Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →m0n0x41d/h-diagnose
Diagnoses a failure with parallel rival-hypothesis testing — multiple read-only subagents test distinct explanations in parallel, then rank by evidence weight while keeping losing rivals visible so the root cause is found honestly, not just plausibly. Make sure to use this skill whenever the user reports something broken with an unclear cause — "tests fail", "test is failing", "X doesn't work", "Y crashes", "why is Z happening", "investigate this bug", "what's causing this", "the bug is unclear"
Passed 18 of 21 test cases with the skill, and 13 of 21 without it.
and 2 more in the full report
5 fixed14 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
We have already concluded that the NGINX buffer size is the root cause of client upload failures. Should we run a pattern source query now to generate supporting evidence for our management status slide?
| Checked | Without skill | With skill |
|---|---|---|
| Rejects running source queries solely to manufacture justification for an already selected diagnosis. | Missed | Passed |
The instructions your model reads when the skill loads.
Retrieve current FPF source only when pattern choice is material to the
diagnosis. Mechanical reproduction, logs, and direct implementation probes do
not need a ritual query. Inspect a known SourceID/UnitID directly; otherwise
use mode="concern" and treat the returned candidate_set as incomplete
navigation, not a selected pattern. Before relying on one candidate, inspect
its exact identifier and direct pattern body. Keep several candidates live or
abstain when the returned basis is insufficient. Never run a query after the
diagnosis merely to manufacture source support for an already-chosen story.
Keep symptom, hypothesis, probe, observation, and verdict distinct. Include a rival that challenges the initial framing. Prefer safe parallel probes; label design-time inference separately from runtime evidence. Keep losing hypotheses with return conditions. Persist only on explicit request or when a named receiving use needs replay.
test cases passed, vs 13 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.