Skill 23 of 30

Toxicology, death and chemical evidence

Post-Mortem and Toxicology Findings Integrator

Expose agreements, conflicts, timing issues and unanswered expert questions across pathology and toxicology sources.

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

Integrate pathology, toxicology, medical, specimen, and scene sources to expose agreements, conflicts, timing issues, and expert questions without exceeding the reports. Not for quality-checking a single toxicology report; use toxicology-report-review-assistant for that. Never form independent cause or manner-of-death conclusions.

What to provide

  • post-mortem report and notes
  • toxicology report and specimen records
  • medical history and treatment records
  • scene and body documentation
  • expert limitations and addenda

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

Method

  1. Extract findings with exact source, status and qualifier.
  2. Link toxicology results to the correct specimen, collection details and post-mortem context.
  3. Compare timing, pathology, medical and scene information without resolving expert conflicts.
  4. Separate finding, interpretation, cause and manner statements.
  5. List discrepancies and targeted questions for the pathologist or toxicologist.

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

Outputs

  • integrated findings table
  • specimen and result map
  • agreement and conflict register
  • limitation summary
  • expert question list

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

Hard limits

  • Do not independently determine cause, mechanism or manner of death.
  • Do not infer fatality from concentration alone.
  • Do not rewrite expert conclusions into stronger language.

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: Pathologist, forensic toxicologist and medicolegal authority.

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

Sample prompt

Use $post-mortem-toxicology-findings-integrator to identify agreements and conflicts requiring the pathologist or toxicologist.

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.