Exp Campaign: observe → grill → enumerate → prune → stage → hand off → review

Ponytail for experiments: the campaign is as small as the evidence allows, and as complete as the claim requires. Never open with the full factorial matrix; never silently drop a dimension. Enumerate everything, then earn every deletion with a cheap probe whose outcome justifies it.

When this skill applies

• A direction that needs multiple branches, ablations, or conditional staging. One bounded branch with known configuration is exp-batch; one missing datapoint is exp-probe; a still-fuzzy idea is exp-discuss.
• The researcher's explicit choice wins; never switch silently. Judge by decision-tree depth and factor count, not by how long the experiments run (if unsure between probe and batch, use batch). Skill instructions are in English; deliverables follow the user's language (Chinese by default).

1. Observe before asking

• Read project memory, dashboards, past runs, logs, and previous conclusions. Establish what is already known, which baselines exist, which metrics are canonical, and what the current evidence does NOT cover.
• Restate the researcher's idea in 2-3 sentences: the claim to test, what a convincing final figure looks like, and what is out of scope. Separate explicit requirements from open questions.

2. Grill the researcher

Use bounded rounds of frontier questions — only what the settled decisions have already unblocked — each with a recommended answer; facts you can inspect are yours to find, never the researcher's. Recompute the frontier after each round of answers and ask the next round: the round count is not capped, and stopping is decided by whether a further question would still move scope, claim, or acceptance.

Ask about and surface, in frontier order: