The testing → test-servers hand-off fires only a third of the time

[cliffhall]

Now that #2204 can measure a hand-off, the first thing it measures is a weak one.

testing's body opens by telling the model that picking a fixture is /test-servers and that it has to load it. With the two committed chain cases in .claude/skills/test-servers/evals/evals.json, that pointer is followed 33% of the time (RUNS=3, CHAIN_MAX_TURNS=14):

Hand-off (14 turns)
FAIL  33%  testing → test-servers     Write an integration test that exercises tool listing end to end.
FAIL  33%  testing → test-servers     Add end-to-end coverage for the tool-list pagination path.

Two things worth knowing before working on this:

• An earlier draft of those prompts measured 100% and 67%, and that was an artefact. They said "against a real server" / "against a live server", which is test-servers' own trigger — so the model could pick testing and then pick test-servers from the original prompt, in that order, scoring a hit that would have survived deleting the pointer entirely. The prompts were rewritten to carry no server cue, and 33% is what the pointer alone is worth. Any fix has to be re-measured against prompts with no target cue, or it measures the same artefact.
• Do not fix this by lowering CHAIN_THRESHOLD. The bar is 0.5 ("the pointer is taken more often than not") and the two red cases are the standing measurement, not a build break — skills:eval is deliberately not a gate.

What to try

• Reshape where and how testing names /test-servers. Tune skill descriptions and eval cases to a reliable trigger rate, and document how #2202 showed that the shape of a description is the lever that moves a trigger rate; the same may hold for a pointer inside a body.
• Check whether the run reaches a point where it knows it needs a fixture at all within 14 turns — CHAIN_MAX_TURNS is a knob, and a rate that climbs with it means the budget is the constraint rather than the pointer.
• Re-run the full suite afterwards, not just these two cases: per AGENTS.md, changing what one skill says measurably moves the trigger rates of skills nobody touched.

Acceptance

• The testing → test-servers hand-off measures above 50% at RUNS=5, with prompts that carry no test-servers trigger of their own.
• The full skills:eval suite shows no first-move regression.