.