Skip to main content
ClaudeWave
Skill1.4k estrellas del repoactualizado 1mo ago

h-diagnose

h-diagnose implements a structured diagnostic workflow for root-cause analysis using parallel hypothesis testing to avoid anchoring bias. It guides users through stabilizing observations, framing diagnosis problems in the HAFT system, querying code context when needed, and generating multiple competing hypotheses with ranked verdicts. Use this skill when investigating intermittent failures, obscure bugs, or system anomalies where systematic elimination of alternatives is necessary rather than intuitive guessing.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/m0n0x41d/haft /tmp/h-diagnose && cp -r /tmp/h-diagnose/packages/haft-pi/skills/h-diagnose ~/.claude/skills/h-diagnose
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# h-diagnose — Test rival explanations

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.