Comet

Decide ship or hold for a candidate from the compare skill's numbers, against an explicit release policy — regressions, pass rate, safety-tagged cases, subgroup consistency, latency and cost budgets, flakiness, evidence size, and whether the judge is validated. Reads two experiments on an Opik test suite via the SDK (or the MCP when connected) and returns a verdict with every criterion shown pass/fail. Use for "is this safe to ship", "can I merge this", "go/no-go on this change", "gate this release", "should I roll this out". Not for producing the numbers (use compare), building an evaluation (use evaluate), or deploying anything.

Turn a failing Opik trace (or a described failure) into a repeatable regression check — a test-suite item with the trace's input and one or two binary assertions — so a fix can be verified by the compare skill. Works over the SDK; uses the MCP write tool when connected. Returns the suite, the item, and the assertion. Use for "turn this into a test", "add a regression case for this trace", "make sure this doesn't happen again", "capture this failure", "add this to the test suite". Not for running the suite (use compare), building an evaluation from scratch (use evaluate), or explaining why the trace failed (use explain).

Improve a prompt with the Opik Agent Optimizer — resolve the prompt, a dataset, and a metric, pick the algorithm, run a bounded optimization, check the gain on held-out data, and save the winner as a new prompt version with the optimization run link. Runs via the opik-optimizer package; reads prompts and datasets via the MCP when connected. Use for "optimize this prompt", "improve my system prompt", "make the agent answer better", "tune the prompt against my dataset", "run the prompt optimizer". Not for measuring quality once (use evaluate), before/after on a suite (use compare), or hand-editing a prompt without data.

Take a judge live on production traffic — create an Opik online evaluation rule (LLM-as-judge or Python metric) on a project with sampling, filters, variable mapping, and a cost cap, then confirm new traces are being scored. Works over the SDK's REST client; reads rules and score names via the MCP when connected. Returns the rule, the score name it emits, and how to watch it. Use for "score production traces", "monitor hallucinations in prod", "take this judge live", "set up an online evaluation rule", "alert me when quality drops". Not for offline experiments (use evaluate or compare) or for finding what is already broken (use diagnose).

Add Opik tracing to an existing app and verify a real trace lands. Installs the Opik package, detects the language and LLM framework, adds the minimum tracing, runs a safe representative path, confirms a trace in Opik, and returns the trace link. Use for "instrument my code", "add opik tracing", "add observability", "trace my agent". Not for building a new app from scratch, or a review-only pass with no code changes.

Root-cause a specific Opik trace, or a pattern across traces, and return a grounded explanation. Uses the hosted Opik MCP when it is connected, and falls back to SDK scripting otherwise. Returns the root cause, the evidence spans as clickable Opik UI links, and one suggested next step. Use for "why did this trace fail", "explain this trace", "debug this trace", "why is my agent slow or wrong". Not for adding tracing to an app (use the instrument skill) or for changing code.

Build an LLM evaluation and run it against the app, returning an Opik experiment with scores and its link. Picks a test suite with judge assertions or a dataset with metrics, sources cases from traces or synthetic data, scores heuristics-first then one-failure-mode judges, runs client-side via the SDK or server-side for prompt-only targets, and reads the scores back. Covers RAG evaluation, error analysis, writing and validating LLM judges against human labels, and auditing an existing eval pipeline. Use for "evaluate my agent", "measure quality", "build an eval", "write an LLM judge for hallucinations", "audit our evaluation pipeline", "how good is my RAG", "set up evals for this". Not for before/after on an existing suite (use compare), one regression case (use test), scoring production traffic (use online-eval), or the ship/hold decision (use verify).

Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agent_insights_issue entities, offers to turn Diagnostics on when the project has it switched off, then fills the gaps with list (filters, sort, a time window); without the MCP it reads the same via the SDK (agent_insights and search_traces), so it works with no MCP. Returns a ranked shortlist, each item ready to hand to the explain skill. Use for "what is broken in production", "which traces need attention", "find failing or slow traces", "which tool calls are failing", "triage my agent". Not for offline experiment results (use evaluate or compare) and not for root-causing one trace (use explain).

Run a candidate against the baseline over an Opik test suite and read the numbers back — which cases broke, which got fixed, the per-metric deltas, worst rows, and whether the two runs are comparable — with the Opik compare-view link. Runs via the SDK; reads results via the MCP when connected. Does not issue a ship/no-ship verdict. Use for "did my fix work", "compare against the baseline", "run the regression suite", "why did quality drop", "which cases regressed", "compare these two experiments". Not for the ship/hold decision itself (use verify), live production triage (use diagnose), building an evaluation from scratch (use evaluate), or capturing a single case (use test).

Reference for the Opik SDK — tracing, span types, framework integrations, threads, and the prompt library (Python, TypeScript, REST). Use for "what span types exist", "how do I flush", "track_openai", "add OpikTracer", "version a prompt". To instrument a repo end to end, use the `opik-instrument` skill.