<< All versions

Skill v1.0.1

currentAutomated scan100/100
cdeust/zetetic-team-subagents/failure-forensics

+3 new

──Details
PublishedNovember 3, 2026 at 07:41 PM
Content Hashsha256:8c102eec575cadfc...
Git SHA4372ea9cfab2
Bump Typepatch
Compare with v1.0.0
──Files
Files (1 file, 2.8 KB)
SKILL.md2.8 KBactive
SKILL.md · 51 lines · 2.8 KB

name: failure-forensics shapes: [failure-forensics] description: > Read the wreckage before rebuilding. Use for incident post-mortems, "what happens when everything goes wrong at once?", flaky or anomalous cases being filtered out as noise, "that's weird" moments nobody wrote down, oscillating or unstable feedback behavior, and designs whose only failure mode is crash. metadata: version: "1.0.1"


Failure Forensics

Problem shape: something failed (or will fail) and the evidence is being averaged away, cleaned up, or explained by its most convenient story. The move: treat anomalies as data, reconstruct the timeline at the right timescale, and design the degraded state as a first-class behavior.

Relevant geniuses

AgentUse when
hamiltonoverload and simultaneous failure scenarios; priority shedding by criticality; the degraded mode is undesigned; "users will never do that"
mcclintockaggregate metrics look smooth but one specific case is weird; a class of observations is being trimmed as noise
fleminganomalies keep appearing during routine work and being cleaned up; "that's weird" said and never investigated
ginzburgreconstruct what happened from marginal traces and involuntary evidence (logs, timestamps, artifacts nobody meant to leave)
braudelthe incident needs three-timescale decomposition — event, cycle, structure — before a root cause is named
wuthe failure hides under an assumption everyone considered too obvious to test
maxwellthe system oscillates, overshoots, or hunts — feedback stability and gain-margin diagnosis

Invocation

  1. Pick the best-fit agent above. If two or more fit, run

tools/genius-invoker.sh route "<problem>" and take the top ranked match.

  1. Load it: tools/genius-invoker.sh invoke <agent> "<problem>", then read

agents/genius/<agent>.md in full.

  1. Apply the agent's <workflow> step by step and answer in its

<output-format>. Reproduce before claiming a cause; classify the cause before proposing the fix (coding-standards §6 root-cause protocol).

  1. Typical chain: ginzburg reconstructs the timeline → braudel separates

timescales → hamilton designs the degraded state. Run via tools/genius-invoker.sh compose ginzburg hamilton -- "<problem>".

  1. If no shape above matches, use a built-in agent with the closest GENIUS: pattern from rules/agent-routes.json instead.

Refuse when

  • No reproduction and no trace evidence exist — forensics reads records, it

does not invent narratives.

  • The requested output is a fix at the throw site with no cause classification.
← v1.0.0All versions