10,102 tagged Debugging, measured the same way as everything else here.
Browse within: LLM 148cli 96agent 95agents 83skills 79javascript 74agentic-ai 72claude-code-plugin 50mcp-server 43ai-coding 42kubernetes 40ab-testing 39agentic 38ai-skills 38
Skill Claude Code
Disciplined six-phase debugging loop (build feedback loop → reproduce → hypothesise → instrument → fix + regression test → cleanup) for hard bugs and performance regressions. Output is a written root-cause report at .devkit/diagnose.md that /bugfix can consume to drive the actual fix. Use when the user says "diagnose…
Skill Codex
Diagnose why a Tdarr transcode job failed from its job report. Use when the user asks why a particular Tdarr job or transcode failed, supplies a Tdarr JobId, or wants to inspect current failed transcodes and choose one to investigate.
lidisching-hue/mcp-packet-tracer
Skill Claude CodeCodex
Use when building, automating, or debugging Cisco Packet Tracer networks through the packet-tracer MCP (the pt tools) — planning topologies from natural language, live-deploying into a running Packet Tracer, adding devices / links / modules, applying ACL / NAT, exporting configs, or writing raw Script-Engine JS via…
Skill Claude CodeCodex
Use when debugging a running application whose behavior you can reproduce — instrument the app with logsafe structured logging, reproduce the bug, and read the session narrow-first (errors → trace → widen). Works via logsafe MCP tools when connected, or plain HTTP/curl.
Skill Claude CodeCodex
When the user says “fix this”, “what is wrong”, or “debug this”, use visible terminal/editor context to create a structured debugging command for Codra / Codex / OpenCode.
Skill Claude CodeCodex
Use when the user reports a 3D model or scene looking wrong (black/invisible/gigantic/untextured model, holes, weird shading), asks to check or QA a 3D file (GLB, GLTF, OBJ, PLY, STL, .splat), works with Gaussian splats, or generates 3D assets with AI and wants them verified. Requires the 3d-eyes MCP server.
Skill Claude CodeCodex
Diagnose runtime bugs by connecting source-code log statements to Graylog events. Use when a user reports missing results, failed callbacks, stuck async jobs, inconsistent data, or asks to trace a code path through logs. Also use when code inspection reveals relevant log.info, log.warn, log.error, logger, tracing, or…
Skill Claude CodeCodex
Diagnose MMDB (MariaDB) incidents from activelog / busy-ratio patterns; maps metric signatures to likely causes and remediations.
Skill Claude CodeCodex
Query the codebase connection graph (HTTP calls, DB/queue access, imports) across app-web + app-services. Use when asked who calls a route, what touches a table/stream, how two parts of the code connect, or to (re)build the graph.
Skill Claude CodeCodex
Rules for editing JavaScript inside Python triple-quoted HTML in mercarigui.py (HTMLPAGE). Prevents silent JS parse errors that break tabs, buttons, and onclick handlers. Use when changing mercarigui.py UI, bulk streaming, CSV download, tabs, or any embedded in this repo.
Skill Claude CodeCodex
Use when the python-mcp MCP server is available for compact, read-only Python quality checks including linting, formatting, type checking, security, dependencies, test collection, dead-code, and spelling analysis.
scalemaker-ship-it/mcp-chrome-scalemaker
Skill Claude CodeCodex
A troubleshooting guide for the chrome-mcp-scalemaker MCP server, its browser extension, bridge process, and connection settings. MCP is a way for an agent to call tools provided by another program.
Skill Claude CodeCodex
Use when the biome-mcp MCP server is available to run biomecheck, biomelint, or biomeformat on TypeScript and web projects. Prefer its compact read-only diagnostics for linting and format verification.
Skill Claude CodeCodex
Triage a broken or degraded data asset in DataHub. Traces the downstream blast radius across all lineage hops, resolves owners, ranks by criticality, writes a structured incident report, and records the incident back into the catalog (tag + runbook document + native incident). Use when a table, view, dashboard, or…
Skill Claude CodeCodex
Investigates migrated Papertrail logs through the read-only SolarWinds Observability logs API. Use for production log searches, incident triage, request tracing, and log correlation.
Skill Claude CodeCodex
Investigates Rollbar items and occurrences through the read-only Rollbar MCP server. Use for production errors, exception triage, stack traces, occurrences, and Rollbar item links or numbers.
Skill Claude CodeCodex
Analyze images, screenshots, diagrams, and videos you cannot see natively. Use for image questions, OCR, UI inspection, visual debugging, screen recordings, video summaries, and timeline analysis on text-only agents.
huanglixinccc/aliyun-log-search
Skill Claude CodeCodex
Use when investigating application failures, task IDs, error codes, or event timelines in the configured Aliyun SLS logs.
Skill Claude CodeCodex needs its repo
Deterministic visual toolbox via EagleEye MCP (not a CLI). Use when the task needs a live screenshot, window capture, waiting for UI to appear, pixel/color/template measurement, OCR, UI checks, or visual regression. Do not use to turn a conversation image into a one-shot description (that is modlens), or to rebuild…
Skill Claude Code
Use the code-graph MCP tools (or the codegraph CLI) instead of grepping when the question is structural.
Skill Claude CodeCodex
A troubleshooting skill for the chrome-mcp-scalemaker server, its browser extension, bridge, and tool calls. It checks the installed fork and investigates problems across the connected components.
quzhiii/ai-disk-doctor-integrations
Skill Claude CodeCodex
Diagnose AI and developer workspace storage with AI Disk Doctor's local Core. Use when asking why a disk is full, which AI tools or model caches consume space, what changed recently, what Core evidence supports a classification, or what should be reviewed safely.
Skill Claude CodeCodex
Use when investigating an FRC robot issue with the nt-mcp-server NetworkTables MCP server.
Skill Claude CodeCodex
Query evidence-backed historical bugs before risky code changes and verify patches before completion.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: