AI Skills Catalog
Skills pack Tools

Interview Mapper

Map interview transcripts to structured findings with line-linked quotes, support checks and a human review queue for disputed interpretations.
SKILL SCORE87How it is scored
VerifiedFreeMIT

Works with

Packaged from the source skill for Claude, Codex and 4 more.

About this skill

Interview Mapper organizes transcript analysis into factual observations and interpretations that need closer review. Alireza Rezvani’s skill includes lenses for customer research, organizational interviews and other interview types, plus local tools for numbering text, checking quotations and assembling evidence.

Inputs can be text, DOCX or speaker-labelled subtitle transcripts. The result is a mapping with traceable quotes, gaps and disputed claims, followed by cross-interview synthesis when enough evidence exists. Synthetic examples and agreement between model runs do not establish real-world validity or justify automated decisions about people.

Use this skill when

  • A stakeholder report must show which interview lines support each conclusion.
  • Several interviews need the same coding lens and a record of contradictory evidence.
  • You want to separate a quote that exists in the transcript from an interpretation that the quote actually supports.

What it can do

  • Prepare numbered transcripts and subtitle timecode sidecars while flagging instruction-like source text as untrusted data.
  • Check exact or approximate quote matches, missing evidence and disagreement between separately prepared interpretations.
  • Create adjudication cards and a provenance board, and retain weak cross-interview patterns as a watchlist rather than settled findings.

Typical workflows

  1. Confirm consent, retention and where transcripts may be processed; de-identify sensitive text before numbering it.
  2. Choose a lens, map claims to quotes and run the local evidence checks. Arrange independent interpretive passes through the chosen agent rather than assuming the Python helpers supply a model service.
  3. Have a researcher resolve disputed or sensitive claims, then synthesize only supported patterns across the relevant interviews. Hiring and other individual assessments remain human decisions.

What is inside the skill

Section headings from the original SKILL.md (about 969 words of instructions). Read the full text in the source repository before installing.

  1. Distinct from product-research
  2. Workflow
  3. 16 lenses (1-on-1 + group formats)
  4. Pipeline (S0–S8)
  5. Scripts
  6. Honest limits
  7. Anti-patterns
  8. Cross-References

Bundled files

  • assets/evals/evals.json
  • assets/evals/gold/gold.json
  • assets/evals/gold/transcript.txt
  • assets/example-outputs/decision-memo.md
  • assets/example-outputs/insight-cards.md
  • assets/example-outputs/journey-map.md
  • assets/example-outputs/opportunity-prioritization.md
  • assets/example-outputs/personas.md
  • references/ethics.md
  • references/intake.md
  • references/pipeline.md
  • references/reliability.md
  • references/rubric.md
  • references/synthesis.md
  • references/validation.md
  • scripts/batch_prepare.py
  • scripts/build_provenance.py
  • scripts/calibrate_threshold.py
  • scripts/check_support.py
  • scripts/compare_to_gold.py
  • scripts/consensus.py
  • scripts/coverage_gaps.py
  • scripts/extract_claims.py
  • scripts/extract_nuggets.py
  • scripts/make_adjudication.py
  • scripts/number_lines.py
  • scripts/render_board.py
  • scripts/route.py
  • scripts/score_insights.py
  • scripts/verify_quotes.py
  • templates/brand-positioning.md
  • templates/candidate.md
  • templates/change-readiness.md
  • templates/conflict-mediation.md
  • templates/custdev.md
  • templates/ethnographic.md
  • templates/exit.md
  • templates/expert.md
  • templates/focus-group.md
  • templates/intercept.md

Example prompts

  • Map these three de-identified customer interviews with the same problem-discovery lens. Cite numbered lines, separate observations from interpretations and put patterns supported by only one interview on a watchlist.
  • Audit this interview mapping against the supplied transcript. Identify missing or altered quotes, claims not supported by their quotes, and substantive passages the mapping omits.
  • Prepare a human adjudication board from these independent coding runs. Show disagreements with source lines and timecodes; do not decide a candidate’s suitability or infer protected characteristics.

How to install Interview Mapper

Claude Packaged
  1. Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files.
  2. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.
  3. For Claude apps, upload the ZIP in the Skills section of the capabilities settings.
  4. Start a new session and describe the task in your own words. Claude picks the skill when the request matches its description.
More about skills for Claude
Codex Packaged
  1. Download the Codex package. The ZIP contains one folder named after the skill, with SKILL.md and bundled resources.
  2. Unpack the complete folder into .agents/skills/ inside your repository, or into ~/.agents/skills/ for personal use. Preserve its relative reference-file paths.
  3. Start a new Codex session and invoke the skill by name or with $skill-name, or describe a matching task.
  4. AGENTS.md is separate project guidance. The ZIP does not generate or modify that file.
More about skills for Codex
GPT Packaged
  1. Download the GPT package from the skill page.
  2. Create or edit a custom GPT (or a ChatGPT project) and paste the contents of SKILL.md into the instructions field.
  3. Upload the bundled reference files as knowledge so the GPT can consult them.
  4. Test with one of the example prompts from the skill page and adjust the instructions if your use case differs.
More about skills for GPT
Gemini Packaged
  1. Download the Gemini package from the skill page.
  2. For a project, unpack the complete folder into .gemini/skills/ or .agents/skills/. For personal use, use ~/.gemini/skills/ or ~/.agents/skills/.
  3. Run /skills reload in Gemini CLI, then /skills list to check discovery. There is no need to paste the skill into GEMINI.md.
  4. Test a matching task and verify the referenced tools and files are available.
More about skills for Gemini
Cursor Packaged
  1. Download the Cursor package from the skill page.
  2. Unpack the complete skill folder into .cursor/skills/ or .agents/skills/ in your project. For personal local use, ~/.cursor/skills/ and ~/.agents/skills/ are also supported.
  3. Start a new Cursor session. Type / in Agent chat and select the skill name, or describe a matching task.
  4. Commit the skill folder and resources for team use. Personal local skills are not automatically available to remote agents or automation runs.
More about skills for Cursor
OpenCode Packaged
  1. Download the OpenCode package from the skill page.
  2. Unpack the complete folder into .opencode/skills/ in your project, or ~/.config/opencode/skills/ for personal use. OpenCode also supports .agents/skills/ and .claude/skills/ compatibility locations.
  3. Keep supporting files at their original relative paths. AGENTS.md is separate project-wide guidance and is not generated by this ZIP.
  4. Start OpenCode in the project and test a matching task with the model and permissions you use.
More about skills for OpenCode

Permissions & security

Low risk

Inspect the source, license and declared permissions before use. Read the scripts before running them. Review method

Read project files
Write generated skill files

Interview Mapper FAQ

What does the Interview Mapper skill do?

Map interview transcripts to structured findings with line-linked quotes, support checks and a human review queue for disputed interpretations.

Which AI agents can use Interview Mapper?

Packages for Claude, Codex and 4 more are built from the same source instructions.

How do I install Interview Mapper in Claude?

Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.

Who made Interview Mapper and what is the license?

Interview Mapper is published by Alireza Rezvani under the MIT license. The source is https://github.com/alirezarezvani/claude-skills/tree/main/research-ops/skills/interview-mapper. The catalog keeps the original attribution.

What permissions does Interview Mapper need?

Declared permissions: read project files, write generated skill files. Risk level: low. Check the scripts in the source before running them.

Interview Mapper Skill — Alireza Rezvani | AI Skills Catalog