Debug
- 4.5k installs
- 23.1k repo stars
- Updated July 28, 2026
- anthropics/knowledge-work-plugins
A structured Debug Report mapping issue reproduction, root cause identification, proposed fix, and regression prevention steps.
About
Debug is a structured troubleshooting workflow for engineers facing production issues, staging-to-prod discrepancies, post-deploy failures, or behavior divergence with unclear root causes. It guides users through four phases: reproduce (map expected vs. actual behavior and scope), isolate (narrow to affected component and recent changes), diagnose (form and test hypotheses, trace code paths), and fix (propose solutions with side-effect analysis and regression tests). When monitoring, source control, or project tracking tools are connected, the skill pulls correlated logs, deploys, config changes, and related tickets to accelerate diagnosis and ticket creation. Four-phase structured workflow: reproduce, isolate, diagnose, fix Integrates with monitoring, source control, and project tracker connectors for log pulls and change correlation Generates Debug Reports with expected vs. actual behavior, root cause analysis, and prevention steps Accepts error messages, stack traces, reproduction steps, logs, or behavioral descriptions as input Emphasizes exact error text, recent changes, and contextual constraints to narrow scope fast Structured error reproduction and scope mapping Root cause.
- Four-phase structured workflow: reproduce, isolate, diagnose, fix
- Integrates with monitoring, source control, and project tracker connectors for log pulls and change correlation
- Generates Debug Reports with expected vs. actual behavior, root cause analysis, and prevention steps
- Accepts error messages, stack traces, reproduction steps, logs, or behavioral descriptions as input
- Emphasizes exact error text, recent changes, and contextual constraints to narrow scope fast
Debug by the numbers
- 4,545 all-time installs (skills.sh)
- +219 installs in the week ending Jul 28, 2026 (Skillselion tracking)
- Ranked #18 of 610 Debugging skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
debug capabilities & compatibility
- Capabilities
- structured error reproduction and scope mapping · root cause diagnosis via code path tracing and h · integration with monitoring logs and recent depl · fix proposal with side effect and regression ana · ticket creation for tracked issues
- Use cases
- debugging · code review · testing
- Runs
- Hosted SaaS
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill debugAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 4.5k |
|---|---|
| repo stars | ★ 23.1k |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 28, 2026 |
| Repository | anthropics/knowledge-work-plugins ↗ |
What it does
Systematically reproduce, isolate, diagnose, and fix runtime errors and behavioral divergences in deployed systems.
Who is it for?
Runtime errors, behavioral divergences, post-deploy failures, staging-to-prod mismatches, log-based triage.
Skip if: Design review, architecture decisions, performance optimization without bug context.
When should I use this skill?
Error message, stack trace, 'works in staging not prod', post-deploy failure, or unexpected behavior with unclear cause.
What you get
Engineer identifies root cause, applies targeted fix, and prevents regression through guided four-phase diagnosis and proposed test cases.
- Repro steps
- root cause analysis
- verified fix
By the numbers
- Four-phase workflow: reproduce, isolate, diagnose, fix
- Supports three optional connector integrations: monitoring, source control, project tracker
Files
/debug
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Run a structured debugging session to find and fix issues systematically.
Usage
/debug $ARGUMENTSHow It Works
┌─────────────────────────────────────────────────────────────────┐
│ DEBUG │
├─────────────────────────────────────────────────────────────────┤
│ Step 1: REPRODUCE │
│ ✓ Understand the expected vs. actual behavior │
│ ✓ Identify exact reproduction steps │
│ ✓ Determine scope (when did it start? who is affected?) │
│ │
│ Step 2: ISOLATE │
│ ✓ Narrow down the component, service, or code path │
│ ✓ Check recent changes (deploys, config changes, dependencies) │
│ ✓ Review logs and error messages │
│ │
│ Step 3: DIAGNOSE │
│ ✓ Form hypotheses and test them │
│ ✓ Trace the code path │
│ ✓ Identify root cause (not just symptoms) │
│ │
│ Step 4: FIX │
│ ✓ Propose a fix with explanation │
│ ✓ Consider side effects and edge cases │
│ ✓ Suggest tests to prevent regression │
└─────────────────────────────────────────────────────────────────┘What I Need From You
Tell me about the problem. Any of these help:
- Error message or stack trace
- Steps to reproduce
- What changed recently
- Logs or screenshots
- Expected vs. actual behavior
Output
## Debug Report: [Issue Summary]
### Reproduction
- **Expected**: [What should happen]
- **Actual**: [What happens instead]
- **Steps**: [How to reproduce]
### Root Cause
[Explanation of why the bug occurs]
### Fix
[Code changes or configuration fixes needed]
### Prevention
- [Test to add]
- [Guard to put in place]If Connectors Available
If ~~monitoring is connected:
- Pull logs, error rates, and metrics around the time of the issue
- Show recent deploys and config changes that may correlate
If ~~source control is connected:
- Identify recent commits and PRs that touched affected code paths
- Check if the issue correlates with a specific change
If ~~project tracker is connected:
- Search for related bug reports or known issues
- Create a ticket for the fix once identified
Tips
1. Share error messages exactly — Don't paraphrase. The exact text matters. 2. Mention what changed — Recent deploys, dependency updates, and config changes are top suspects. 3. Include context — "This works in staging but not prod" or "Only affects large payloads" narrows things fast.
Related skills
Azure DiagnosticsSystematically diagnose and resolve production issues on Microsoft Azure using official Microsoft guidance.472k1.3kAzure MessagingQuickly diagnose and fix connection, authentication, and message-processing failures when using Azure Event Hubs or Service Bus SDKs.460k1.3k
Use My BrowserWhen their agent task requires access to the live browser session, rendered DOM state, authenticated dashboards, localhost apps, or DevTools-selected elements instea269k72
Diagnosing BugsGet a systematic, step-by-step process that surfaces the real root cause instead of guessing at bugs.222k183k
Systematic DebuggingFollow a repeatable four-phase process that forces root-cause discovery before any code changes.197k260k
Safe DebugGet conservative, non-destructive diagnosis of deep learning and agent errors before any code changes are made.161k507FAQ
What information helps fastest diagnosis?
Exact error text, reproduction steps, recent changes (deploys/dependencies), logs, expected vs. actual behavior, and scope (who/when affected).
What are the four debug phases?
Reproduce (map expected/actual, identify scope), Isolate (narrow component, check recent changes), Diagnose (form/test hypotheses, trace code), Fix (propose solution, prevent regression).
How does this integrate with tools?
When monitoring, source control, or project tracker connectors are active, debug pulls correlated logs, deploys, config changes, and related tickets.
Is Debug safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.