Skill 16 of 30

Toxicology, death and chemical evidence

Toxicology Report Review Assistant

Make analytical results transparent and identify internal or downstream inconsistencies for expert resolution.

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

Extract and quality-check one forensic toxicology report across analytes, matrices, units, methods, thresholds, qualifiers, specimen condition, and stated interpretation. Not for cross-source pathology and toxicology integration; use post-mortem-toxicology-findings-integrator for that. Never form independent fatality, impairment, or causation opinions.

What to provide

  • toxicology report and attachments
  • specimen and custody records
  • method and reporting references supplied by the laboratory
  • related medical or pathology report when authorised
  • the review question

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 analyte, matrix, value, unit, method, threshold and qualifier.
  2. Separate screening, confirmation, quantification and interpretive statements.
  3. Reconcile specimen IDs, collection times and condition with submission records.
  4. Flag unit, matrix, identifier, threshold, transcription and qualifier inconsistencies.
  5. Route clinical effect, fatality, interaction and causation questions to qualified experts.

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

Outputs

  • toxicology result table
  • specimen reconciliation
  • inconsistency register
  • interpretation boundary summary
  • expert clarification questions

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

Hard limits

  • Do not independently determine therapeutic, toxic or fatal effect.
  • Do not infer impairment or cause of death from concentration alone.
  • Do not provide harmful substance-use instructions.

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: Forensic toxicologist and pathologist or clinician where relevant.

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

Sample prompt

Use $toxicology-report-review-assistant to separate measured results from interpretation and flag unit, matrix, and qualifier inconsistencies.

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.