Agent skill

Vibe Flake Root Cause

by ash1794 in ash1794/vibe-engineering

Refuses "flaky" as a diagnosis. An agent skill from ash1794/vibe-engineering.

MITAuto-check passedDevelopment

Install Vibe Flake Root Cause

skills CLI
$ npx skills add ash1794/vibe-engineering --skill vibe-flake-root-cause -a claude-code

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

GitHub CLI
$ gh skill install ash1794/vibe-engineering vibe-flake-root-cause --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/ash1794/vibe-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/vibe-engineering/skills/vibe-flake-root-cause .claude/skills/vibe-flake-root-cause && 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/

Facts

Skill name
vibe-flake-root-cause
GitHub stars
163
Token cost
~783 tokens
SKILL.md length
391 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
MIT

At a glance

Refuses "flaky" as a diagnosis. An agent skill from ash1794/vibe-engineering.

  • Works in 6 steps: Record the failure exactly. Commit,… → Run it alone, cleanly. If it passes in… → List candidate variables and force each… → …
  • Performance check
  • SKILL.md covers When to Use This Skill, When NOT to Use This Skill, Steps and Output Format
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Vibe Flake Root Cause is an agent skill from ash1794/vibe-engineering. Refuses "flaky" as a diagnosis. Turns an intermittent failure into a reproduction by isolating it from the environment, naming the variable that controls it, forcing that variable, and measuring before and after with enough runs to count. Separates real defects from environment contention with evidence, and never retries to green or widens a threshold. Use when a test, performance check, or deploy step fails intermittently or passes on rerun.

Its SKILL.md is about 780 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 Development, covering Root cause analysis and Failing and flaky tests. The repository describes itself as: 33 engineering discipline skills for Claude Code, OpenAI Codex & Gemini CLI + a CLI for CI/CD enforcement. Extracted from real-world multi-agent system development. Born from… The licence is MIT.

When your agent uses it

  • Performance check
  • Deploy step fails intermittently
  • Passes on rerun

Example prompts

  • “Use the vibe-flake-root-cause skill to refuse "flaky" as a diagnosis. An agent skill from ash1794/vibe-engineering”
  • “/vibe-flake-root-cause”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Record the failure exactly. Commit, environment, profile or device, the failing value, and the threshold. Keep the log.
  2. Run it alone, cleanly. If it passes in isolation, treat it as contention until proven otherwise, and name the resource: CPU, a shared…
  3. List candidate variables and force each in turn. Common ones
  4. Reproduce at a stated rate before changing anything (for example "10 of 15 runs fail with fonts held back 600 ms"). No reproduction means…
  5. Fix the cause, not the symptom. Then rerun the forced condition N times and report the new rate (for example "0 of 240 loads across 4…
  6. Disclose any mitigation. If you clip, retry, or quarantine anything, say what, why, and why it doesn't hide a defect. Never widen a…

What it can do on your machine

Read from SKILL.md and the folder at commit 8f1d71b. 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

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

Vibe Flake Root Cause loads about 783 tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 391 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~117
When it runs · the whole SKILL.md, loaded when a task matches
~783

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 ash1794/vibe-engineering at commit 8f1d71b, republished under its MIT licence (© ash1794). 391 words, ~783 tokens.

Download SKILL.mdSave it as .claude/skills/vibe-flake-root-cause/SKILL.md (or your agent's skills folder).
name
vibe-flake-root-cause
description
Refuses "flaky" as a diagnosis. Turns an intermittent failure into a reproduction by isolating it from the environment, naming the variable that controls it, forcing that variable, and measuring before and after with enough runs to count. Separates real defects from environment contention with evidence, and never retries to green or widens a threshold. Use when a test, performance check, or deploy step fails intermittently or passes on rerun.
user-invocable
true

vibe-flake-root-cause

"Flaky" ends an investigation without finding anything, and a retry-to-green hides real defects. An intermittent failure is a hypothesis: some variable you haven't controlled decides the outcome. Find it, force it, and prove the fix with counts.

When to Use This Skill

  • "It passed on rerun"
  • A failure that shows up only in CI
  • A threshold (performance, visual diff, timeout) that fails on some runs
  • You're tempted to add a retry, raise a timeout, or loosen a tolerance

When NOT to Use This Skill

  • The failure reproduces every time (debug it directly)
  • Race conditions visible in the test code itself (use vibe-concurrent-test-safety)
  • The job died before any test ran (checkout, install, runner loss); a single re-run is fine there, but say so

Steps

  1. Record the failure exactly. Commit, environment, profile or device, the failing value, and the threshold. Keep the log.

  2. Run it alone, cleanly. If it passes in isolation, treat it as contention until proven otherwise, and name the resource: CPU, a shared port, a shared database, disk, or network. Record machine load alongside every timing measurement.

  3. List candidate variables and force each in turn. Common ones:

    • timing: network latency, font or asset arrival, animation frames
    • environment: CPU load, parallel agents or tests, shared ports and servers
    • data: ordering, time of day, random seeds, page or payload size
    • process mode: a server started in a mode the framework doesn't support in production
  4. Reproduce at a stated rate before changing anything (for example "10 of 15 runs fail with fonts held back 600 ms"). No reproduction means no root cause yet, so keep looking or report it as unresolved.

  5. Fix the cause, not the symptom. Then rerun the forced condition N times and report the new rate (for example "0 of 240 loads across 4 routes").

  6. Disclose any mitigation. If you clip, retry, or quarantine anything, say what, why, and why it doesn't hide a defect. Never widen a threshold or budget to pass (vibe-anti-rationalization-check).

Show full SKILL.md (59 more words)Show less

Output Format

Flake Investigation: [test/check]

Symptom: [value vs threshold, where, how often] Isolated run: pass / fail · Load at failure: [value]

VariableForced howFailure rate
font arrivalheld back 600 ms10/15
CPU loadrun alone0/15

Root cause: [mechanism, in one or two sentences] Fix: [change] · After: [0/N under the forced condition] Mitigations disclosed: [none / list with reasons]

© ash1794, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/vibe-engineering/skills/vibe-flake-root-cause of ash1794/vibe-engineering.

Open the folder on GitHubat commit 8f1d71b

Compare with similar skills

Vibe Flake Root Cause 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.

Vibe Flake Root Cause compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vibe Flake Root Cause this skillash1794/vibe-engineering163—~783Automated safety check: PassMIT
Backprop: Bug-to-Spec ProtocolJuliusBrussee/cavekit1.2k—~653Automated safety check: PassMIT
CI TriageMentra-Community/MentraOS2.4k—~582Automated safety check: PassApache-2.0
Root Cause Debuggingjsmastery-pro/skills1.5k—~1.8kAutomated safety check: NotesMIT
Superpowers Systematic Debuggingchristopherarter/superpowers-reasonix102—~2kAutomated safety check: PassMIT
Minimal Code Fixcobusgreyling/loop-engineering11k1 repos~345Automated safety check: NotesMIT

Similar skills

  • Backprop: Bug-to-Spec Protocol

    JuliusBrussee/cavekit

    After a bug is found, traces its root cause and feeds a new testable invariant back into the project spec so the bug class can't recur.

    1.2k GitHub stars~653 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • CI Triage

    Mentra-Community/MentraOS

    Triage failing GitHub PR checks: list failures with gh, fetch capped Actions logs, skip non-Actions checks, and summarize root cause.

    2.4k GitHub stars~582 tokensUpdated today
    DevelopmentAuto-check passed
  • Root Cause Debugging

    jsmastery-pro/skills

    Runs a reproduce, localize, hypothesize, test, fix and verify loop to find a bug's root cause, applies the minimal fix and hands off a regression test.

    1.5k GitHub stars~1.8k tokensUpdated 2 mo ago
    DevelopmentAuto-check: notes
  • Superpowers Systematic Debugging

    christopherarter/superpowers-reasonix

    Any bug, failing or flaky test, or surprise behavior?. An agent skill from christopherarter/superpowers-reasonix.

    102 GitHub stars~2k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Minimal Code Fix

    cobusgreyling/loop-engineering

    Makes the smallest code change that fixes one well-scoped problem, such as a CI failure, review comment or typo, without refactoring anything unrelated.

    11k GitHub starsUsed in 1 repo~345 tokens
    DevelopmentAuto-check: notes
  • CI Fix

    warpdotdev/oz-skills

    Diagnose and fix GitHub Actions CI failures. An agent skill from warpdotdev/oz-skills.

    825 GitHub stars~790 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from ash1794/vibe-engineering

All 33 skills in this repo
  • Vibe Concurrent Test Safety

    ash1794/vibe-engineering

    Audits tests for concurrency safety — race conditions, shared mock state, cleanup ordering.

    163 GitHub stars~665 tokensUpdated 2 days ago
    Auto-check passed
  • Vibe Fuzz Parser Inputs

    ash1794/vibe-engineering

    Generates fuzz test scaffolding for parsers handling external input (YAML, JSON, config files, user input).

    163 GitHub stars~722 tokensUpdated 2 days ago
    Auto-check passed
  • Vibe Golden File Testing

    ash1794/vibe-engineering

    Implements snapshot/golden file tests with temporal normalization so tests don't break daily.

    163 GitHub stars~669 tokensUpdated 2 days ago
    Auto-check passed
  • Vibe Parallel Task Decomposition

    ash1794/vibe-engineering

    Analyzes large tasks for independent subtasks that can be safely parallelized.

    163 GitHub stars~717 tokensUpdated 2 days ago
    Auto-check passed
  • Vibe Slop Filter

    ash1794/vibe-engineering

    Strips AI-generation "smell" from prose before it ships (READMEs, docs, release notes, PR descriptions, posts, emails).

    163 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed
  • Vibe Spec Sync

    ash1794/vibe-engineering

    Keeps specification documents and code in agreement. An agent skill from ash1794/vibe-engineering.

    163 GitHub stars~2.2k tokensUpdated 2 days ago
    Auto-check passed

Questions about Vibe Flake Root Cause

What does Vibe Flake Root Cause do?

Refuses "flaky" as a diagnosis. An agent skill from ash1794/vibe-engineering. Vibe Flake Root Cause is an agent skill from ash1794/vibe-engineering. Refuses "flaky" as a diagnosis.

When should I use Vibe Flake Root Cause?

Vibe Flake Root Cause fits situations like: performance check; deploy step fails intermittently; passes on rerun.

How do I install Vibe Flake Root Cause in Claude Code?

Run `npx skills add ash1794/vibe-engineering --skill vibe-flake-root-cause -a claude-code`. Or copy the skill folder (plugins/vibe-engineering/skills/vibe-flake-root-cause in ash1794/vibe-engineering) into .claude/skills/vibe-flake-root-cause in your project. Claude Code loads it when a task matches its description.

How do I install Vibe Flake Root Cause in Codex?

Run `npx skills add ash1794/vibe-engineering --skill vibe-flake-root-cause -a codex`. Or copy the skill folder (plugins/vibe-engineering/skills/vibe-flake-root-cause in ash1794/vibe-engineering) into .agents/skills/vibe-flake-root-cause in your project. Codex loads it when a task matches its description.

Can I use Vibe Flake Root Cause 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 ash1794/vibe-engineering --skill vibe-flake-root-cause -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vibe-flake-root-cause, .gemini/skills/vibe-flake-root-cause, .github/skills/vibe-flake-root-cause and .opencode/skills/vibe-flake-root-cause in your project.

What does Vibe Flake Root Cause need to run?

SKILL.md names no scripts, command-line tools or credentials: Vibe Flake Root Cause is instructions for the agent only.

Does Vibe Flake Root Cause access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vibe Flake Root Cause 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 Vibe Flake Root Cause use?

Vibe Flake Root Cause 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 Vibe Flake Root Cause use?

About 783 tokens (SKILL.md is roughly 3.1k 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 Vibe Flake Root Cause?

Skills that share tags, products or a category with Vibe Flake Root Cause: Backprop: Bug-to-Spec Protocol (JuliusBrussee/cavekit, 1.2k stars), CI Triage (Mentra-Community/MentraOS, 2.4k stars), Root Cause Debugging (jsmastery-pro/skills, 1.5k stars) and Superpowers Systematic Debugging (christopherarter/superpowers-reasonix, 102 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vibe Flake Root Cause?

ash1794 (a GitHub user) maintains it in ash1794/vibe-engineering, which has 163 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 7, 2026.

Source: ash1794/vibe-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.