forensic-research

forensic-research is a Root-cause investigation skill for AI agents, published by deftai in the directive repository on GitHub. Skillspace rates forensic-research D (66/100) and it passed the safety scan; the rating is based on static analysis only.

Exhaustive evidence-based investigation with sub-agents, vBRIEF claim ledger, and mandatory falsification before conclusions or recommendations. Domain-agnostic core with pluggable domain packs. Artifacts live under .tmp/investigations/ only. Use for "why did", "investigate", "root cause", "what caused", "forensic research", production delay/failure questions, or when the operator rejects a first-theory diagnosis. Do NOT trigger on action requests that already name a fix unless the operator also wants investigation first. Do NOT trigger on bare "run tests" or "read logs" without a causal question. Triggers: forensic research, investigate why, root cause, what caused, forensic mode, stay in forensic. Mode stays ACTIVE across follow-ups until operator exits (exit forensic, done investigating, normal mode). Read references/forensic-mode.md + follow-ups.md.

Grade

D

Quality

66 / 100

Safety

Passed

GitHub stars

28

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.