$ ~/registry/skill/microsoft-agency-plugins-nori-skills-root-cause-tracing

SKILL

root-cause-tracing

Name: root-cause-tracing
Author: microsoft

Trace errors backward through execution paths to identify the true root cause.

Stars

★ 4,934

Source

GitHub

Updated

2026-07-14

// securityLow risk

Prompt only, no code
Open source
Community-trusted· 4.9k

Running security audit…

Credentials
Network egress
Code execution
Data access
Supply chain

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "root-cause-tracing" skill from askskill:
1. Download https://raw.githubusercontent.com/microsoft/FluidFramework/main/.agency/plugins/nori/skills/root-cause-tracing/SKILL.md
2. Save it as ~/.claude/skills/root-cause-tracing/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Trace an abnormal API response

Prompt

Help me perform root-cause tracing: an API endpoint returns an incorrect user status. Start from the failure point, trace backward through the call chain, show each layer’s inputs, outputs, and key state changes, and identify the most likely source issue. If information is missing, suggest what logs or breakpoints to add.

Expected

A backward call-chain investigation showing suspicious steps, evidence, and recommended instrumentation points.

Locate the source of dirty data

Prompt

I found abnormal order amounts in a downstream report. Trace backward from the bad output to the original data write source, analyze which processing step may have introduced the incorrect value, and provide ways to validate each hypothesis.

Expected

A reverse data-flow analysis showing where the bad value likely appeared, why, and how to verify it.

Analyze a crash in deep call stacks

Prompt

The program crashes deep inside nested function calls, but the visible error message is unclear. Use the call stack to trace backward step by step, find the earliest point where the state became invalid, and suggest a minimal reproduction and fix.

Expected

A root-cause report including the earliest invalid state, reproduction steps, and fix recommendations.

// docs

Root Cause Tracing

Overview

Bugs often manifest deep in the call stack (git init in wrong directory, file created in wrong location, database opened with wrong path). Your instinct is to fix where the error appears, but that's treating a symptom.

Core principle: Trace backward through the call chain until you find the original trigger, then fix at the source.

When to Use

digraph when_to_use {
    "Bug appears deep in stack?" [shape=diamond];
    "Can trace backwards?" [shape=diamond];
    "Fix at symptom point" [shape=box];
    "Trace to original trigger" [shape=box];

    "Bug appears deep in stack?" -> "Can trace backwards?" [label="yes"];
    "Can trace backwards?" -> "Trace to original trigger" [label="yes"];
    "Can trace backwards?" -> "Fix at symptom point" [label="no - dead end"];
}

Use when:

Error happens deep in execution (not at entry point)
Stack trace shows long call chain
Unclear where invalid data originated
Need to find which test/code triggers the problem

The Tracing Process

1. Observe the Symptom

Error: git init failed in /Users/jesse/project/packages/core

2. Find Immediate Cause

What code directly causes this?

await execFileAsync('git', ['init'], { cwd: projectDir });

3. Ask: What Called This?

WorktreeManager.createSessionWorktree(projectDir, sessionId)
  → called by Session.initializeWorkspace()
  → called by Session.create()
  → called by test at Project.create()

4. Keep Tracing Up

What value was passed?

projectDir = '' (empty string!)
Empty string as cwd resolves to process.cwd()
That's the source code directory!

5. Find Original Trigger

Where did empty string come from?

const context = setupCoreTest(); // Returns { tempDir: '' }
Project.create('name', context.tempDir); // Accessed before beforeEach!

Adding Stack Traces

When you can't trace manually, add instrumentation:

// Before the problematic operation
async function gitInit(directory: string) {
  const stack = new Error().stack;
  console.error('DEBUG git init:', {
    directory,
    cwd: process.cwd(),
    nodeEnv: process.env.NODE_ENV,
    stack,
  });

  await execFileAsync('git', ['init'], { cwd: directory });
}

Critical: Use console.error() in tests (not logger - may not show)

Run and capture:

npm test 2>&1 | grep 'DEBUG git init'

Analyze stack traces:

Look for test file names
Find the line number triggering the call
Identify the pattern (same test? same parameter?)

Finding Which Test Causes Pollution

If something appears during tests but you don't know which test:

Use the bisection script: @find-polluter.sh

./find-polluter.sh '.git' 'src/**/*.test.ts'

Runs tests one-by-one, stops at first polluter. See script for usage.

Real Example: Empty projectDir

Symptom: .git created in packages/core/ (source code)

Trace chain:

git init runs in process.cwd() ← empty cwd parameter
WorktreeManager called with empty projectDir
Session.create() passed empty string
Test accessed context.tempDir before beforeEach
setupCoreTest() returns { tempDir: '' } initially

Root cause: Top-level variable initialization accessing empty value

Fix: Made tempDir a getter that throws if accessed before beforeEach

Also added validation at multiple layers:

Layer 1: Project.create() validates directory
Layer 2: WorkspaceManager validates not empty
Layer 3: NODE_ENV guard refuses git init outside tmpdir
Layer 4: Stack trace logging before git init

Key Principle

digraph principle {
    "Found immediate cause" [shape=ellipse];
    "Can trace one level up?" [shape=diamond];
    "Trace backwards" [shape=box];
    "Is this the source?" [shape=diamond];
    "Fix at source" [shape=box];

…

View full docs ↗