Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/redhuntlabs/wizard/interview-synthesisnpx skills add redhuntlabs/wizard --skill interview-synthesisgit clone --depth 1 https://github.com/redhuntlabs/wizardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/redhuntlabs/wizard/interview-synthesis)<a href="https://agentmods.dev/skills/redhuntlabs/wizard/interview-synthesis"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/interview-synthesis.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00025 | $0.01096 |
| Opus 5 | $0.00013 | $0.00548 |
| Sonnet 5 | $0.00005 | $0.00219 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
interview-synthesis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Synthesis
What this does
Turns raw interview notes (1-N interviews) into a structured synthesis: themes that recurred, verbatim quotes that anchor each theme, and the decisions or hypotheses the synthesis supports.
When to use
- After user research interviews
- After expert interviews for journalism / writing / product work
- After internal stakeholder interviews
- After any structured set of conversations where the next step is "what do we do with this"
What you bring (Inputs)
- Raw notes from N interviews (transcripts or your shorthand)
- The original research question (what were you trying to learn)
- Who the synthesis is for (you / a team / a client) — drives format
What you get (Output)
A document with: research question, methods, themes (3-7), verbatim supporting quotes per theme, surprises, and the decisions or hypotheses the data supports.
How it works (Steps)
This is a workflow.
Stages
Stage 1: Re-read with fresh eyes
Read all the notes through once without highlighting anything. Just take in the totality. This guards against latching onto the first idea.
Stage 2: Tag each note
Go through each interview and tag observations. Tags are short — 2-4 words. Examples: "Pricing confusion," "Wants integration," "Onboarding too slow."
Don't merge tags yet. Keep them granular.
Stage 3: Cluster tags into themes
Group similar tags. Aim for 3-7 themes. If you have 1-2, you're under-clustering. If you have 15+, you're over-tagging.
A theme is interesting if it appears in more than one interview AND is non-obvious.
Stage 4: Find the verbatim quote per theme
For each theme, pull the strongest 1-2 verbatim quotes. Use the speaker's actual words. These anchor the theme and prevent paraphrasing drift.
Stage 5: Note surprises
What did you NOT expect to hear? What contradicted your hypothesis going in? Surprises are often the most valuable output.
Stage 6: State the decisions or hypotheses
The synthesis should support concrete next steps. Examples:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 126 lines · 25 tokens per session scan A 9768b5566193
interview-synthesis is a skill published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 1,096 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
fastapi
FastAPI - 高性能 Python Web API 框架.
glances
Skill "glances" from CN-big-cabbage/github-skill-distiller, covering glances 跨平台系统监控工具, 技能概述, 使用流程, 关键章节导航 and ai 助手能力.
lazydocker
本技能帮助用户通过 lazydocker 的终端 UI 界面管理 Docker 容器、镜像、卷和网络，支持以下场景：.
fzf
Skill "fzf" from CN-big-cabbage/github-skill-distiller, covering fzf 通用命令行模糊查找器, 技能概述, 使用流程, 关键章节导航 and ai 助手能力.
paper-checking
论文查重系统 - 一亿字次级论文库秒级查重，支持纵向查重和横向查重.
you-get
网页媒体下载助手 - 从YouTube、Bilibili等网站下载视频、音频、图片.