code-flow-tracer
Trace code execution paths and data flow. Use when user asks "how does X work", "what happens when X", "trace the flow of X", "where does data come from", or needs to understand feature implementation.
langsmith-fetch
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.
Debugging
Read [[principles/fix-root-causes]] before starting. Every debugging session follows that principle: trace to root cause, never paper over symptoms.
phoenix-cli
Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, review experiments, inspect datasets, and query the GraphQL API. Use when debugging AI/LLM applications, analyzing trace data, working with Phoenix observability, or investigating LLM performance issues.
Android Reverse Engineering
Decompile Android APK, XAPK, JAR, and AAR files using jadx and Fernflower/Vineflower, trace call flows through application code and libraries, produce structured documentation of extracted APIs, and escalate to runtime analysis only after static triage shows that it is needed. Two decompiler engines
agent-skills
Datadog skills for AI agents. Essential monitoring, logging, tracing and observability.
bug-investigator
Executes diagnostic investigation tasks to test debugging hypotheses. Runs tests, traces execution, checks git history, and reports evidence. (converted from agent)
Io.Github.GreptimeTeam/Greptimedb Mcp Server
Query and analyze GreptimeDB metrics, logs and traces via SQL, TQL and RANGE queries.
agent-monitoring
Investigation and monitor creation guide for AI agent observability. Activates when the user asks about monitoring AI agents, setting up alerts on agent behavior, investigating agent traces, or creating agent monitors.
monitoring-feature-observability
Add or adjust monitoring for a Hypeman feature using repository standards for logs, traces, and metrics. Use when a user asks for instrumentation, observability reviews, telemetry consistency changes, metric design, or production-signal improvements.
Io.Github.Alanzha2/Observe Instrument Mcp
Add OpenTelemetry tracing to Python AI agents. Supports LangGraph, LlamaIndex, CrewAI, OpenAI SDK.
stove-e2e-setup
Use when adding Stove e2e tests to a project, creating a test-e2e source set, configuring Stove systems (HTTP, PostgreSQL, Kafka, WireMock, gRPC), setting up the stove {} test DSL, enabling OpenTelemetry tracing for tests, writing AbstractProjectConfig, or extending Stove with custom systems.
deepagents-planning-todos
Use the write_todos tool effectively for task planning and decomposition in Deep Agents. Use when users want to (1) implement task planning with write_todos, (2) break down complex tasks into subtasks, (3) track agent progress through todos, (4) debug why todos aren't completing, (5) design todo structures for different task types (research, coding, analysis), (6) understand todo status lifecycle and best practices, or (7) visualize todo progression from LangSmith traces.
magpie
Performs GPU kernel correctness and performance evaluation and LLM inference benchmarking with Magpie. Analyzes single or multiple kernels (HIP/CUDA/PyTorch), compares kernel implementations, runs vLLM/SGLang benchmarks with profiling and TraceLens, and runs gap analysis on torch traces. Creates kernel config YAMLs, discovers kernels in a project, and queries GPU specs. Use when the user mentions Magpie, kernel analyze or compare, HIP/CUDA kernel evaluation, vLLM/SGLang benchmark, gap analysis, TraceLens, creating kernel configs, or discovering GPU kernels.
Mcp Observability Server
MCP server for querying logs from observability platforms with unified search and tracing
Io.Github.TANTIOPE/Datadog Mcp
Full Datadog API access: monitors, logs, metrics, traces, dashboards, and observability tools
exploring-llm-traces
ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace URL (e.g. /llm-observability/traces/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs.
Io.Github.MasonChow/Source Map Parser Mcp
Parse JavaScript error stack traces back to original source code using source maps
ALM X++ MCP Server
50 AI tools for D365 F&O: X++ search, ADO integration, code gen, security tracing & upgrade impact.
ACE â Learn from Traces
This skill ships `learn_from_traces.py`, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk.
coderlm
Primary tool for all code navigation and reading in supported languages (Rust, Python, TypeScript, JavaScript, Go, Java, Scala, SQL). Use instead of Read, Grep, and Glob for finding symbols, reading function implementations, tracing callers, discovering tests, and understanding execution paths. Provides tree-sitter-backed indexing that returns exact source code â full function bodies, call sites with line numbers, test locations â without loading entire files into context. Use for: finding functions by name or pattern, reading specific implementations, answering 'what calls X', 'where does this error come from', 'how does X work', tracing from entrypoint to outcome, and any codebase exploration. Use Read only for config files, markdown, and unsupported languages.
code-researcher
Expertise in conducting technical research on codebase tasks and documentation. Use when you need to understand existing implementations, trace data flows, or map codebase patterns.
rdc-cli
Use this skill when working with RenderDoc capture files (.rdc), analyzing GPU frames, tracing shaders, inspecting draw calls, or running CI assertions against GPU captures. Trigger phrases: "open capture", "rdc file", ".rdc", "renderdoc", "shader debug", "pixel trace", "draw calls", "GPU frame", "assert pixel", "export render target".
Ucn
Code intelligence for AI agents. Extract, trace, and analyze code without reading whole files.
crash-debugging
Crash log analysis, symbolication, and debugging workflows for iOS apps. Use when investigating app crashes, analyzing crash reports, symbolicating stack traces, or identifying root causes. Covers crash log retrieval, symbolication with dSYM files, stack trace analysis, and common crash patterns.
jetbrains-debugger
Guide for using JetBrains IDE Debugger MCP tools to programmatically debug applications. TRIGGER when ANY of these MCP tools are available: list_run_configurations, execute_run_configuration, start_debug_session, stop_debug_session, get_debug_session_status, list_debug_sessions, set_breakpoint, remove_breakpoint, list_breakpoints, resume_execution, pause_execution, step_over, step_into, step_out, run_to_line, get_stack_trace, select_stack_frame, list_threads, get_variables, set_variable, get_source_context, evaluate_expression. Use when debugging any application, investigating bugs, tracing execution flow, inspecting runtime state, or when the user says "debug", "breakpoint", "step through", "inspect variable", "why is this returning X", "trace execution", or similar debugging-related requests. PREFER the debugger over reading code and guessing when runtime behavior is unclear.
codebase-search
Search and navigate large codebases efficiently. Use when finding specific code patterns, tracing function calls, understanding code structure, or locating bugs. Handles semantic search, grep patterns, AST analysis.
trace-mcp
Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate whenever the agent needs to explore, understand, or modify a codebase that has trace-mcp indexed.
SpecLeft
Python intent tracing MCP: map specs to pytest tests, monitor implementation progress, offline-only.
diagnose
Analyze error logs from QEMU output, serial monitor, CI pipelines, or build failures. This skill should automatically activate when the user pastes terminal output containing error messages, stack traces, build failures, boot logs, or CI job output.
call-chain
Trace execution paths from entry points through the code knowledge graph. Shows call chains with criticality scores and generates Mermaid flowcharts.
ctf-forensics
Provides digital forensics and signal analysis techniques for CTF challenges. Use when analyzing disk images, memory dumps, event logs, network captures, cryptocurrency transactions, steganography, PDF analysis, Windows registry, Volatility, PCAP, Docker images, coredumps, side-channel power traces, DTMF audio spectrograms, packet timing analysis, CD audio disc images, or recovering deleted files and credentials.
build-review-interface
Build a custom browser-based annotation interface tailored to your data for reviewing LLM traces and collecting structured feedback. Use when you need to build an annotation tool, review traces, or collect human labels.
capture
Capture HTTP traffic from web apps using playwright-cli. Includes site fingerprinting (framework detection, protection checks, iframe detection, auth detection, API discovery) and full traffic recording with tracing and optional HAR output. TRIGGER when: "record traffic from", "capture API calls from", "start Phase 1 for", "analyze traffic from URL", "assess site", "site fingerprint", "start capture for", "open browser for", or any URL is given as the first step of CLI generation. DO NOT trigger for: Phase 2 implementation, test writing, or quality validation.
control-flow
Analyze and design control flows and data structures. Produces compact ASCII tree diagrams showing triggers, call chains, payload shapes, state mutations, and re-render effects. Use when user asks to diagram, trace, visualize, or design a flow or data structure.
Decompile Android APK, XAPK, AAB, DEX, JAR, and AAR files using jadx
Decompile Android APK, XAPK, AAB, DEX, JAR, and AAR files using jadx or Fernflower/Vineflower. Reverse engineer Android apps, extract HTTP API endpoints (Retrofit, OkHttp, Volley, GraphQL, WebSocket), trace call flows from UI to network layer, analyze security patterns (cert pinning, exposed secrets), and perform dynamic analysis with Frida (adaptive bypass generation, crash analysis, runtime hooking). Use when the user wants to decompile, analyze, or reverse engineer Android packages, find API endpoints, follow call flows, audit app security, or bypass runtime protections.
Analyzing systing traces
Systing stores traces in **DuckDB**. The `systing-analyze` MCP server exposes structured tools to query them. This skill tells you which tool to reach for and how the data is laid out.
dbg
Debug applications using the dbg CLI debugger. Supports Node.js (V8/CDP), Bun (WebKit/JSC), and native code via LLDB (DAP). Use when: (1) investigating runtime bugs by stepping through code, (2) inspecting variable values at specific execution points, (3) setting breakpoints and conditional breakpoints, (4) evaluating expressions in a paused context, (5) hot-patching code without restarting (JS/TS), (6) debugging test failures by attaching to a running process, (7) debugging C/C++/Rust/Swift with LLDB, (8) any task where understanding runtime behavior requires a debugger. Triggers: "debug this", "set a breakpoint", "step through", "inspect variables", "why is this value wrong", "trace execution", "attach debugger", "runtime error", "segfault", "core dump".
droidrun-docs
DroidRun documentation reference. Use when users ask about DroidRun setup, configuration, SDK usage, CLI commands, device setup, agents, architecture, app cards, credentials, tracing, Docker, migration, structured output, or any DroidRun "how do I..." questions.
claudette-debug
Debug the running Claudette Tauri app by executing JavaScript in the webview and reading results back. Inspect Zustand store state, trace state changes, monitor sessions long-term, run end-to-end UAT, and diagnose UI bugs in real-time. Only works in dev builds.
add-reference-tests
Add pytest tests to validate reference implementations in flashinfer_trace against FlashInfer or SGLang ground truth. Use when validating kernel definitions, adding tests for new op_types, or verifying reference implementations are correct.
debug-isolate
This skill should be used during Phase 2 (ISOLATE) of a debug session when the bug has been reproduced and needs to be narrowed down to a specific location. Provides isolation techniques including binary search, stack trace analysis, and diagnostic logging.
Mcp Agent Trace Inspector
Step-by-step observability for MCP agent workflows
citation-check-skill
Vision-enabled verification gate with web search. Use when users want to (1) verify slides/reports/PDFs/images against authoritative online sources, (2) validate that citations actually exist and say what's claimed, (3) check charts/graphs/tables for accuracy, (4) audit AI-generated content in doc-only mode (no external knowledge). Two modes - search mode validates against web, doc-only mode ensures everything traces to provided documents. Supports content in any language.
Scrapercity Cli
B2B lead generation MCP server - 20+ scrapers, email finder, skip trace, and more.
benchmarking-cairo
Use when profiling Cairo functions, measuring step counts, analyzing resource usage, generating call-graph PNGs, or launching pprof to visualize Cairo execution traces
Co.Okahu.Mcp Registry/Okahu
Cloud hosted Okahu MCP server that helps you manage genAI trace data
tma1
Query TMA1 observability data. Use when the user asks: how much did I spend, token usage, what has my agent been doing, agent cost, show me traces, show me events, check for errors, model comparison, tool usage.
cast-subagents
Use when suggesting exactly one Codex subagent lineup before work begins for multi-lane tasks: branch/PR review across bugs, security, tests, maintainability, docs, or regression risk; codepath tracing plus docs/API verification; option research with tradeoff synthesis; auth/codebase mapping before risk assessment or planning. Advisory only; no auto-spawn; approval required. Do not use for delegated subagent handoffs, trivial single-file fixes, wording-only edits, one fact lookup, unclear requests, or explicit opt-out.
Io.Github.Base76 Research Lab/Cognos Session Memory
CognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.