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 Waddling-Penguin/mogkit --skill interview-coachgit clone --depth 1 https://github.com/Waddling-Penguin/mogkitWrote 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/waddling-penguin/mogkit/interview-coach)<a href="https://agentmods.dev/skills/waddling-penguin/mogkit/interview-coach"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/interview-coach.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 5.1 | $0.00004 | $0.01294 |
| Opus 5 | $0.00002 | $0.00647 |
| Sonnet 5 | $0.00001 | $0.00259 |
| Haiku 4.5 | $0.00000 | $0.00129 |
Grade A, and why
interview-coach 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
A PM gets better at discovery by reviewing their own interviews with someone who knows what to look for. Most of the value of a discovery interview is hidden in what the interviewer didn't do — the leading question they didn't notice, the rich answer they didn't pull on, the moment they started pitching the product instead of listening. This skill plays the role of the person who watches the tape with them.
It coaches the interviewer. It does NOT summarize what the interviewee said — that would be content extraction, which is a different job (and a job a PM should still do themselves before they reach for tools). The review reads the transcript from the interviewer's seat and points at the craft moves the PM can make next time.
Procedure
- Read the transcript. Identify the interviewer's turns and the interviewee's turns. If the transcript is ambiguous about who's speaking, say so and ask the PM to relabel before proceeding.
- Scan the interviewer's turns for the following craft patterns. For each hit, capture the quote of the interviewer's question or response, a short note on the pattern, and the better move: a. Leading the witness — questions that telegraph the desired answer ("Don't you think it would be easier if...?", "Would you use this if we built it?"). Frame the rewrite as a non-leading open question. b. Hypothetical instead of behavioral — asking what the user would do instead of what they have done. The Mom Test principle. Note the past-behavior version of the question they should have asked. c. Accepted-without-follow-up — a rich answer (a specific story, a strong emotion, a contradiction) that the interviewer moved past without pulling on. Note the follow-up that was right there. d. Pitched instead of listened — the interviewer slipping into describing the product, hinting at the solution, or selling. Note where this happened and what listening would have looked like. e. Compound or vague questions — two questions in one, or a question so abstract the interviewee answered something easier. f. Confirmation-seeking — questions designed (often unconsciously) to validate a hypothesis the PM brought in.
- Identify the two or three highest-value follow-ups missed — the moments where one more "tell me more about that" or "when was the last time?" would have produced the most learning. Pick the ones that would have changed what the PM walked away with.
- Note what the interviewer did well. Specific moves: a good silence held, a good "and then what happened?", an artful refusal to take the bait of a hypothetical. Coaching that only critiques is bad coaching.
- Identify the one craft move to focus on next interview — a single, specific behavioral change. Not "ask better questions"; rather "stop yourself before any question that contains the word 'would'."
- Emit the output contract. Do not summarize the interview content.
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 · 111 lines · 4 tokens per session scan A 79201e1d8cd9
interview-coach is a skill published in the GitHub repository Waddling-Penguin/mogkit (5 stars, last pushed 3mo ago), licensed MIT. It adds 4 tokens to every session and 1,294 once invoked, about $0.0000 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
find-skills
Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.