requirements — Claude Code skill: build list and install
The requirements Claude Code skill turns paying customers’ requests into a ranked feature list. It activates after a customer pays or when the conversation turns to scope, specs, or feature requests.
MIT ★ 92 updated 2026-11-06
/plugin marketplace add Jakeschincariol/whale-skill
/plugin install whale-skill@whale-skillWhat requirements does
The skill records each customer’s request in their own words, maps it to a feature, and combines matching features across customers. Running build writes whale/requirements.md, ordered by the paid amount behind each feature; requests from people who have not paid go under Later.
Customers can confirm their own list, and completed features can be marked with done. The reqs.py script runs with python3. Each outgoing message needs the user’s explicit approval, and one customer’s list stays private from others unless they agree to share it.
What it helps with
- turn paying customers’ requests into a feature list
- combine matching requests from different customers
- rank features by the paid amount behind them
- separate unpaid requests from committed work
- record customer confirmations and mark finished features
Example prompts for the agent
- Turn the paying customers’ requests into a feature list.
- Add the request to deal
north-pierto sync with QuickBooks. - Mark the feature
QuickBooks syncas done.
How to install requirements
1Plugin marketplace
/plugin marketplace add Jakeschincariol/whale-skill/plugin install whale-skill@whale-skillThis installs the whole whale-skill plugin with all its skills
2Skills CLI (Vercel)
npx skills add Jakeschincariol/whale-skill --skill requirements -a claude-code3Manually: put the files in place
~/.claude/skills/requirements/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/requirements/
1Skills CLI (Vercel)
npx skills add Jakeschincariol/whale-skill --skill requirements -a codex2Manually: put the files in place
.agents/skills/requirements/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Jakeschincariol/whale-skill --skill requirements -a cursor2Manually: put the files in place
.cursor/skills/requirements/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Jakeschincariol/whale-skill requirements2Manually: put the files in place
.github/skills/requirements/SKILL.md1Skills CLI (Vercel)
npx skills add Jakeschincariol/whale-skill --skill requirements -a gemini-cli2Platform CLI
gemini skills install https://github.com/Jakeschincariol/whale-skill --path requirementsManually: put the files in place
.devin/skills/requirements/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about requirements
How do I install requirements in Claude Code?
Run these commands in order: /plugin marketplace add Jakeschincariol/whale-skill, then /plugin install whale-skill@whale-skill.
What does requirements do?
It maps paying customers’ words to features, combines matching requests, and ranks the list by paid deal amounts. Requests from people who have not paid go into a separate Later section.
What does requirements need to run?
The reqs.py script runs with python3. The user must explicitly approve each outgoing message.
Source text
SKILL.md · MIT
---
name: requirements
description: >-
Requirements. Turns what paying customers asked for into the build list. Captures each ask in their own
words with the feature it becomes, merges the same feature across customers, and ranks the list by how
much paid money is behind each line, so you build exactly what was paid for and nothing else. Asks from
people who haven't paid wait on a separate list. Logs each customer confirming the list, and marks
features done. Use when the user says "what should I build", "requirements", "build list", "they asked
for", "what did they want", "scope", "spec", "feature requests", or right after a customer pays.
argument-hint: "[add <deal> | list | build | confirm <deal> | done <feature>]"
---
# requirements
Most products fail because the founder guessed. Here nobody guesses: every line traces back to a company that
paid and said what they need. That list is the product.
`${CLAUDE_SKILL_DIR}` below is this skill's folder (where this SKILL.md lives).
```bash
python3 "${CLAUDE_SKILL_DIR}/reqs.py" add --deal north-pier --ask "Sync with QuickBooks" --feature "QuickBooks sync"
python3 "${CLAUDE_SKILL_DIR}/reqs.py" list --deal north-pier
python3 "${CLAUDE_SKILL_DIR}/reqs.py" build
python3 "${CLAUDE_SKILL_DIR}/reqs.py" confirm --deal north-pier --said "Yes, that's what we need." --at 2026-11-04
python3 "${CLAUDE_SKILL_DIR}/reqs.py" done --feature "QuickBooks sync" --at 2026-11-20
```
## Steps
1. **Ask right after they pay.** While it's fresh, on a call or by email. Three questions do most of it:
- "Walk me through what happens today, from the invoice going late to the money coming in."
- "What would have to be true for you to cancel what you pay for now?"
- "What else has to work with this?"
2. **Write down their words.** `reqs.py add --ask` is what they said, close to word for word. `--feature` is what it becomes.
Same feature, same name: that's how asks merge across customers.
3. **Build the list.** `reqs.py build` writes `whale/requirements.md`: features by the paid money behind them, each with who asked
and how they said it. What someone who hasn't paid asked for goes under Later.
4. **Send it back to them.** Show the user the customer's own list, then "Send this to Renee to confirm? Reply yes or no." Their
reply goes in with `reqs.py confirm --said "<their words>"`. This is your scope in writing, and it protects you both.
5. **Say no when it's a no.** If an ask can't be built by the promised date, tell the customer now and agree what happens. Move the
date only with their yes (`/pre-sale new-date`), or refund them. Never quietly drop it.
6. **Build.** Claude can start on the list. `reqs.py done` marks each feature, for everyone who asked. `/launch-planner` tracks the dates.
## Reading the list
- **Top of the list:** several customers asked, or one big one did. Build it first.
- **One customer, small money, big job:** ask if it's a must-have before the ship date, or can come after.
- **Under Later:** a real signal, not a commitment. Ask if they would pay for it.
- **Nobody asked:** it isn't on the list, however good the idea is. Build that after they have what they paid for.
## Example from the reel
North Pier's requirements, ask to feature: "Text the customer first, then email" to Text + email sequence. "Sync with QuickBooks" to
QuickBooks sync. "Escalate after 30 days" to Auto-escalation at 30 days. "Weekly report to the CFO" to Monday CFO report. On the example
board, Saltmarsh and Copperline ask for some of the same, so QuickBooks sync has $42,000 behind it and goes first. (Illustrative: every
company and ask is fictional. QuickBooks is a real product, and using its name here implies no connection to it.)
## What it never does
- Never adds a feature nobody asked for, and never puts words in a customer's mouth.
- Never logs a confirmation they didn't give.
- Never drops a paid-for feature without telling the customer.
## Consent and truth
- Nothing is sent, built or promised without the user's explicit yes for that exact message. Claude drafts, the user says "yes", then
it goes out from the user's own accounts. One yes per message. Never "yes to all".
- A customer's requirements are private to that customer. Never show one customer's list or name to another without their okay.
- Never invent a number, a result, a client or a deadline.
© Jake Schincariol · MIT · Jakeschincariol/whale-skill