interview-insights
Skill2 starsChanged 26 days agoMITView on GitHub
Turn a company's interview experiences from OAHelper into a round-by-round brief with recurring questions, what interviewers probe, and why candidates were rejected. Use when the user asks "what are X's interview rounds", "what does X ask in interviews", "how was X's interview process", "prep me for the X interview", or has an interview (not an OA) coming up.
In this repository8 other files it gives its agents.
- mcq-drillSkill
- oa-compareSkill
- oahelper-setupSkill
- oa-mockSkill
- oa-prepSkill
- revise-mistakesSkill
- solve-coachSkill
- study-planSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
If the user named a role (SDE intern, analyst, FTE), keep only matching write-ups and say how many remain.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Interview insights
Part of oahelper-mcp by Sirjan Singh.
1. Gather
oahelper_interviews(company, pages=2). It saves every write-up tolibrary/<co>/interviews/; read those files for full text, not the short list.- If the user named a role (SDE intern, analyst, FTE), keep only matching write-ups and say how many remain.
- Fewer than 3 write-ups: say the evidence is thin and treat patterns as tentative.
2. Analyse
- Weight by date. Write-ups from the last 12 months decide the current process; older ones are background. Put the year on everything you cite.
- Round structure: how many rounds, what each tests (DSA, LLD, HLD, CS fundamentals, projects, HR), duration and mode where stated.
- Repeated questions: anything asked in 2 or more write-ups, with the count.
- Signals: what interviewers dug into (projects, complexity, edge cases, SQL, OOP).
- Rejection reasons people reported, and offers vs rejections in the sample.
3. Output
# <Company> interview brief (<n> write-ups, <date range>)
## Process
| Round | Focus | Duration | Seen in |
## Asked more than once
- <question or topic> (<count>, <years>)
## What sank people
## Prep checklist (5 to 10 items, most important first)
## Sources
- <file links>Report only what the write-ups say. Mark anything inferred as inferred, and write
UNKNOWN where the data is silent. Never present one person's experience as policy.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

