Skill 11 of 30

Scene and core workflows

Scene Reconstruction Hypothesis Manager

Structure event segments and competing accounts so investigators and experts can identify discriminating evidence without premature closure.

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

Test competing scene-event hypotheses against supporting, weakening, conflicting, and non-discriminating evidence after source documentation exists. Use crime-scene-documentation-planner to decide what scene records are needed. Do not declare what happened or rank people.

What to provide

  • scene observations and measurements
  • approved expert reports
  • witness or record-based event claims
  • time and spatial data
  • explicit hypotheses to test

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

Method

  1. Break each proposed account into testable event segments.
  2. Record the source and evidence state for every premise, plus when potentially biasing context was introduced and to whom.
  3. Map evidence as supporting, weakening, conflicting or non-discriminating.
  4. Identify alternative mechanisms and evidence that would distinguish them.
  5. Track excluded hypotheses only with the exact basis and reviewer.

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

Outputs

  • event-segment timeline
  • hypothesis-evidence matrix
  • discriminating-test plan
  • assumption and conflict register
  • expert-review questions

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

Hard limits

  • Do not declare that an event occurred or identify a participant.
  • Do not convert absence of evidence into evidence of absence without an expert basis.
  • Do not use the matrix to rank people for 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: Qualified scene reconstruction experts and investigating officer.

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

Sample prompt

Use $scene-reconstruction-hypothesis-manager to compare three event sequences and identify evidence that genuinely distinguishes them.

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.