failure-diagnosis

FoundationJIT only

analysis-agent/task-agent/review-agent: use when symptoms, logs, metrics, regressions, or incidents need cause analysis; skip when no diagnosis decision exists.

Group: Engineering workflow
Supported roles: MainAnalysisTaskReview
Source: SKILL.md

Use when

Trigger signals that make this skill the right owner

diagnose failures SEV incident response symptoms logs metrics regressions hypotheses root cause and postmortem actions

Do not use when

Anti-triggers — as binding as the triggers above

no task-local failure diagnosis decision is required

Required inputs

What must be supplied before this skill can decide anything

current task contract
selected primary Professional Skill
task-local trigger evidence

Output contract

What this skill owes the next role

bounded diagnosis with symptoms, timeline, evidence provenance, causal hypotheses, discriminating observations, verified or provisional cause, reproduction or equivalent proof, corrective rationale, proof limits, and residual owners

Escalation signals

When this skill must hand the decision back

Jumping to fixes without evidence or incident command can mask root cause and extend customer impact

Loaded by

This skill never owns a task. These professionals may pull it in as Layer 3.

Targeted references

Each reference carries its own load condition. None of them enter context by default.

Reference	Load when	Do not load when	Required by
benchmarks-and-patterns.mdbenchmark-pattern	A real symptom needs competing hypotheses or causal reconstruction.	The verified failure mechanism is already established.	TaskReviewAnalysis
checklist.mddecision-checklist	Diagnosis spans triggers, contributors, timelines, and falsifying checks.	No unresolved symptom or causal question remains.	TaskReviewAnalysis
evidence-freshness.mdevidence-pattern	Cause claims depend on current logs, traces, commands, or source.	No diagnostic conclusion awaits freshness review.	TaskReviewAnalysis