Debugging Toolkit Bundle

Browse all skill bundles

Included Skills (24)

1. Tilegym Converting Cutile To Triton — Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers dual-kernel layout flags (e.g. transpose=True/False + autotune grid via META) per translations/advanced-patterns.md. Use when converting, porting, or translating cuTile kernels to Triton, or debugging existing Triton translations.
2. Warp Debug Gradients — Use to diagnose and fix incorrect gradients in differentiable Warp programs. Anything trained, optimized, calibrated, or fit through Warp kernels depends on wp.Tape gradients, so treat any misbehavior of such a workflow as a gradient problem until proven otherwise — use this when training diverges or NaNs, won't train at all, stalls or plateaus above the expected loss, converges to a wrong or biased answer, is worse than a reference implementation, works at small scale but fails at production scale, or fails a QA/validation recheck. Also for explicit symptoms — exploding, NaN/inf, zero, or subtly wrong gradients, suspected wp.Tape/backward issues, gradcheck failures — but users usually describe only the surface symptom ("the sim explodes", "the fit gets dragged toward outliers") without mentioning gradients: make that leap. Not for forward-only Warp work, build/install problems, or autograd issues in other frameworks without Warp.
3. Doca Dpa Hl Tracer — Use this skill when the user runs doca_dpa_hl_tracer to capture/decode DPA-side traces at the programming-events layer (kernel entry/exit, sync points, comm primitive calls, RDMA WR submission, completion drain) — picking TRACE vs CRIT, tuning the JSON config (file-size limits + file_size_limit_policy, thread priorities/cores), decoding against the matching DPA-side ELF, or diagnosing empty/noisy captures. Trigger even when the user does not explicitly mention "DOCA DPA tracer" or "high-level tracer" — typical implicit phrasings include "DPA kernel returns wrong result but host completions look clean", "kernel-entry to first-comm latency is huge", "RDMA WR to drain gap on the DPA", "trace file truncated mid-run", "TRACE doubled my DPA latency", or "tracer wrote a file but parser shows zero events". Refuse and route elsewhere for writing DPA kernels, DPA-Comms/DPA-Verbs programming, raw per-cycle DPA profiling, host-side doca-dpa debugging, or production DPA telemetry — those belong to other skills.
4. Doca Bench Extension — Use this skill when the operator is authoring, building, loading, or debugging a custom doca-bench plug-in — a versioned shared library with DOCA_EXPERIMENTAL-marked C entry points that doca-bench loads to measure a workload class its built-in modes do not cover, with doca_bench_cuda as the shipped reference exemplar. Trigger even when the user does not say "doca-bench-extension" or "doca_bench_cuda" — typical implicit phrasings include "no built-in doca-bench mode fits my workload", "how do I benchmark a CUDA GPUNetIO RX/TX kernel", "doca-bench cannot find or load my custom .so", "extension exported symbols do not match what the parent expects", "soversion mismatch after a DOCA upgrade", or "my GPU kernel hangs because stop_flag was never set". Refuse and route elsewhere for questions about which built-in doca-bench mode to pick, DOCA GPUNetIO programming semantics, CUDA toolkit installation, or contributor work on in-tree extensions — those belong to other skills.
5. Understand Explain — Explains one file, function, class, table or folder of a codebase in depth, starting from the knowledge graph built by the Understand-Anything plugin and confirming every statement in the source. Use when someone says "explain this file", "how does this function work", "walk me through the scheduler module", "what is this class for and who uses it", "run /understand-explain src/services/scheduler.ts", "I inherited this code, what does it do", or needs a written deep dive on a specific part of a project.
6. AI Governance Engine — This engine provides safety gates, evidence-based debugging, and ripple awareness to help AI agents deliver verified, disciplined, and reliable code modifications for developers.
7. API Integration Architect — Designs, implements, and debugs robust API integrations for developers and engineers.
8. Makepad Animation — Helps developers write and debug code for the Makepad animation system.
9. Google Agents CLI Onboarding — Onboarding entrypoint for agents-cli in Agent Platform. It should be used when the user wants to "create a new agent", "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "evaluate an agent", "deploy an agent", "publish an agent", "monitor an agent", or needs the ADK (Agent Development Kit) development lifecycle.
10. Debugging And Error Recovery — Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.
11. Gdb CLI — GDB debugging assistant for AI agents - analyze core dumps, debug live processes, investigate crashes and deadlocks with source code correlation
12. Durable Objects — Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
13. N8n Workflow Orchestrator — This router streamlines n8n MCP workflow development, testing, and debugging by directing tasks to specialized guidance for developers and automation engineers.
14. Orca Replay — Answer questions about an earlier agent run from its recording rather than from memory, and replay or fork that run. Use when the user asks why a previous run did something, which step changed a file or broke the build, whether yesterday's failure still reproduces, or whether a different model would have got it right.
15. Systematic Debugging Framework — This four-phase methodology helps developers identify root causes before applying fixes, ensuring reliable resolutions for bugs and complex test failures.
16. Memory Status — Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations. Use when the user runs /si:memory-status or asks how full or healthy the agent memory is.
17. Systematic Debugging — Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
18. Playwright Test Fixer — This skill diagnoses and fixes failing or flaky Playwright tests, helping developers ensure reliable end-to-end testing.
19. Code Execution Tracer — This tool generates detailed, step-by-step execution traces to help developers understand complex code behavior and resolve logic-based confusion during debugging.
20. Structured Debugging Protocol — Enforces a rigorous five-phase debugging workflow that prevents premature code edits, helping developers and AI agents identify root causes before applying fixes.
21. Root Cause Debugger — Debugging specialist for developers to analyze and fix errors, test failures, and unexpected behavior.
22. Diagnosing Superpowers — Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
23. JavaScript Concept Guide — This skill provides developers with comprehensive explanations and best practices for thirty-three essential JavaScript concepts to improve coding proficiency and debugging.
24. Rust Async Architect — This skill assists developers in building, optimizing, and debugging robust concurrent systems using the Tokio runtime and advanced asynchronous Rust programming patterns.