Interview qa
A forkable job-search operating system for Claude — cover letters, interview prep, transcript Q&A, thank-you notes, and daily pipeline briefings, all in your own voice.
npx -y skills add ldenson1120/job-search-os --skill interview-qaAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
This skill should be used when the user says "extract interview questions", "what did they ask me", "pull questions from this transcript", "build my Q&A doc", "update my interview Q&A", "what questions came up at [company]", or shares a meeting transcript and wants the interview questions pulled out and organized.
SKILL.md
2.8 KB, as published. Nobody here has run it
Interview Q&A
Extract questions from interview transcripts, organize them by interviewer role, and map answers from the story bank. The output is a running document the user can build on across their entire search.
What to do
-
Get the transcript. The user will either paste it directly, share a file path, or it will come from ~~transcript tool. If nothing is provided, ask for it.
-
Extract the questions. Scan the transcript for every question the interviewer asked. Include:
- Direct questions ("Tell me about a time when...")
- Disguised questions ("I'm curious what your approach would be to...")
- Follow-ups that functionally changed direction
Exclude small clarifying questions ("What year was that?", "Can you spell that?") unless they signal something substantive about what the interviewer was probing.
-
Organize by interviewer. If the transcript includes multiple interviewers, group questions by person. Use their name and role if available; use "Interviewer 1" etc. if not.
-
Map to story bank answers. For each question, load
context/STORY_BANK.mdand identify the best matching story or answer. Format as:Q: [Question as asked] Best answer: [Story name] — [one-line summary] Gap: [If no story covers this well, note it plainly]
-
Flag patterns. After the question list, add a brief "What they were probing" section: 3-5 observations about what the interview was really testing. This helps the user calibrate for future rounds or similar companies.
-
Update the running doc if it exists. If a file called
context/INTERVIEW_QA.mdexists, append the new questions to it under a section for this company and interviewer. If it doesn't exist, create it in the same format.
Format for INTERVIEW_QA.md
# Interview Q&A
## [Company] — [Role] — [Date]
### [Interviewer Name, Role]
**Q: [Question]**
Best answer: [Story name] — [one-line summary]
**Q: [Question]**
Best answer: [Story name] — [one-line summary]
Gap: No strong story for this — consider building one around [theme]
---
Style rules
- Quote questions as close to verbatim as possible, not paraphrased
- If the same question came up in multiple interviews, flag it — it means the company cares about it
- Gaps are valuable. Don't skip them or soften them. If the story bank doesn't cover something that came up, that's information