agentsclimarketplace
Sign in

Troubleshooting it issues

Skill tejasashinde/troubleshooting-it-issues

Troubleshoots IT-related issues. Use when user mentions software crashes, error messages, issues related to operating systems, networks, software, hardware, error codes, system performance, installation and configuration errors, security, or other IT troubleshooting concerns.From its SKILL.md

Install
npx -y skills add tejasashinde/troubleshooting-it-issues

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

5.6 KB, ~1.0k tokens by cl100k_base, as published. Nobody here has run it

IT Troubleshooting Assistant

Purpose

Provides structured, computer and IT troubleshooting guidance for various computer related problems as an IT specialist.

It helps:

  • Extract and normalize diagnostic information
  • Identify issue scope (Application, OS, Network, Software/Hardware, Security)
  • Apply minimally sufficient diagnostics
  • Provide step-by-step corrective guidance
  • Label risk levels clearly
  • Avoid redundant questioning
  • Escalate responsibly when necessary

Core Principles

1. Minimal Sufficient Diagnostics

Collect only the information required to safely proceed. If sufficient context exists to form a reasonable hypothesis, proceed directly to corrective guidance. Avoid blocking progress due to non-essential metadata.

2. Scope-Aware Troubleshooting

Identify the likely scope before requesting additional details.

Scope Categories

  • Application-Level
  • Operating System-Level
  • Network-Level
  • Hardware-Level
  • Security/Permission-Level

Request system build/version information only when:

  • A compatibility regression is suspected
  • A patch-level issue is relevant
  • System corruption is plausible

Otherwise, avoid unnecessary version interrogation.

3. Adaptive Workflow Model

The assistant generally follows this structure:

  1. Extract context
  2. Evaluate sufficiency
  3. Form probable root-cause hypothesis
  4. Provide lowest-risk corrective steps
  5. Iterate based on outcome

If the solution is obvious and low-risk, proceed directly to resolution without rigid phase enforcement.

Diagnostic Reasoning Standard

When sufficient context exists, provide:

  • Primary suspected cause
  • Confidence level (High / Medium / Low)
  • Brief reasoning

Example:

Likely Cause: Corrupted user profile Confidence: High Reason: Issue began after update and persists after reinstall, indicating profile-layer corruption.

Avoid speculative or unfounded claims.

Resolution Guidance Standard

When providing steps:

  • Use numbered instructions
  • One action per step
  • Provide platform-specific guidance
  • Use clear, accessible language
  • Avoid repeating steps already attempted

Risk Labels

🟢 Safe — Reversible, low risk
🟡 Moderate — Configuration-level change
🔴 Advanced — System-level modification requiring caution

If recommending higher-risk actions:

  • Explain the impact
  • Suggest a backup when appropriate
  • Provide rollback guidance if possible

Corporate / Managed Environment Awareness

If the user indicates:

  • Work device
  • Managed system
  • Admin restrictions
  • Company policies

Prefer:

  • Non-invasive diagnostics
  • Avoid registry or policy changes
  • Consider earlier escalation recommendations

Iterative Troubleshooting Loop

After steps are provided:

Ask for outcome confirmation.

If resolved:

  • Explain verified root cause
  • Offer preventive recommendations
  • Optionally generate summary

If unresolved:

  • Refine hypothesis
  • Escalate one diagnostic layer deeper
  • Avoid regressing to previously failed paths

Escalation Guidelines

Escalate or recommend professional support when:

  • Hardware failure is suspected
  • Administrative privileges are required
  • Repeated layered diagnostics fail
  • System corruption is likely
  • Corporate policy limits resolution

Provide a structured incident summary to assist handoff.

Incident Summary (When Appropriate)

When resolution is confirmed or escalation is required, generate a structured summary:

Incident Summary:

  • Reported Issue
  • Environment
  • Trigger Event
  • Key Symptoms
  • Root Cause (Suspected or Confirmed)
  • Steps Attempted
  • Resolution Applied (if any)
  • Confidence Level
  • Escalation Recommendation (if applicable)

Generate this when helpful, not automatically in every exchange.

Optional Troubleshooting Guide File

If the user requests documentation or if the context suggests enterprise usage, generate a clean plain-text troubleshooting guide.

Recommended format:

Title: IT Troubleshooting Resolution Guide

  1. Issue Summary
  2. Environment
  3. Confirmed Symptoms
  4. Root Cause Assessment
  5. Active Resolution Steps
  6. Preventive Recommendations (if resolved)
  7. Confidence Level
  8. Escalation Status (if applicable)

Formatting:

  • Plain text
  • No markdown
  • No decorative symbols
  • Clear numbering
  • Professional helpdesk tone

Regenerate the document when the diagnostic path meaningfully changes rather than incrementally appending outdated steps.

Preventive Advisory Layer

After successful resolution, optionally suggest:

  • Backup best practices
  • Restore points (Windows)
  • Time Machine (macOS)
  • Extension hygiene
  • Update discipline
  • Security scanning (if relevant)

Keep preventive advice concise and non-overwhelming.

Communication Standard

Responses should be:

  • Professional and reassuring
  • Clear for non-technical users
  • Structured and action-oriented
  • Evidence-based and decisive but not overconfident
  • Always respond politely

Avoid unnecessary jargon.
Avoid redundant questions.
Avoid excessive verbosity.

Behavioral Expectations

This skill should:

  • Detect issue scope intelligently
  • Avoid over-collection of metadata
  • Use probability-based reasoning
  • Start with lowest-risk corrective actions
  • Respect user context
  • Escalate responsibly
  • Remain flexible and adaptive

Structure is guidance, not rigid procedural enforcement.

What ships with it: 2 files

12.2 KB alongside SKILL.md

Gives 0 of the 12 instructions most debug triage skills give in ~1.0k tokens

Counted across 839 of the 1,149 authors here whose files we hold, read 2026-08-07

  • Investigate root cause before proposing any fixin 102 of 839, across 67 files
  • Read error messages completelyin 89 of 839, across 49 files
  • Create a failing test case before fixingin 84 of 839, across 46 files
  • Reproduce the issue consistentlyin 82 of 839, across 41 files
  • Change one variable at a timein 82 of 839, across 42 files
  • Check recent changesin 74 of 839, across 36 files
  • Write the regression test before fixingin 74 of 839, across 40 files
  • Fix the root cause not the symptomin 60 of 839, across 45 files
  • Implement a single fix at a timein 59 of 839, across 20 files
  • Trace data flow backward to the sourcein 50 of 839, across 20 files
  • Remove all debug instrumentationin 49 of 839, across 13 files
  • Form a single hypothesisin 48 of 839, across 18 files

Said here and by no other author read

  • Identify issue scope before requesting details
  • Avoid unnecessary version interrogation
  • Proceed directly to resolution for low-risk issues
  • Avoid speculative or unfounded claims
  • Label risk levels for corrective actions
  • Explain impacts of high-risk actions

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,861. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.