Skill 08 of 30

Toxicology, death and chemical evidence

Suspicious Death Investigation Planner

Keep competing explanations visible and turn fragmented death-investigation material into a coordinated, reviewable plan.

View SKILL.md on GitHub Download this skill
AI-assisted draft. Not a forensic conclusion.

Use this skill only with authorised material and within the user's role, competence, jurisdiction, laboratory procedures and information-handling rules.

When to use this skill

Plan hypothesis-neutral investigations of unexplained or suspicious deaths across scene, medical, witness, digital, pathology, and laboratory workstreams. Do not declare murder, cause, manner, or perpetrator.

What to provide

  • scene and body documentation
  • identity and medical history
  • witness and timeline material
  • post-mortem and toxicology status
  • digital and physical evidence inventories
  • applicable local death-investigation procedure

If a material input is absent, it should remain marked as unknown. The skill must not reconstruct missing facts from narrative fit.

Method

  1. Use suspicious or unexplained death terminology until a competent authority determines otherwise.
  2. Build a verified timeline and mark reported, observed, tested and unknown events.
  3. Maintain natural, accidental, self-inflicted and third-party-involvement hypotheses unless evidence validly excludes one.
  4. Map each hypothesis to supporting, weakening and non-discriminating evidence.
  5. Coordinate scene, pathology, toxicology, biology, trace, digital and identification questions.

Direct observations, reported facts, test results, expert interpretations, hypotheses, unknowns, conflicts and exclusions must remain in separate fields.

Outputs

  • investigation plan
  • death timeline
  • hypothesis matrix
  • forensic workstream map
  • unresolved-question and owner register

Every material statement should cite an exhibit, file, page, image, timestamp, record, standard or named assumption.

Hard limits

  • Do not determine murder, suicide, accident, cause, mechanism, manner or perpetrator.
  • Do not use victimology to blame the deceased or infer dangerousness.
  • Do not recommend arrest or coercive action.

The skill must not determine guilt, recommend arrest or coercive action, invent evidence, backfill records, promise admissibility or hide potentially exculpatory, adverse, inconsistent or limiting information.

Required human review

Reviewer: Investigating officer, medicolegal authority, pathologist and relevant forensic experts.

The reviewer must approve, amend or reject each material observation and interpretation before operational, laboratory, prosecutorial or court use.

Sample prompt

Use $suspicious-death-investigation-planner to build a neutral plan that keeps competing death hypotheses visible until expert review.

Skill source files

Skill instructionsScope, intake, method, outputs, limits and review requirements OpenAI metadataDisplay name, description and default prompt Discipline guidancePrimary publications and controls specific to this skill Core forensic workflowEvidence states and the shared output contract Safety and human reviewProhibited uses, scientific controls and reviewer levels India legal layerBNSS, BSA, MHA and local implementation controls

View the complete Forensic AI Skills project on GitHub.