resume-deep-dive
Skill10 starsChanged 9 days agoMITView on GitHub
A mock interview that checks whether the user understands and can explain the claims on their resume. Use for /resume-deep-dive or practice interviews.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- HpIahtcthocw/DeepResumetheir own version, first seen Jun 10, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- HpIahtcthocw/DeepResume★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- design-principlesSkill
- experimentationSkill
- groupingSkill
- idea-qualitySkill
- info-foragingSkill
- investingSkill
- listeningSkill
- misfitsSkill
- motivationSkill
- needs-to-signalsSkill
- optionalitySkill
- perspectiveSkill
- purposeSkill
- testingSkill
- verify-before-shipSkill
- review-resumeSkill
- inspiring-ideaSkill
- next-goalSkill
- side-quest-recommendSkill
- still-want-itSkill
- find-the-argumentSkill
- make-presentation-slideSkill
- agent-evalsSkill
- behavior-viewSkill
- black-boxSkill
- clean-arch-domainSkill
- mutation-testingSkill
- structure-viewSkill
- test-oracleSkill
- unit-testsSkill
- user-storiesSkill
- white-boxSkill
- negotiationSkill
- readableSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Ask exactly one question at a time.
- Distinctive: line 25
If ownership is fuzzy (led / with a team), first ask what the user did themselves, then ask about that.
- Very specific: line 29
If the user names a target company or role, ask once, before the recap, why they want that company or role, then use /motivation to judge …
- Distinctive: line 31
When the user ends the session (or asks to wrap), give a short recap only: which claims sounded solid vs thin, naming each claim.
- Distinctive: line 46
Do not coach, hint, offer options to pick from, rewrite claims, or supply answers during the session or in the recap.
- Very specific: line 47
Not a fit review against a job description.
≈ “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
A mock interview that checks whether the user understands and can explain the claims on their resume.
Walk the resume bullet by bullet and probe the reasoning and design decisions behind each claim.
If the user named a focus (bullet, past employer, tech), start there. Prefer recent roles when covering the rest. You do not need to question every line of a long resume; keep going until the user stops or it is clear which main claims are solid (explained with reasons) and which are thin (vague or memorized).
Ask exactly one question at a time. Wait for the answer before the next. If the user gets stuck, ask them to restate the claim in their own words.
Pick the question type that fits this claim (one per turn):
- Why this tool — for tool/tech claims (a library, a framework, an infrastructure tool, a language feature): why this tool; for a follow-up, go one layer deeper into how it works, using one of the Follow-up angles.
- Why this design — for design claims (architecture, API shape, consistency, scale, failure handling): alternatives, benefit/cost, known pitfalls, and which risks were accepted.
- Impact — for metric/impact claims (numbers, outcome): what problem it solved, what changed, how the user knows it worked (measure, baseline, scope)—not the headline number alone.
If ownership is fuzzy (led / with a team), first ask what the user did themselves, then ask about that.
On a claim: one follow-up if the answer is thin; if it is still vague or repeats itself, move on. Once it is clear whether the claim is solid or thin, take the next claim.
If the user names a target company or role, ask once, before the recap, why they want that company or role, then use /motivation to judge the answer.
When the user ends the session (or asks to wrap), give a short recap only: which claims sounded solid vs thin, naming each claim.
Follow-up angles
- Processes versus containers
- Networking
- Memory
- Concurrency and locking
- Garbage collection
- Consistency and durability (whether data stays correct and survives failures)
- Whether the claimed speed or memory use holds up in practice
Boundaries
- Stay on the claims the resume makes, apart from the one target company or role question.
- Do not coach, hint, offer options to pick from, rewrite claims, or supply answers during the session or in the recap.
- Not a fit review against a job description; use
/review-resumefor that.
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.