More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Interview Transcript Coding System

    1

    Code interview transcripts into themes with an auditable codebook, so findings survive challenge.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Interview Transcript Coding System

    Interview Transcript Coding System

    Example session with this skill installed

    Apply the skill to a small test input and produce its core output. The script counts keyword hits from a small built-in codebook only; it does not code themes, and its counts must not be quoted as findings.

    • Read your context and instructions
    • Compiled the interview transcript coding

    A team had 14 user interviews about a checkout flow and a stakeholder who believed price was the main blocker. Coding produced 22 codes; the theme of trust in delivery appeared in 11 transcripts and 12 speakers, while price appeared in 6 transcripts and was prompted by the guide in 4 of them. The report showed speaker counts, which reversed the stakeholder's reading: trust, not price, was the unprompted theme. A negative case, one participant who praised delivery speed, was included and led to a follow-up question about regional differences. The decision that followed, a delivery-tracking fix before a discount, came from the coded evidence, and the codebook was reused for the second interview round, making the before-and-after comparison valid.

    Script demo (verified): running python3 scripts/code_transcript.py on a two-line test transcript printed Alice with trust 1 and delivery 1, and Bob with price 1 and delivery 1.

    This is a worked example produced by applying the skill, not a claim about a live customer outcome.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    A full coding workflow for interview transcripts: build a codebook from the data, apply it consistently, check agreement between coders, and report themes with evidence counts instead of impressions. The skill provides a step-by-step protocol with decision points, a decision table, a fill-in template, a checklist, and a scoring rubric, plus a runnable script (code_transcript.py) that applies a small keyword codebook to a speaker-labelled transcript and prints code counts per speaker. It focuses on finding the bottleneck first and fixing in an order backed by evidence, rather than applying generic advice.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    Coding does not prove a theme is widespread; it shows what appeared in this sample. Small samples and leading questions limit what can be claimed.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 23 days ago

    Permissions

    Terminal / Shell
    Listed23 days ago
    Updated21 days ago

    What's inside

    Frequently Asked Questions

    No. It organises evidence and decisions so judgement is applied to the right question, with a record of why.

    Longer than a generic checklist, because measurement comes first. Later uses are faster once templates and scripts are in place.

    Yes, by narrowing scope explicitly and recording what was skipped. The quality gate still applies to the narrowed work.