Loading...
Loading...
Found 360 Skills
Observability Designer (POWERFUL)
Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP. Use when the user asks about service traces, slow HTTP/database spans, error spans, trace IDs, or span attributes — not LLM analytics traces or product logs. Uses posthog:query-apm-spans, posthog:apm-trace-get, posthog:apm-services-list, posthog:apm-attributes-list, and posthog:apm-attribute-values-list.
High-performance code intelligence MCP server that indexes codebases into knowledge graphs for structural queries, call traces, and architecture analysis
Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", or wants context on a specific location in the codebase.
Drives a disciplined explore → plan → implement → verify loop for changing an AI agent's behavior with confidence — whether fixing a reported failure or introducing a new requirement, business rule, or policy. Grounds the diagnosis in MLflow traces, codifies the desired behavior as a regression test suite (`mlflow.genai.evaluate` assertions in `@mlflow.test` pytest tests), and iterates the agent — not the test — until green, resisting quick system-prompt patches when the real fix is upstream (missing tool, retrieval source, or capability). Use whenever the user wants to fix or change how an agent behaves — e.g. "fix this issue in my agent", "this answer is wrong", "the agent is hallucinating", "improve my agent based on this trace", "make the agent do X instead of Y", "I want the agent to lead with/prioritize/recommend X", "new business rule: the agent should X", "always/never do X", "change the agent's default behavior" — or shares a trace they want addressed.
Decompose the unified docs/specs/ artifact into parallelizable tasks — the ## Decomposition section of the same document whose ## Design & Rationale section holds the DR-N source. Triggers: 'plan implementation', 'create tasks from spec', or /plan. Applies the verification ladder: verification depth matches each task's blast radius — static analysis for low-risk tasks, scoped tests plus a kill-probe for medium, the integration suite on top for high-risk surfaces (judged test-after, not test-first ordering). Auto-chained from /ideate, or run directly to author the whole unified spec at thin/standard depth. Do NOT use for brainstorming, debugging, or code review.
Interactive code execution path tracer that explains how code flows from entry point to output. Uses step-by-step navigation with AskUserQuestion to explore conditional branches and function calls. Use when: - User asks "How does X work in this codebase?" - User wants to understand HTTP request/response flow - User asks about middleware execution order - User wants to trace a function call chain - User asks "What happens when..." questions - User wants to learn how code paths connect Keywords: trace, flow, execution, path, call chain, middleware, request handling, what happens, how does, step through, follow the code
Analyze and optimize Xano workspace performance. Use when the user wants to find slow endpoints, trace execution bottlenecks, deep-dive request stacks, or understand why their Xano API is slow. Also use when the user mentions "performance," "slow endpoint," "bottleneck," "stack trace," or "optimization."
Use when asked to trace existing codepaths or explicitly asked to run the code-explorer subagent.
Investigates completed DEX sandwich-style MEV from public blocks and bundles—front-victim-back ordering on EVM and Solana, Jito bundle traces, swap decoding, victim slippage vs searcher profit estimates, and evidence-style case studies. Use when the user asks for sandwich attack analysis, MEV sandwich post-mortems, high-slippage swap forensics, or searcher clustering—not for building sandwich bots, mempool manipulation for profit, or harassing labeled wallets.
Trace agent execution by collecting spans and building a trace tree for a task
Trace bugs and manual fixes back to kits and prompts; fix at the source so the iteration loop can reproduce the fix autonomously. Six-step revision process plus the single-failure backpropagation protocol. Use when a manual hot-fix has been applied, when convergence stalls, or when the same class of bug keeps reappearing.