Skills troubleshoot

📦

troubleshoot

Name: troubleshoot
Author: Chachamaru127

Content revision r1 High Risk ⚙️ External commands📁 Filesystem access

Diagnose Code and Build Failures

Broken builds, blank screens, and dependency errors slow project work. This skill guides structured diagnosis, evidence collection, fixes, and escalation.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "troubleshoot" from https://skillstore.io/skills/chachamaru127-troubleshoot.md and its manifest at https://skillstore.io/api/skills/chachamaru127-troubleshoot/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/chachamaru127-troubleshoot.md Signed manifest GET /api/skills/chachamaru127-troubleshoot/manifest Signed lockfile GET /api/skills/chachamaru127-troubleshoot/lockfile

Test it

Using "troubleshoot". The screen is blank after the latest change.

Expected outcome:

A concise diagnosis lists likely runtime, routing, or build causes, then asks for console evidence before recommending a fix.

Using "troubleshoot". npm install fails with a dependency conflict.

Expected outcome:

The response explains the dependency conflict, separates safe checks from modifying actions, and requests approval before changing dependencies.

Using "troubleshoot". The same error returns after three repair attempts.

Expected outcome:

The skill prepares a shareable report with the error summary, attempted fixes, suspected root cause, and escalation notes.

Security Audit

High Risk

v8 • 7/5/2026 Open versioned report

The skill is mostly troubleshooting guidance, and many backtick findings are markdown false positives. Confirmed risks remain where it directs npm, git, build, and test execution, especially an automatic npm install flow without clear confirmation.

Files scanned

289

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

High

SKILL.md:145-153

Unprompted Dependency Installation Guidance

The automatic-fix pattern says the skill will run npm install after detecting a missing module. That can change dependency state and execute package lifecycle scripts without a separate confirmation step.

The cited example explicitly presents automatic repair and npm install execution. The risk is contextual because the skill also includes a separate confirmation pattern elsewhere.

Capability review items (10)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

SKILL.md:51-63

Ruby/shell backtick execution

```bash

The diagnostic block instructs Bash execution of node, npm, git, build, test, and dependency commands. npm scripts can execute project-defined code, so this is a real external-command risk.

Medium

SKILL.md:63-69

Ruby/shell backtick execution

```

Although the trigger is a markdown fence, the range reaches the dependency response that recommends npm install. npm install modifies dependencies and can run package lifecycle scripts.

Medium

SKILL.md:69

Ruby/shell backtick execution

| 依存関係 | `Cannot find module` | `npm install` |

The line explicitly recommends npm install as an automatic response to missing modules. Package installation can alter the project and execute install hooks.

Medium

SKILL.md:116-123

Ruby/shell backtick execution

エラー: `ERESOLVE unable to resolve dependency tree`

The example proposes clearing cache and reinstalling node_modules after user confirmation. The exact command is not shown, but the intended package-manager operations can modify files and run scripts.

Medium

SKILL.md:145-152

Ruby/shell backtick execution

```

The automatic-fix example says it will run npm install. That package-manager action changes dependencies and may execute dependency lifecycle scripts.

Medium

SKILL.md:152-154

Ruby/shell backtick execution

→ `npm install` を実行中...

The line explicitly states that npm install is being executed. This is a real external command with filesystem, network, and install-script impact.

Medium

SKILL.md:187-206

Ruby/shell backtick execution

```

The FAQ range includes using git log to inspect recent changes. This is a legitimate diagnostic command, but it is still external command execution.

Medium

SKILL.md:215-222

Ruby/shell backtick execution

```

The detailed diagnosis workflow calls for dependency checks, build tests, and test execution. The exact commands are omitted, but the skill is directing external tool execution.

Medium

SKILL.md:222-230

Ruby/shell backtick execution

```

The cited range reaches the preventive advice to run npm run build regularly. Running npm scripts executes project-controlled commands.

Medium

SKILL.md:230-251

Ruby/shell backtick execution

1. **定期的な `npm run build`**: 問題を早期発見

The line explicitly recommends npm run build. That executes a project-defined script and can perform arbitrary configured actions.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/chachamaru127-troubleshoot/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/chachamaru127-troubleshoot/security.svg)](https://skillstore.io/skills/chachamaru127-troubleshoot?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/chachamaru127-troubleshoot?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/chachamaru127-troubleshoot/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/chachamaru127-troubleshoot.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

Chachamaru127. (2026). troubleshoot security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/chachamaru127-troubleshoot/audits/8

BibTeX citation

@techreport{chachamaru127-chachamaru127-troubleshoot-2026,
  author = {Chachamaru127},
  title = {troubleshoot security audit report (audit version 8)},
  institution = {Skillstore},
  year = {2026},
  number = {8},
  url = {https://skillstore.io/skills/chachamaru127-troubleshoot/audits/8},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "troubleshoot security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
  - name: "Chachamaru127"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/chachamaru127-troubleshoot/audits/8"
identifiers:
  - type: other
    value: "skillstore:chachamaru127-troubleshoot:audit:8"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Recover From a Broken App

Collect symptoms, identify likely categories, and receive a simple repair path for common project failures.

Debug Frontend Behavior

Reproduce UI bugs, inspect console or network evidence, and connect symptoms to source files.

Prepare an Escalation Report

Summarize errors, attempted fixes, and likely causes when repeated troubleshooting does not resolve the issue.

Try These Prompts

Start Basic Diagnosis

Diagnose this project problem. The app is not working, and I need a simple explanation of the likely cause and next step.

Investigate a Blank Screen

Diagnose why the page is blank. Check likely build, runtime, routing, and browser console causes before suggesting a fix.

Analyze an npm Failure

Analyze this npm or dependency failure. Explain the probable cause, side effects of each fix, and ask before running package commands.

Create a Troubleshooting Report

Create an escalation report with symptoms, evidence, commands reviewed, fixes attempted, remaining hypotheses, and the safest next actions.

Best Practices

Provide the exact symptom, recent change, and expected behavior before diagnosis starts.
Review any package-manager, build, test, Git, or file-changing action before approval.
Keep logs and reproduction steps attached to each troubleshooting attempt.

Avoid

Running dependency or Git fixes without reading the proposed side effects.
Treating sample output as proof that the same cause exists in your project.
Skipping escalation after repeated failed automatic repair attempts.

Frequently Asked Questions

What problems does this skill target?

It targets broken apps, build errors, dependency failures, Git issues, UI bugs, and LSP-detected code problems.

Does it work only with Claude?

No. The report lists support for Claude, Codex, and Claude Code.

Will it run commands automatically?

It may suggest commands. Review and approve package, build, test, Git, and file-changing actions before execution.

Can it fix dependency conflicts?

It can explain likely causes and suggest repair steps, but dependency changes should be confirmed by the user.

Can it diagnose UI bugs?

Yes. It guides reproduction, browser evidence collection, source review, and verification after a fix.

What happens if the issue remains unresolved?

It guides creation of an escalation report with evidence, attempted fixes, and likely causes.

Developer Details

Author

Chachamaru127

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/Chachamaru127/claude-code-harness/tree/main/skills/troubleshoot

Ref

02f077c174c5335e2f5d02ca15e77b70d9543e58

Maintenance freshness

7/20/2026

Usage

6 downloads · 222 views

File structure

📄 SKILL.md

troubleshoot

Install with my Agent

Agent-readable resources

Test it

Security Audit

Confirmed security concerns (1)

Risk Factors

Copy report link

Markdown badge

HTML badge

Embed card

APA citation

BibTeX citation

CITATION.cff

Skillstore Score

What You Can Build

Recover From a Broken App

Debug Frontend Behavior

Prepare an Escalation Report

Try These Prompts

Best Practices

Avoid

Frequently Asked Questions

Developer Details