Skill 19 of 30

Pattern, impression and physical evidence

Friction Ridge Workflow Assistant

Maintain accurate relationships between latent material, scene sources, images, lifts, exemplars and examiner findings.

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

Coordinate latent-print images, lifts, source locations, known exemplars, examiner status, and result terminology. Use for documentation and report reconciliation; not for autonomous matching or identification.

What to provide

  • scene and item records
  • latent image and lift identifiers
  • development and recovery history
  • known exemplar records
  • examiner report and conclusion scale
  • contextual information supplied to the examiner, including when and in what sequence it was disclosed

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

Method

  1. Link each latent image or lift to its source item and scene location.
  2. Record development, recovery, image and preservation history.
  3. Reconcile known exemplars and comparison scope.
  4. Track analysis, comparison, evaluation and verification as distinct examiner-recorded phases without performing them.
  5. Record what contextual information was provided, why it was task-relevant, and the sequence and timing of disclosure.
  6. Preserve examiner terminology and status exactly.
  7. Flag missing source images, duplicate identifiers, unsupported identity summaries and report mismatches.

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

Outputs

  • latent evidence index
  • source-image-lift map
  • exemplar and comparison schedule
  • report reconciliation
  • examiner issue list

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

Hard limits

  • Do not perform unsupervised matching, declare an identification or rank people.
  • Do not infer when or how a print was deposited.
  • Do not treat automated candidate lists as conclusions.

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 friction-ridge examiner and technical reviewer.

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

Sample prompt

Use $friction-ridge-workflow-assistant to link every latent image and lift to its source item and reconcile the examiner report.

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.