11,152 tagged Debugging, measured the same way as everything else here.
Browse within: LLM 143agent 114cli 105skills 105agents 91agentic-ai 81javascript 81cursor 68ai-coding 51claude-code-plugin 50ab-testing 42antigravity 41copilot 39mcp-server 38
Skill Claude CodeCodex
Use when stuck on a long, cryptic, or environment-sensitive error (build failures, CUDA/toolchain mismatches, distributed-training crashes) that you cannot solve from memory. Searches the Hindsight commons for a known fix and reports whether it worked.
InitialXW/devops-agent-networking
Skill Claude CodeCodex
Methodology for investigating network CONNECTIVITY / reachability problems.
Skill Claude CodeCodex
Debug firmware on a real board using hwlog structured serial logs. Use whenever working with ESP32/embedded firmware — flashing, testing on hardware, reading device output, or diagnosing crashes, reboots, or silent boards.
Skill Claude CodeCodex
Investigate authorized binaries and runtime behavior with HexWitness's durable evidence MCP and optional Binary Ninja or IDA live tools. Use for function or class discovery, UUID and field mapping, protocol reconstruction, capture comparison, contradiction analysis, evidence-gap planning, and promotion of live…
adityaarakeri/senior-agent-skills
Skill Claude CodeCodex
Thoroughly find dead, unused, and unreachable code in a repository and produce a confidence-ranked report. Use this skill whenever the user asks to find dead code, unused variables, unused functions or classes, unreachable code, orphaned files, unused exports, unused dependencies, stale CI files, orphaned config…
Skill Claude CodeCodex
Read-only environment diagnostic for a solo-lane repo: whether the tools the hooks and skills assume are installed, and whether the guardrails and the pre-commit really fire here or are silently skipping, each gap reported with a copy-paste fix.
Skill Claude CodeCodex
Audit CLAUDE.md against .claude/settings.json. Reports which rules are enforced by hooks/permissions and which are prose, plus context cost, import resolution, contradictions, and structure. Use when the user asks to audit, check, lint, or grade their CLAUDE.md, or asks whether their Claude Code rules are enforced.
Skill Claude CodeCodex
Activates a structured, hypothesis-driven debugging loop. Use this skill whenever the user reports a bug, unexpected behavior, or runtime error and wants help diagnosing the root cause - especially for bugs that are hard to reproduce or where the fix isn't obvious. Trigger on phrases like: "debug this", "figure out…
Skill Codex
Use this skill whenever the user needs SonarCloud or SonarQube issue and hotspot triage, measures, gates, profiles, settings, tags, or safe mutations with environment-variable tokens.
Skill Claude Code
Use when writing or running code through the PcmHackMCP runpython tool (or POSTing to the Ghidra plugin's :8765/runpython endpoint) - i.e. executing an arbitrary Jython script server-side inside a live Ghidra session via MCP. Covers the whole-script execution model, print/JSON output discipline, the automatic…
Skill Claude CodeCodex
Debug local Windows dev problems (port conflicts, HTTP 5xx, slow machines, hanging tests, crashes) via WinKit MCP. Use whenever user mentions local app broken, port in use, localhost not responding, machine slow, BSOD/crash, or asks about WinKit/workspace/dev server. Always use for Windows local diagnostics.
Skill Claude CodeCodex
Analyze change impact using Ontoly dependency and dependent traversal. Use when asked what breaks if a symbol, service, route, package, or repository node changes or is removed.
Asana/cursor-marketplace-plugin
Skill Claude CodeCodex
Diagnose and fix Asana MCP connection issues. Run when the user reports Asana tools are not working, the connection is failing, or they are stuck during setup.
Skill Claude Code
Audit code in scope against your architectural rules; report drift (dead code, SoC, monolith, missing-pattern, principle, comment-drift, naming-quality) with propose-confirm per fix; route misses to /capture. Triggers: /review [path | --since | --vault], "review this", "audit the architecture", "check for drift".…
JunMystery/Agent-Guidance-Python
Skill Claude CodeCodex
React and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills). Organizes 70+ rules across 8 priority categories — waterfalls, bundle size, server-side, client fetching, re-render, rendering, JS micro-perf, advanced. Use when…
Skill Claude CodeCodex
A review process for reverse-engineering work, such as unpacking software, rebuilding tools, or downloading required tooling. Reverse engineering means examining compiled software to understand how it works.
Skill Claude Code
Map and analyze a codebase with the project-explorer MCP server - structure scan, import/export dependency graph, filtered regex search, npm dependency audit, and gated rename operations.
Skill Claude CodeCodex
Depurar ou executar rotina AdvPL/TLPP no AppServer pelo MCP tds (tdsdebug, tdsrun). Use para depurar (breakpoint, valor de variável em execução), rodar/testar uma User Function ou relatório no servidor, ou reproduzir erro de execução (error.log).
Skill Claude CodeCodex
Use when creating, repairing, testing, or reviewing OpenGrep YAML rules, porting Semgrep rules, or modeling sources, sinks, sanitizers, and propagators. Apply procedural-first augmentation, claim-specific semantics, test-first fixtures, and false-positive/false-negative regression gates. Includes four complete…
Skill Claude CodeCodex
Record what a just-finished debugging session taught as a numbered card in PATTERNS.md. Use right after a bug is fixed and its root cause is known, or when the user asks to record, document, or register a pattern or incident.
Skill Claude CodeCodex
Map repositories, locate and extract functions/types, trace calls and dependencies, and edit Go/Rust/C#/D/JS/TS/Kotlin/Goose declarations through versioned JSON code objects. Use for code navigation, impact analysis and function/type replacement with the funcfinder toolkit.
Skill Claude CodeCodex
A skill that examines logs from a failed continuous integration pipeline. Continuous integration is an automated service that builds and tests code when changes are submitted.
edwardyap90/counterfactual-engineering-skill
Skill Codex
Use when a code change has multiple plausible implementation paths, high regression risk, uncertain root cause, or unclear tradeoffs. Creates isolated candidate implementations, runs comparable verification across each candidate, compares evidence, and applies the best proven approach while preserving user changes.
sudhasubash1990/Salesforce-Enterprise-skills
Skill Claude CodeCodex
Analyze Salesforce issues, structure them as ADO-ready defects with evidence, severity/priority assessment, root cause hypothesis, and create ADO bugs via MCP/API when integration is available. Never pretend a defect was created without confirmed API success.
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: