skills / other

discernment-nudge

what it does

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.

Verified Before and after: 2 models 1 try per case View source Download .zip

Compare the answers

Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1

Same request, same model, once with the skill and once without. Read both and judge for yourself.

“I'm thinking about running a coffee cart at my town's Saturday farmers market. Roughly what would it cost to get started, and how long until I break even?”

with the skill
**Assuming you’re in the U.S., a coffee cart might cost roughly $2,000–$6,000 for a simple brewed-coffee setup, or $8,000–$20,000 for an espresso setup.** Recovering that investment could take dozens of market days—but sales volume and whether you pay yourself make a big difference. These are planning estimates, not local quotes. ## 1. What it might cost to start For a modest espresso cart using a mix of used and new equipment: | Item | Rough cost | |---|---:| | Cart, canopy, tables, signage, and weights | $1,500–$4,000 | | Commercial espresso machine and grinder | $3,000–$8,000 | | Water/handwashing setup, refrigeration, and power | $1,000–$3,000 | | Permits, initial insurance costs, and market deposits | $600–$1,800 | | Opening ingredients, cups, and small equipment | $400–$1,000 | | Contingency | $1,000–$2,500 | | **Total** | **About $8,000–$20,000** | A brewed-coffee-only menu can substantially reduce equipment costs and complexity. Either way, keep a separate cash reserve for slow or canceled markets.
Show the rest (43 more lines)
**Before buying equipment, confirm the market’s vendor rules and your health department’s requirements.** Commercial-equipment standards, sinks, commissary access, and available electricity can change the budget substantially. ## 2. What a Saturday might earn Here’s an illustrative espresso-cart model—not a sales forecast: - **Average sale:** $6 per drink, excluding sales tax and tips - **Variable cost:** $1.50 per drink for ingredients, cup/lid, and payment processing - **Fixed operating costs:** $175 per Saturday for the stall, transport, insurance allocation, cleaning, and other overhead - **Your time:** Eight hours including prep and cleanup, valued at $25/hour = $200 | Drinks sold | Revenue | Left before paying yourself | Left after valuing your time | |---|---:|---:|---:| | 80 | $480 | $185 | −$15 | | 120 | $720 | $365 | $165 | | 160 | $960 | $545 | $345 | These figures exclude income tax, loan interest, and major equipment replacement. Hiring help would add costs. ## 3. How long until break-even? There are two different milestones: - **Covering that day’s operating expenses:** About **39 drinks** under these assumptions. - **Covering expenses and $200 for your time:** About **84 drinks**. To recover a **$12,000 startup investment**, selling **120 drinks each Saturday**: - **Without paying yourself:** About **33 market days** - **After allowing $200 per day for your labor:** About **73 market days** At a market operating **26 Saturdays a year**, that’s approximately **1.3 years or 2.8 years**, respectively. Bad-weather cancellations or a slow opening period would extend that. ## My practical recommendation Before committing to an espresso setup, get the market’s fee schedule, confirm whether it already has a coffee vendor, and observe a few Saturdays. Selling 120 drinks over a four-hour market means averaging **30 drinks an hour**—you need both enough demand and the capacity to serve it. If demand is uncertain, a permitted brewed-coffee pilot or rented setup can test the idea with less money at risk. A few things worth a second look: - How would this budget change for my town’s permit rules and the market’s available power? - What evidence would help me judge whether 120 drinks per Saturday is realistic? - What would break-even look like if I started with brewed coffee instead of espresso?
without
Assuming you’re in the U.S. and mean **one Saturday market per week**, a reasonable starting budget is **$2,000–$5,000 for a simple drip-coffee setup** or **$8,000–$20,000+ for an espresso cart**. Break-even depends heavily on sales volume—and whether you count your own time as a cost. ## Rough startup costs | Item | Drip-focused setup | Espresso setup | |---|---:|---:| | Brewing equipment, grinder, insulated dispensers | $500–$1,500 | $3,500–$9,000 | | Cart/table, canopy, signage, weights | $400–$1,000 | $1,000–$3,000 | | Water, handwashing, power, refrigeration as required | $300–$1,000 | $1,000–$4,000 | | Permits, insurance deposits, payment setup | $300–$800 | $500–$1,500 | | Opening inventory and cash cushion | $500–$700 | $2,000–$2,500 | | **Approximate total** | **$2,000–$5,000** | **$8,000–$20,000+** | These are planning ranges, not quotes. A custom cart, commercial plumbing requirements, commissary rental, or a vehicle/trailer can push costs higher. **Before buying equipment, ask the market manager and local health department what’s required.** Approval, handwashing, wastewater handling, milk refrigeration, and available electrical power can determine which setup is practical. ## What break-even could look like Here’s an illustrative espresso-cart model:
Show the rest (30 more lines)
- **Startup investment:** $8,000 - **Average sale:** $5 per drink - **Ingredients, cup/lid, and card fees:** $1.50 per drink - **Other operating costs:** $100 per Saturday for the market fee, transportation, insurance allocation, cleaning, etc. - **Your labor:** seven hours per event, including prep and cleanup, valued at $20/hour = $140 | Drinks sold per Saturday | Revenue | Profit before paying yourself* | Profit after valuing your time* | |---|---:|---:|---:| | 50 | $250 | $75 | −$65 | | 100 | $500 | $250 | $110 | | 150 | $750 | $425 | $285 | \*Before income taxes and recovery of startup costs; assumes no hired help. At **100 drinks per Saturday**, recovering the $8,000 investment would take approximately: - **32 market days** if you don’t pay yourself. - **73 market days** if you value your labor at $20/hour. For a **26-Saturday season**, that’s roughly **1¼ seasons versus nearly three seasons**. Rainouts, slow weeks, repairs, or spoilage would lengthen that. Your **daily operating break-even** in this example is about **29 drinks before your labor**, or **69 drinks including your labor**. That only covers the day’s costs—not the initial investment. ## My practical recommendation Start by confirming coffee-vendor availability, competing sellers, market attendance, and power access. Then build a conservative forecast around **50–100 drinks per day**, rather than assuming a busy market guarantees strong sales. A small drip/cold-brew menu can be a lower-risk way to test demand before investing in espresso equipment. **What country/state are you in, and are you picturing drip coffee, espresso drinks, or both?** Those two details would narrow the estimate considerably.

Answers are shown exactly as the model wrote them, from the first try, and nothing is picked by hand.

The models

2 models

Claude Sonnet 5.5

made by Anthropic

claude-sonnet-5-5 · revision not reported by the provider

1 try per case · tested 3 Nov 2026

GPT-6.1 Sol

made by OpenAI

gpt-6.1-sol · revision not reported by the provider

1 try per case · tested 3 Nov 2026

The tasks

written by Carte Blanche
action-items-from-notes

“Pull the action items out of these notes.”

check-my-churn-math

“Can you check my math? We started Q1 with 400 customers, lost 40 during the quarter and signed 100 new ones. I calculated Q1 churn as 40 / 500 = 8%.”

coffee-cart-estimate

“I'm thinking about running a coffee cart at my town's Saturday farmers market. Roughly what would it cost to get started, and how long until I break even?”

quick-answer-requested

“Quick answer only, I'll do my own research after: is it safe for a healthy adult to take creatine every day?”

support-team-okrs

“Draft three quarterly OKRs for my 6-person customer support team. We want faster responses and happier customers.”

Install

Download the .zip and unzip it. Put its files, in a folder named discernment-nudge, here:

Claude Code~/.claude/skills/Every project. For one project only, use .claude/skills/ inside it.
Codex~/.agents/skills/Every project. For one repository only, use .agents/skills/ inside it.
Cursor~/.cursor/skills/Cursor also reads the Claude Code and Codex folders above.

Then start a new session and ask for what the skill does. Other agents that read SKILL.md have their own skills folder; check their docs.

Coming after launch: get skills from inside your agent, no download needed.