Onboard New Hires to a Codebase with Gemini
Upload the whole repo or its key files, and Gemini gives new hires a reading order to understand the codebase within an hour
You are a senior engineer giving a new hire their first day onboard. I've uploaded the codebase. The new engineer has {{experience}} experience.
Produce a 1-hour reading plan:
## Stage 1: The 30,000-ft view (10 min)
Which 1-2 files give the "what does this project do" answer fastest? Why those?
## Stage 2: The data model (15 min)
Which files define the schema / types / domain model? What's the central object?
## Stage 3: The request lifecycle (20 min)
Follow one typical request from entry point to response. List files in order with 1-sentence "this is where X happens" annotation.
## Stage 4: Where the action is (15 min)
What 2-3 files contain the most domain-specific business logic that other engineers will mostly modify? Why those?
## Things to skip on day 1
3-5 folders that look intimidating but are auto-generated / vendor / tests / migrations — say "don't worry about these yet, come back week 2".
For every file mentioned: give the relative path, 1-sentence what it does, and "look for X" hint.Swap the variables inside the [ ] brackets for your own content, then paste into Gemini 2.5 Pro.
See what this prompt actually produces without leaving the site (live AI run, 1 credit).
Onboarding new hires is an eternal headache for engineering managers. Gemini can read the entire repo and produce a reading order — 10x faster than slogging through the README.
4 stage 讀檔計畫、每檔有「look for X」hint、加「不要看這些」防嚇跑
A description of the intended result. Check this entry's testing notes and try the prompt with your own inputs.
[tech_stack]技術棧（如：Next.js + TypeScript + Postgres / Django + Celery / Rails + Sidekiq）
[experience]年資（5+ years Python but new to TS / fresh grad / mid-level full-stack）
填下面的欄位，上方 prompt 會即時替換 [方括號] 內容。填好後按「複製組好的 prompt」直接丟進工具。
You are a senior engineer giving a new hire their first day onboard. I've uploaded the codebase. The new engineer has {{experience}} experience.
Produce a 1-hour reading plan:
## Stage 1: The 30,000-ft view (10 min)
Which 1-2 files give the "what does this project do" answer fastest? Why those?
## Stage 2: The data model (15 min)
Which files define the schema / types / domain model? What's the central object?
## Stage 3: The request lifecycle (20 min)
Follow one typical request from entry point to response. List files in order with 1-sentence "this is where X happens" annotation.
## Stage 4: Where the action is (15 min)
What 2-3 files contain the most domain-specific business logic that other engineers will mostly modify? Why those?
## Things to skip on day 1
3-5 folders that look intimidating but are auto-generated / vendor / tests / migrations — say "don't worry about these yet, come back week 2".
For every file mentioned: give the relative path, 1-sentence what it does, and "look for X" hint.Suno Engineer's Mindset: 4 Steps to a Song That Doesn't Sound Like AI
A studio engineer's breakdown of Suno's fatal weaknesses (fried vocals, high-frequency artifacts), plus a 4-step DAW workflow and a Suno Studio cleanup prompt.
5 Claude Weekly Workflows That Stuck After 6 Months
Proposal generator / meeting processor / content repurposer / Friday review / shutdown reset — out of 40 I tried, only these 5 survived, each saving 30+ minutes per run.
7 Cross-Model A/B-Tested Prompt Techniques (Not Vibes)
Written after six months of A/B testing 200+ prompts on Claude, GPT-4, and Gemini with human raters. Covers persona + constraint stacking, anti-examples, role-reversal QA, cognitive scaffolds, emotional priming, uncertainty CoT, and steelman-first.
5 trust-checking one-liner prompts (no role-play)
After a year of role-play system prompts and 14-step frameworks, here's the takeaway: the thing that actually moved the needle on quality was 5 one-line prompts. No roles, no markdown, no "you are an expert."