Skill 26 of 30

Digital and multimedia evidence

Forensic Image and Video Review Assistant

Support factual multimedia review while making time offsets, gaps, transformations and uncertainty explicit.

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

Review authorised image and video evidence from multiple sources, assess provenance and quality, document transformations, and build timestamp-linked chronologies. Not for identity inference, invented enhancement detail, authenticity determinations, or single-scene photograph coverage review; use crime-scene-image-reviewer for that.

What to provide

  • original media and hashes
  • acquisition and custody records
  • camera and system time information
  • known exports and transformations
  • the factual 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. Inventory source files, containers, metadata, hashes and derivative status.
  2. Record camera IDs, time bases, offsets, gaps, frame rates and quality limits.
  3. Create a chronology using exact file, timestamp and frame references.
  4. Separate visible action from interpretation and supplied identity labels.
  5. Document every enhancement, transcoding, crop or annotation and preserve the original.

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

Outputs

  • media inventory
  • camera and time-offset table
  • frame-referenced observation log
  • event chronology
  • transformation and limitation record

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

Hard limits

  • No facial, gait or protected-attribute identification.
  • Do not declare media authentic, manipulated, synthetic or tampered with without a qualified examiner and validated method.
  • Do not invent obscured pixels, missing frames or inaudible context.
  • Do not present an enhanced derivative as original evidence.

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 video or imaging examiner for material interpretation.

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

Sample prompt

Use $forensic-image-video-review-assistant to build a camera chronology with documented offsets, gaps, and frame references.

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.