Loading...
Loading...
Found 10 Skills
Use when a developer wants to iterate on ONE specific Agent Observability / LLM Obs trace whose output they didn't like — re-running that trace against their LOCAL code, seeing a concise diff of the old vs new output, and looping (change code → replay → diff) until satisfied. Invoked as /agent-observability-replay-trace <trace-id> [changes to test]. Signals: "replay this trace"; "iterate on a trace"; "this trace's output is wrong, fix it and re-run"; "re-run trace <id> with <change>"; pasting a trace id from the Agent Observability UI with a description of what to fix. It fetches the trace via the datadog-llmo MCP or the pup CLI, edits code, re-runs the app to emit a NEW trace, and diffs the two — no local server, no browser. For agents traced with ddtrace / LLM Obs (Python first-class), with JSON-serializable entry input. Do NOT use for: scored Experiments or the browser "Replay" button (that's agent-observability-replay-experiment), building an experiment from a dataset/CSV, writing evaluators, root-causing failed traces, or RUM/HTTP session replay.
Self-report agent issues by logging user corrections for later review, then resume with the correct skill. Use when a user says "don’t do that", "stop doing X", "always do Y", or requests self-correction.
Run an iterative code-improvement hill-climb against real Datadog LLM-Obs data, locally, with Claude Code as the agent. Establishes a baseline eval, makes one focused change, re-scores with the same harness, keeps the change if it improves the score in the goal's direction (labeling within-noise gains tentative), and repeats. Use when the user says "run an auto experiment", "hill-climb this code", "iteratively improve X and measure the delta", "optimize this prompt/file against my traces", "auto-optimize against LLM-Obs", or wants the local equivalent of the auto_experiments worker. Works from a local dataset file, an ml_app, a dataset_id, or a list of trace_ids.
Take your AI agent to the next level with full LangWatch integration. Adds tracing, prompt versioning, evaluation experiments, and simulation tests in one go. Use when the user wants comprehensive observability, testing, and prompt management for their agent.
Install, connect, and verify Phargus diagnostics in a Node.js application. Use when adding Phargus, configuring agent output, or repairing the agent-to-collector-to-dashboard connection.
Install the AgentHog SDK and wire tracing into the project — init at startup, wrap the primary agent loop, add env vars, verify a first trace lands. Use when the user asks to "set up agenthog", "add agenthog tracing", "instrument with agenthog", "add observability", "wire up tracing", or "add tracing to this app".
Add Forge AgentLens tracing to Python or TypeScript agents. Use when asked to trace agent turns, model calls, tools, or subagents with Forge or AgentLens.
Use this skill when the user asks about AI Center Coding Agents data, wants to reproduce or extend the Coding Agents dashboards, or asks questions about usage, cost, tokens, sessions, tools, code impact, users, models, spans, or logs for Claude Code, Codex, Cursor, Gemini CLI, or Copilot CLI.
Keep a one-row-per-decision log during long or unattended runs, and re-read it before each step so the run does not drift from its goal. Use for multi-phase or autonomous work, work a human will review later, or /ds-ledger.
Add Weave tracing to Python or TypeScript agents and LLM applications. Use when asked to instrument model calls, tools, or agent turns with Weave.