Agent skill

Test Failure Investigator

by proffesor-for-testing in proffesor-for-testing/agentic-qe

A skill your agent uses when a test is failing and you need to determine root cause: is it flaky, an environment issue, or a real regression?

MITAuto-check passedTesting & QA

Install Test Failure Investigator

skills CLI

$ npx skills add proffesor-for-testing/agentic-qe --skill test-failure-investigator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install proffesor-for-testing/agentic-qe test-failure-investigator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/proffesor-for-testing/agentic-qe.git skills-src && mkdir -p .claude/skills && cp -r skills-src/assets/skills/test-failure-investigator .claude/skills/test-failure-investigator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "test-failure-investigator" agent skill from https://github.com/proffesor-for-testing/agentic-qe/tree/main/assets/skills/test-failure-investigator into .claude/skills/test-failure-investigator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-failure-investigator", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/proffesor-for-testing/agentic-qe/tree/main/assets/skills/test-failure-investigator

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add proffesor-for-testing/agentic-qe --skill test-failure-investigator -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install proffesor-for-testing/agentic-qe test-failure-investigator --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/proffesor-for-testing/agentic-qe.git skills-src && mkdir -p .agents/skills && cp -r skills-src/assets/skills/test-failure-investigator .agents/skills/test-failure-investigator && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "test-failure-investigator" agent skill from https://github.com/proffesor-for-testing/agentic-qe/tree/main/assets/skills/test-failure-investigator into .agents/skills/test-failure-investigator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-failure-investigator", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add proffesor-for-testing/agentic-qe --skill test-failure-investigator -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install proffesor-for-testing/agentic-qe test-failure-investigator --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/proffesor-for-testing/agentic-qe.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/assets/skills/test-failure-investigator .cursor/skills/test-failure-investigator && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "test-failure-investigator" agent skill from https://github.com/proffesor-for-testing/agentic-qe/tree/main/assets/skills/test-failure-investigator into .cursor/skills/test-failure-investigator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-failure-investigator", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/proffesor-for-testing/agentic-qe.git --path assets/skills/test-failure-investigator

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add proffesor-for-testing/agentic-qe --skill test-failure-investigator -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install proffesor-for-testing/agentic-qe test-failure-investigator --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/proffesor-for-testing/agentic-qe.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/assets/skills/test-failure-investigator .gemini/skills/test-failure-investigator && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "test-failure-investigator" agent skill from https://github.com/proffesor-for-testing/agentic-qe/tree/main/assets/skills/test-failure-investigator into .gemini/skills/test-failure-investigator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-failure-investigator", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install proffesor-for-testing/agentic-qe test-failure-investigator

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add proffesor-for-testing/agentic-qe --skill test-failure-investigator -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/proffesor-for-testing/agentic-qe.git skills-src && mkdir -p .github/skills && cp -r skills-src/assets/skills/test-failure-investigator .github/skills/test-failure-investigator && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "test-failure-investigator" agent skill from https://github.com/proffesor-for-testing/agentic-qe/tree/main/assets/skills/test-failure-investigator into .github/skills/test-failure-investigator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-failure-investigator", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add proffesor-for-testing/agentic-qe --skill test-failure-investigator -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install proffesor-for-testing/agentic-qe test-failure-investigator --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/proffesor-for-testing/agentic-qe.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/assets/skills/test-failure-investigator .opencode/skills/test-failure-investigator && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "test-failure-investigator" agent skill from https://github.com/proffesor-for-testing/agentic-qe/tree/main/assets/skills/test-failure-investigator into .opencode/skills/test-failure-investigator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-failure-investigator", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: test-failure-investigator
GitHub stars: 495
Token cost: ~811 tokens
SKILL.md length: 216 words
Files: 1
Skills in repo: 93
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A skill your agent uses when a test is failing and you need to determine root cause: is it flaky, an environment issue, or a real regression?

Works in 5 steps: Classify the Failure → Narrow the Scope → Root Cause Analysis → …
A test is failing and you need to determine root cause: is it flaky
SKILL.md covers Activation, Investigation Flow, Composition and Gotchas
Calls git, npx and npm

What it does

Test Failure Investigator is an agent skill from proffesor-for-testing/agentic-qe. Use when a test is failing and you need to determine root cause: is it flaky, an environment issue, or a real regression? Traces failure from symptom to fix.

Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Failing and flaky tests and Root cause analysis. The repository describes itself as: Agentic QE Fleet is an open-source AI-powered QA/QE platform designed for use with Coding Agents (works best with Claude Code) featuring specialized agents and skills to support… The licence is MIT.

When your agent uses it

A test is failing and you need to determine root cause: is it flaky
An environment issue
A real regression?

Example prompts

“/test-failure-investigator”

Requirements

Node.js
Docker

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Classify the Failure
Narrow the Scope
Root Cause Analysis
Flaky Test Investigation
Report

What it can do on your machine

Read from SKILL.md and the folder at commit 1363bc7. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- git
- npx
- npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, npx and npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Test Failure Investigator loads about 811 tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 216 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~46
When it runs · the whole SKILL.md, loaded when a task matches: ~811

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from proffesor-for-testing/agentic-qe at commit 1363bc7, republished under its MIT licence (© proffesor-for-testing). 216 words, ~811 tokens.

Download SKILL.mdSave it as .claude/skills/test-failure-investigator/SKILL.md (or your agent's skills folder).

name: test-failure-investigator
description: Use when a test is failing and you need to determine root cause: is it flaky, an environment issue, or a real regression? Traces failure from symptom to fix.
user-invocable: true

Test Failure Investigator

Runbook-style skill for systematic test failure investigation. Given a failing test, determines root cause and recommends action.

Activation

/test-failure-investigator [test-name-or-file]

Investigation Flow

Step 1: Classify the Failure

Run the test 3 times and classify:

Result Pattern	Classification	Action
Fails consistently	Regression or Environment	Continue to Step 2
Fails intermittently	Flaky	Skip to Step 4
Passes now	Transient	Check CI logs, environment diff

bash

# Run test 3 times
for i in 1 2 3; do npx jest {{test_file}} 2>&1 | tail -5; echo "--- Run $i ---"; done

Step 2: Narrow the Scope

bash

# When did it start failing?
git log --oneline -20 -- {{related_source_files}}

# What changed recently?
git diff HEAD~5 -- {{related_source_files}}

# Does it fail in isolation?
npx jest {{test_file}} --testNamePattern="{{test_name}}"

# Does it fail with other tests?
npx jest --runInBand  # sequential execution

Step 3: Root Cause Analysis

Symptom	Likely Cause	Investigation
Timeout	Network/DB dependency	Check external service availability
Assertion mismatch	Logic change	Compare expected vs actual, check git blame
Import error	Dependency change	Check package.json changes, run `npm ci`
Permission denied	Environment	Check file permissions, Docker volumes
Out of memory	Resource leak	Profile with `--detectOpenHandles`

Step 4: Flaky Test Investigation

bash

# Run 10 times to confirm flakiness
for i in $(seq 1 10); do npx jest {{test_file}} --forceExit 2>&1 | grep -E 'PASS|FAIL'; done

# Common flaky causes:
# - Shared state between tests (missing cleanup)
# - Time-dependent assertions (use fake timers)
# - Race conditions (missing await)
# - Port conflicts (use random ports)
# - Order dependency (run with --randomize)

Step 5: Report

markdown

## Test Failure Report
- **Test**: {{test_name}}
- **File**: {{test_file}}
- **Classification**: Regression / Flaky / Environment / Transient
- **Root Cause**: {{description}}
- **First Failed**: {{commit_hash}} ({{date}})
- **Fix**: {{recommended_action}}
- **Verified**: [ ] Fix applied and test passes 3x consecutively

Composition

After investigation, compose with:

/bug-reporting-excellence — if regression found, file a bug report
/regression-testing — if regression, add to regression suite
/qe-test-execution — for re-running tests after fix

Gotchas

Agent may guess at root cause without running the test — always reproduce first
"Works on my machine" is not a diagnosis — compare environments (node version, OS, deps)
Flaky tests that pass 9/10 times will still be reported as "passing" by CI — run 10+ times
Test isolation failures are the #1 cause of flaky tests — check for shared state in beforeAll/afterAll

Files

Just SKILL.md in assets/skills/test-failure-investigator of proffesor-for-testing/agentic-qe.

Open the folder on GitHubat commit 1363bc7

Compare with similar skills

Test Failure Investigator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Test Failure Investigator compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Test Failure Investigator this skillproffesor-for-testing/agentic-qe	495	—	~811	Automated safety check: Pass	MIT	yesterday
Trx Analysismicrosoft/vstest	969	—	~1.8k	Automated safety check: Pass	MIT	yesterday
Evanflow Debugevanklem/evanflow	418	—	~760	Automated safety check: Pass	Custom licence	5 mo ago
Issue TracerZaxbyHub/opencode-swarm	494	—	~383	Automated safety check: Pass	MIT	yesterday
Issue TracerZaxbyHub/opencode-swarm	494	—	~397	Automated safety check: Pass	MIT	yesterday
Pester Failure AnalysisPowerShell/PowerShell	56k	—	~5.1k	Automated safety check: Pass	MIT	yesterday

Similar skills

Trx Analysis
microsoft/vstest
Official
Parse and analyze Visual Studio TRX test result files. An agent skill from microsoft/vstest.
969 GitHub stars~1.8k tokensUpdated yesterday
Testing & QAAuto-check passed
Evanflow Debug
evanklem/evanflow
Root-cause discipline for bugs, test failures, and unexpected behavior.
418 GitHub stars~760 tokensUpdated 5 mo ago
Testing & QAAuto-check passed
Issue Tracer
ZaxbyHub/opencode-swarm
A skill your agent uses when asked to trace, investigate, root-cause, reproduce, plan, fix, resolve, close, or prepare a PR for an issue, bug report, defect, regression, failing test, or confusing…
494 GitHub stars~383 tokensUpdated yesterday
Testing & QAAuto-check passed
Issue Tracer
ZaxbyHub/opencode-swarm
A skill your agent uses when asked to trace, investigate, root-cause, reproduce, plan, fix, resolve, close, or prepare a PR for an issue, bug report, defect, regression, failing test, or confusing…
494 GitHub stars~397 tokensUpdated yesterday
Testing & QAAuto-check passed
Pester Failure Analysis
PowerShell/PowerShell
Investigates failing Pester tests in PowerShell CI jobs by following a six-step workflow from pull request status to documented fix recommendations.
56k GitHub stars~5.1k tokensUpdated yesterday
Testing & QAAuto-check passed
Diagnose Playwright Failure as Product Bug
appsmithorg/appsmith
Investigates a stubbornly failing Playwright test as a possible product bug, using error output, screenshots, traces and server code, and writes a structured bug report.
41k GitHub stars~1.5k tokensUpdated yesterday
Testing & QAAuto-check passed

Questions about Test Failure Investigator

What does Test Failure Investigator do?

A skill your agent uses when a test is failing and you need to determine root cause: is it flaky, an environment issue, or a real regression? Test Failure Investigator is an agent skill from proffesor-for-testing/agentic-qe. Use when a test is failing and you need to determine root cause: is it flaky, an environment issue, or a real regression?

When should I use Test Failure Investigator?

Test Failure Investigator fits situations like: A test is failing and you need to determine root cause: is it flaky; an environment issue; A real regression?.

How do I install Test Failure Investigator in Claude Code?

Run `npx skills add proffesor-for-testing/agentic-qe --skill test-failure-investigator -a claude-code`. Or copy the skill folder (assets/skills/test-failure-investigator in proffesor-for-testing/agentic-qe) into .claude/skills/test-failure-investigator in your project. Claude Code loads it when a task matches its description.

How do I install Test Failure Investigator in Codex?

Run `npx skills add proffesor-for-testing/agentic-qe --skill test-failure-investigator -a codex`. Or copy the skill folder (assets/skills/test-failure-investigator in proffesor-for-testing/agentic-qe) into .agents/skills/test-failure-investigator in your project. Codex loads it when a task matches its description.

Can I use Test Failure Investigator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add proffesor-for-testing/agentic-qe --skill test-failure-investigator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/test-failure-investigator, .gemini/skills/test-failure-investigator, .github/skills/test-failure-investigator and .opencode/skills/test-failure-investigator in your project.

What does Test Failure Investigator need to run?

Going by SKILL.md and its folder, Test Failure Investigator needs the command-line tools its instructions call (git, npx and npm). Our summary lists: Node.js; Docker.

Does Test Failure Investigator access the network?

SKILL.md contains no URLs. Its commands use git, npx and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Test Failure Investigator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Test Failure Investigator use?

Test Failure Investigator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Test Failure Investigator use?

About 811 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Test Failure Investigator?

Skills that share tags, products or a category with Test Failure Investigator: Trx Analysis (microsoft/vstest, 969 stars), Evanflow Debug (evanklem/evanflow, 418 stars), Issue Tracer (ZaxbyHub/opencode-swarm, 494 stars) and Issue Tracer (ZaxbyHub/opencode-swarm, 494 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Test Failure Investigator?

proffesor-for-testing (a GitHub user) maintains it in proffesor-for-testing/agentic-qe, which has 495 GitHub stars. The repository holds 93 skills in this directory. The repository was last updated on October 9, 2026.

Source: proffesor-for-testing/agentic-qe on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Test Failure Investigator

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Test Failure Investigator

Activation

Investigation Flow

Step 1: Classify the Failure

Step 2: Narrow the Scope

Step 3: Root Cause Analysis

Step 4: Flaky Test Investigation

Step 5: Report

Composition

Gotchas

Files

Compare with similar skills

Similar skills

More from proffesor-for-testing/agentic-qe

Related

Questions about Test Failure Investigator