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 skills add ur-grue/autopunk-media-skills --skill interview-question-buildergit clone --depth 1 https://github.com/ur-grue/autopunk-media-skillsWrote 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/ur-grue/autopunk-media-skills/interview-question-builder)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/interview-question-builder"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/interview-question-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/interview-question-builder"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/interview-question-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00042 | $0.02290 |
| Opus 5 | $0.00021 | $0.01145 |
| Sonnet 5 | $0.00008 | $0.00458 |
| Haiku 4.5 | $0.00004 | $0.00229 |
Grade A, and why
interview-question-builder 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 7d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Question Builder
What This Skill Does
Builds a complete, staged interview question set for a podcast guest — organized from opening warm-up through core subject matter to closing reflection — with embedded follow-up prompts for each key question.
When To Use This Skill
- You have a confirmed podcast guest and need a full question set before the recording
- Your guest is an expert in a field you know less well, and you want preparation that allows you to have a genuine conversation rather than reading from a list
- You want to ensure the interview covers all necessary territory without feeling like a questionnaire
- You are interviewing someone with a sensitive personal story and need questions that build trust before going deep
What You Need To Provide
Required:
- Guest name and their relevant background (one paragraph is enough — what they do, what they're known for, why they're on the show)
- The episode's core subject or focus (what the conversation should primarily be about)
- Your show's tone and audience (e.g., "curious general audience, conversational tone" or "professionals in the field, technical questions welcome")
Optional:
- Any specific stories, moments, or claims you want to make sure you reach in the conversation
- Topics to avoid (personal subjects, ongoing legal matters, past controversies the guest has asked not to address)
- Approximate episode length (helps calibrate how many questions to include)
- Any prior work, writing, or interviews by the guest that the assistant should reference
How the Assistant Approaches This
- Reviews the guest's background and the episode focus to identify the three or four most interesting tensions, turning points, or ideas in the guest's work — these become the anchors for the core question section
- Builds a staged arc: opening questions that are easy and biographical (let the guest warm up), core questions that go to the heart of the subject (the ones that will make the episode worth listening to), and closing questions that pull back to perspective and reflection
- For each core question, adds two or three follow-up prompts in brackets — not scripted follow-ups, but reminders of where to dig if the guest's answer opens a door
- Flags any question that might be sensitive or that the guest may deflect, with a brief note on why and a suggested alternative framing
- Adds a "questions to have ready but not necessarily use" section at the end — overflow questions that can fill dead air or redirect a conversation that has stalled
- Closes with a "Next Step" note: which opening question to actually use first (and why), and whether guest-research-brief should be run to deepen background preparation before the recording
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 143 lines · 42 tokens per session scan A f02fc715ca9d
interview-question-builder is a skill published in the GitHub repository ur-grue/autopunk-media-skills (30 stars, last pushed 10d ago), licensed MIT. It adds 42 tokens to every session and 2,290 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
visual-prompt-forge
Generate model-specific prompts from shots.json. Outputs copy-paste-ready prompts for stills (Midjourney, Flux, Ideogram, GPT Image, Nano Banana, Seedream) and motion video (Kling, Veo, Seedance, Hailuo). Also runs a revision mode that reads a critique.json and re-emits prompts for only the failed shots, closing the…
storyboard-architect
Turn a creative brief into a production-grade storyboard with shot specs, timing, on-screen text, and per-shot rationale. Use when the user describes a video brief, plans a video, references shots or beats, scripts a social video, or hands over a creative concept to break into scenes. Produces run.json, storyboard.md…
storyboard-html-preview
Render a structured storyboard (storyboard.md, shots.json, text-overlays.json, brand-lock.snapshot.md) into a single-file HTML preview that is shareable, printable, and offline. Use when the user wants to share a storyboard, export for review, hand off to an editor, or print a hard copy. Triggers on "preview the…
visual-asset-critic
Critique a generated image against its source storyboard shot and prompt, producing revision notes. Use when the user has generated an image and wants feedback before committing. Triggers on "does this match the brief", "review this render", "is this on-brand", "what should I change", or uploading an image alongside a…
youtube-seo-thumbnail
Advanced thumbnail CTR analysis using computer vision, face/emotion detection, CLIP-embedding SERP similarity, Gestalt composition rules, and YouTube native Test & Compare planning. Use when user says "thumbnail review", "improve CTR", "thumbnail design", or provides a thumbnail image/URL.
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…