debug
installsforks
How to install debug?
anthropics/knowledge-work-plugins/debug
$npx -y skills add anthropics/knowledge-work-plugins --skill debugdebug is an agent skill published from anthropics/knowledge-work-plugins, installable through the skills CLI.
SKILL.md
| 1 | # /debug |
| 2 | |
| 3 | > If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md). |
| 4 | |
| 5 | Run a structured debugging session to find and fix issues systematically. |
| 6 | |
| 7 | ## Usage |
| 8 | |
| 9 | ``` |
| 10 | /debug $ARGUMENTS |
| 11 | ``` |
| 12 | |
| 13 | ## How It Works |
| 14 | |
| 15 | ``` |
| 16 | ┌─────────────────────────────────────────────────────────────────┐ |
| 17 | │ DEBUG │ |
| 18 | ├─────────────────────────────────────────────────────────────────┤ |
| 19 | │ Step 1: REPRODUCE │ |
| 20 | │ ✓ Understand the expected vs. actual behavior │ |
| 21 | │ ✓ Identify exact reproduction steps │ |
| 22 | │ ✓ Determine scope (when did it start? who is affected?) │ |
| 23 | │ │ |
| 24 | │ Step 2: ISOLATE │ |
| 25 | │ ✓ Narrow down the component, service, or code path │ |
| 26 | │ ✓ Check recent changes (deploys, config changes, dependencies) │ |
| 27 | │ ✓ Review logs and error messages │ |
| 28 | │ │ |
| 29 | │ Step 3: DIAGNOSE │ |
| 30 | │ ✓ Form hypotheses and test them │ |
| 31 | │ ✓ Trace the code path │ |
| 32 | │ ✓ Identify root cause (not just symptoms) │ |
| 33 | │ │ |
| 34 | │ Step 4: FIX │ |
| 35 | │ ✓ Propose a fix with explanation │ |
| 36 | │ ✓ Consider side effects and edge cases │ |
| 37 | │ ✓ Suggest tests to prevent regression │ |
| 38 | └─────────────────────────────────────────────────────────────────┘ |
| 39 | ``` |
| 40 | |
| 41 | ## What I Need From You |
| 42 | |
| 43 | Tell me about the problem. Any of these help: |
| 44 | - Error message or stack trace |
| 45 | - Steps to reproduce |
| 46 | - What changed recently |
| 47 | - Logs or screenshots |
| 48 | - Expected vs. actual behavior |
| 49 | |
| 50 | ## Output |
| 51 | |
| 52 | ```markdown |
| 53 | ## Debug Report: [Issue Summary] |
| 54 | |
| 55 | ### Reproduction |
| 56 | - **Expected**: [What should happen] |
| 57 | - **Actual**: [What happens instead] |
| 58 | - **Steps**: [How to reproduce] |
| 59 | |
| 60 | ### Root Cause |
| 61 | [Explanation of why the bug occurs] |
| 62 | |
| 63 | ### Fix |
| 64 | [Code changes or configuration fixes needed] |
| 65 | |
| 66 | ### Prevention |
| 67 | - [Test to add] |
| 68 | - [Guard to put in place] |
| 69 | ``` |
| 70 | |
| 71 | ## If Connectors Available |
| 72 | |
| 73 | If **~~monitoring** is connected: |
| 74 | - Pull logs, error rates, and metrics around the time of the issue |
| 75 | - Show recent deploys and config changes that may correlate |
| 76 | |
| 77 | If **~~source control** is connected: |
| 78 | - Identify recent commits and PRs that touched affected code paths |
| 79 | - Check if the issue correlates with a specific change |
| 80 | |
| 81 | If **~~project tracker** is connected: |
| 82 | - Search for related bug reports or known issues |
| 83 | - Create a ticket for the fix once identified |
| 84 | |
| 85 | ## Tips |
| 86 | |
| 87 | 1. **Share error messages exactly** — Don't paraphrase. The exact text matters. |
| 88 | 2. **Mention what changed** — Recent deploys, dependency updates, and config changes are top suspects. |
| 89 | 3. **Include context** — "This works in staging but not prod" or "Only affects large payloads" narrows things fast. |
People who liked this also viewed
6 picksType
- azure-diagnosticsDebug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deploySkillsJul 2026
- systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesSkillsJul 2026
- safe-debugRigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training SkillsMay 2026
- explore-runRigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subseSkillsMay 2026
- minimal-run-and-auditRigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation SkillsMay 2026
- insforge-debugUse when diagnosing problems in an InsForge project — reactive failures (SDK error object, HTTP 4xx/5xx, gateway timeout 502/503/504, edge function failure or timeout, login/OAuth/auth errors, RLS denSkillsJul 2026
