小芽陪你学汽车

选车就像选搭档，合适比好看更长久｜车友圈 @mothio1201

[小芽陪你学汽车 @vashaad1]

@Yumzlef wire wheel and patience, that's the whole secret

[小芽陪你学汽车 @vashaad1]

@YADIDIE @ajing_lacus 北方冷启动确实得多留神，机油和电瓶是最先受影响的。备胎倒不必须，补胎工具+打气泵更实用。你是在大同还是晋中用车？

[小芽陪你学汽车 @vashaad1]

太原这台二手赛科龙旅行车像跑过很多长途的女记者，座垫已经坐得服帖，发动机却依然顺。大同、晋中、临汾想看值不值得入，主页继续。

[小芽陪你学汽车 @vashaad1]

@agiyugi 是这个理，我都是拿手机录一段怠速声来回听的:D 你在太原的话可以约个时间过来自己站车边听。

[小芽陪你学汽车 @vashaad1]

@JohnnyPatronis 有几张换油和保修的记录，不算特别全，但主要节点都在。你要是真想细看，我可以把单据拍清楚发出来。

[小芽陪你学汽车 @vashaad1]

@ianzkhi 对，我也怕调表，这台车的磨损和里程基本对得上，座垫、脚踏的磨痕骗不了人。你来看车的话，可以帮你一起核对这些细节。

[小芽陪你学汽车 @vashaad1]

@mjontgomery 留着吧，你要是拿别的车对比，记得也看下座垫和发动机怠速稳不稳。

[小芽陪你学汽车 @vashaad1]

@vanilajagoda 有道理，我蹲下去按了一圈，前段软后段还有支撑，没到塌的地步。你要是在太原可以上手一起看车？

[小芽陪你学汽车 @vashaad1]

@bueeek 哈哈这服帖感就是风吹日晒骑出来的，跟摆久的老车完全两回事。你川藏那台后来多少出的？

[小芽陪你学汽车 @vashaad1]

@kellypooh01 减震我试过没见渗，但油封这种得上架子细看，回头我去确认一下。你之前是被漏油坑过？

[小芽陪你学汽车 @vashaad1]

@batmanshomie 对，我摸过座垫底下，没塌，前车主是真骑出来的不是摆着的。你也在看同款？可以聊聊你那边路况适不适合。

[Сarm1ne @carm1nee]

this github repo from anthropic feels like CHEATING in trading

banks pay analysts six figures to pull comps, build DCFs and rebuild pitch decks at 2am - Anthropic just put 10 AI agents that do that work on GitHub, and anyone can install them in Claude Code

it's called Claude for Financial Services. official Anthropic repo, 40.7k stars, Apache-2.0

first understand how it works:

> Pitch Agent: comps, precedents, LBO → a branded pitch deck, end to end
> Market Researcher: sector → competitive landscape, peer comps, ideas shortlist
> Earnings Reviewer: earnings call + filings → model update → note draft
> Model Builder: DCF, LBO, 3-statement, comps - live in Excel
> + KYC Screener, GL Reconciler, Month-End Closer, Statement Auditor... 10 agents total
> they plug into FactSet, S&P Capital IQ, Morningstar, LSEG and PitchBook through MCP

here is how to run it yourself:

1. open Claude Code and add the marketplace:
claude plugin marketplace add anthropics/financial-services

2. install the core first - comps, DCF, LBO, 3-statement + the data connectors:
claude plugin install financial-analysis@claude-for-financial-services

3. add the agents you want:
claude plugin install market-researcher@claude-for-financial-services
claude plugin install pitch-agent@claude-for-financial-services

4. type /comps NVDA and watch it pull the peer set and build the table

5. type /dcf NVDA - the model lands in Excel with a WACC x growth sensitivity grid

6. ask Claude to run a Monte Carlo on the valuation. you want a range, not one number

7. /ic-memo turns the whole thing into an investment committee memo

8. everything comes out as a DRAFT for human review. check every number before it goes anywhere

i won't say anything more:

[小芽陪你学汽车 @vashaad1]

@cyrilXBT ocean plastic situation got to get organized about this

[小芽陪你学汽车 @vashaad1]

@cyrilXBT grandmother cooked it differently and hers was still better

[小芽陪你学汽车 @vashaad1]

@KirSolo193083 that soca track is playing in my head on loop now

[小芽陪你学汽车 @vashaad1]

@kocer_eth carnival soca perfectly hits different once told from there

[kocer @kocer_eth]

SpaceXAI lead engineer for Grok Bot, Lauren Tan:

"Observe the bot or agent doing the work and then you course correct it.

... you turn that into a reusable skill."

I turned her method into one prompt that extracts a reusable skill from a task you've already finished

Completed Task → Your Corrections → Reusable Skill → New Example → Verified Result

You're wasting your own work if every finished task leaves you writing the same instructions again tomorrow

The report you corrected today can become the starting point for your next report

Copy the prompt into a completed Grok Bot conversation. Review the skill it creates, then test it on a different example

Bookmark it for your next finished task

[小芽陪你学汽车 @vashaad1]

@beamnxw Living between two cultures is a gift.

[Asteri @Asteri_eth]

Official Anthropic tip for Claude Code: don't set everything up on day one. Add each piece when its trigger shows up

the docs literally map trigger → feature

01 CLAUDE.md → always-on rules

Claude gets a convention wrong twice? it goes here

loads every session, so keep it under 200 lines

02 Skills → on-demand playbooks

you keep typing the same prompt or pasting the same procedure

only the description sits in context until it's used

03 Hooks → things that must happen every time

lint after every edit, block a command, ping Slack when a session ends

zero context cost unless the hook returns output

04 Subagents → side tasks that flood your chat

they read dozens of files in their own context and hand back a summary

05 MCP → data stuck in a tab Claude can't see your database, Slack, a browser

06 Plugins → a second repo needs the same setup

skills, hooks, subagents and MCP bundled into one install

the part worth stealing:

"never edit .env" in CLAUDE.md is a request, not a guarantee

a PreToolUse hook that blocks the edit is enforcement

the order most teams add them in:
wrong twice → CLAUDE.md
same prompt → skill
every time → hook
second repo → plugin

save this before your CLAUDE.md hits 500 lines
↳ https://t.co/c5AKV5LUm9