debug
Skill6 starsChanged 28 days agoMITView on GitHub
Magento 2 debugging assistant. Use when the user wants to inspect logs, trace plugins or observers for a given event, inspect the DI graph, find slow queries, or get a health snapshot of indexer/queue/cron state. Read-only by default — produces a diagnostic report without modifying code. Mode-driven: logs / trace / di / slow-queries / snapshot / xdebug. Read-only single-session inspection; for severity-ranked, actionable performance findings (N+1, caching) use magento2-tools:perf-audit.
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 166 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Read-only debugging assistant.
- Distinctive: line 67
All plugins on the resolved type
- Very specific: line 68
All argument bindings from <type> entries
- Distinctive: line 120
Check Xdebug config in container
- Distinctive: line 121
Verify port 9003 + IDE-side path mapping
“Common” is measured: kept by at least 6 in 10 of the 166 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Magento 2 Debug
Read-only debugging assistant. Surfaces information that's expensive to gather manually and easy to misread.
Core Rules
- Read-only by default. This skill does not edit source code. If the user wants
remediation, redirect to
fixorperf-audit. - Mode-driven. Each invocation picks one mode based on the user's request.
- Static-first where possible.
traceanddimodes work entirely off the source tree; runtime modes (logs,slow-queries,snapshot) need filesystem/CLI access. - De-dupe noisy output. Log triage groups by error signature; slow-query analysis groups by query pattern. Don't dump raw output into the conversation.
Modes
logs
/debug logs --since=1h --pattern="checkout"Inspects Magento logs. Reads var/log/system.log, var/log/exception.log,
var/log/debug.log, or a custom path. Groups by error signature, surfaces the top 20
distinct entries with first/last seen + count + sample.
See references/log-locations.md and ${CLAUDE_SKILL_DIR}/scripts/log-triage.sh.
trace
/debug trace --event=checkout_submit_all_after
/debug trace --method='Magento\Catalog\Model\Product::save'
/debug trace --class='Magento\Catalog\Api\ProductRepositoryInterface'For an event: lists all observers across enabled modules, sorted by area then module.
For a method: lists all plugins (before / around / after) with sortOrder and disabled.
For a class: shows DI <preference> resolution.
Output: Mermaid sequence diagram of the actual call chain.
See references/event-catalog.md and ${CLAUDE_SKILL_DIR}/scripts/plugin-trace.sh.
di
/debug di --for='Magento\Catalog\Api\ProductRepositoryInterface'Shows DI graph for a type:
- All
<preference>for the interface - All plugins on the resolved type
- All argument bindings from
<type>entries
Useful when wondering "why is Magento using this implementation?"
See references/di-graph-walk.md and ${CLAUDE_SKILL_DIR}/scripts/di-walk.sh.
slow-queries
/debug slow-queries --since=24hReads MySQL slow log (path configurable). Groups queries by signature (replaces literals with placeholders). Top 20 by total time + per-query suggestions:
- Missing index inferred from WHERE columns
- WHERE on non-indexed columns
- Table scan hint
- Repeat-query pattern hint
See references/slow-query-patterns.md and ${CLAUDE_SKILL_DIR}/scripts/slow-query-parse.sh.
snapshot
/debug snapshotOne-shot system snapshot:
- Indexer status + mode
- Cache type status
- Queue consumers + backlog
- Pending cron jobs
- Magento mode (developer/production)
- Maintenance flag
- DB version
- PHP version + extensions
composer outdated
Output: single Markdown snapshot for paste-into-ticket. Produced by
${CLAUDE_SKILL_DIR}/scripts/snapshot.sh (read-only; resolves {magento_cli}/{runner} from
the context cache, every probe best-effort).
See references/snapshot-format.md.
xdebug
/debug xdebug- Check Xdebug config in container
- Verify port 9003 + IDE-side path mapping
- Toggle Xdebug on/off (delegating to Makefile / project script if present)
Includes troubleshooting checklist.
Inputs
/debug <mode> [mode-specific flags]Common flags:
--since=<duration>—1h,24h,7d--module=<Vendor>_<Module>— constrain scope--format=markdown|json— output format--save— write to{output_root}/debug/{mode}-{date}.md--docs-root=<path>— output-root override for--save; see "Output root" below.
Outputs
- Markdown to conversation (always)
- Optional
{output_root}/debug/{mode}-{date}.mdwhen--save
Output root (--docs-root)
This skill accepts --docs-root=<path> (see
context/references/artifact-layout.md). It only affects the opt-in --save
output: when set, write the saved report under <path>/debug/; otherwise default to
{ctx.docs_root}/debug/. feature passes this so a feature run's
reports collect under its folder.
Reference Files
references/log-locations.md— default log paths + variations.references/event-catalog.md— common Magento events.references/slow-query-patterns.md— known patterns + index suggestions.references/di-graph-walk.md— di.xml graph walking technique.references/snapshot-format.md— snapshot section structure.references/xdebug-troubleshooting.md— Xdebug config + common issues.
Scripts
${CLAUDE_SKILL_DIR}/scripts/log-triage.sh— group log entries by signature.${CLAUDE_SKILL_DIR}/scripts/di-walk.sh— di.xml graph walker.${CLAUDE_SKILL_DIR}/scripts/plugin-trace.sh— plugin discovery for a target.${CLAUDE_SKILL_DIR}/scripts/slow-query-parse.sh— MySQL slow-log parser.
Acceptance Criteria
- Each mode runs without writing to source code.
- Failure to read a log file degrades gracefully (reports "log not readable" rather than crashing).
tracemode produces output matchingbin/magento dev:di:infowhere the CLI is available, and is correct from static inspection alone otherwise.
Notes
This skill is read-only. It does not edit any file. If the user wants to act on findings, the skill suggests the appropriate next skill:
- defects →
fix - slow-query patterns →
perf-audit - DI collisions →
security
Related Skills
| Phase | Skill |
| 0 | context |
| (none — output is the deliverable; no code changes) |
Other versions190 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 190
- Yeachan-Heo/oh-my-claudecode★ 40ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 40ksame name
- anthropics/knowledge-work-plugins★ 34ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- openai/symphony★ 27ksame name
- FalkorDB/FalkorDB★ 11ksame name
- NVIDIA/Model-Optimizer★ 5.5ksame name
- NVIDIA/TensorRT-Model-Optimizer★ 5.3ksame name
180 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use add-discord, add-slack and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
MicrosoftSkilladd-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
- +10 more from microsoft
In this repository35 other files it gives its agents.
- a11y-auditSkill
- admin-formSkill
- admin-listingSkill
- auditSkill
- breeze-adaptSkill
- breeze-compatSkill
- breeze-themeSkill
- cli-commandSkill
- contextSkill
- data-migrationSkill
- deploySkill
- docsSkill
- eav-attributeSkill
- extension-pointSkill
- featureSkill
- fixSkill
- frontendSkill
- graphqlSkill
- i18nSkill
- indexerSkill
- lintSkill
- marketplaceSkill
- message-queueSkill
- module-createSkill
- perf-auditSkill
- releaseSkill
- remediateSkill
- reviewSkill
- securitySkill
- system-configSkill
- test-generateSkill
- triageSkill
- upgradeSkill
- webapiSkill
- widgetSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

