Skill 06 of 30

Scene and core workflows

Laboratory Submission Pack Builder

Give each laboratory the task-relevant context, item history, controls and neutral questions needed to assess and accept the work.

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

Build neutral multi-discipline laboratory forwarding material from authorised case and exhibit records and identify submission deficiencies. Use a discipline-specific skill when biology, DNA, drugs, documents, impressions, toxicology, or another specialist workflow is the main task. Not for directing a desired conclusion.

What to provide

  • case question and authority
  • exhibit register and custody
  • recovery and packaging details
  • known references and controls
  • hazards
  • laboratory submission rules

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

Method

  1. Separate requests by appropriate discipline and laboratory scope.
  2. State the question neutrally and avoid embedding a preferred result.
  3. List each item, source, condition, packaging, seal, history, hazard and relevant control.
  4. Include only task-relevant context and identify potentially biasing information.
  5. Check acceptance prerequisites, priorities, contact details and return requirements.

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

Outputs

  • forwarding memo draft
  • discipline-specific exhibit schedules
  • neutral examination questions
  • hazard and handling notice
  • deficiency and approval checklist

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

Hard limits

  • Do not omit potentially exculpatory context.
  • Do not instruct the laboratory to reach a result or use a method outside its approved scope.
  • Do not represent the submission as accepted until the laboratory confirms it.

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 and receiving laboratory examiner.

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

Sample prompt

Use $laboratory-submission-pack-builder to prepare separate neutral biology, toxicology, digital, and trace submissions.

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.