Skip to main content
skill CX Codex

first-win — Claude Code skill: tasks and installation

This Claude Code skill offers three starter tasks that end with a usable artifact. Run /first-win to turn a post into social content, shape an idea into a plan, or sort email into priorities.

MIT ★ 26 updated 2026-11-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add wrg32786/aigent-os --skill first-win -a claude-code
Open on GitHub

What first-win does

first-win offers three tasks and creates the result in the session. It can reshape a post or a few sentences into social posts written in the author’s voice, or turn a short idea into a plan with an outcome, ordered steps, a first action for today, and a definition of done. The output is ready to use or copy.

The email task picks three priorities for today. It can use a connected inbox, or work from emails and notes pasted into the session. The first two tasks need no extra connections. If there is no source material, the skill can demonstrate the task with a sample post or an idea for a weekly customer email.

What it helps with

  • turn a post or newsletter into social posts
  • break an idea into steps and choose a first action
  • pull three priorities from emails or notes

Example prompts for the agent

  • Run /first-win and turn my latest post into social posts.
  • Run /first-win and make a plan for my idea of a weekly customer email.
  • Run /first-win and pull three priorities from these emails.

How to install first-win

1Skills CLI (Vercel)

npx skills add wrg32786/aigent-os --skill first-win -a claude-code

2Manually: put the files in place

~/.claude/skills/first-win/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/first-win/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about first-win

How do I install first-win in Claude Code?

Run npx skills add wrg32786/aigent-os --skill first-win -a claude-code. The skill file is at ~/.claude/skills/first-win/SKILL.md.

What does first-win do?

It offers three starter tasks: create social posts from existing content, make a structured plan from an idea, or find priorities in email. It produces the artifact in the session.

Does first-win need an inbox connector?

No. For the email task, paste emails or notes into the session instead. A connected inbox is another way to provide the material.

Source text

SKILL.md · MIT
---
name: first-win
description: "Offer three starter tasks that produce usable artifacts. Use when seeking a first win, a day-one task, or something useful to try first."
trigger: /first-win
---

# /first-win: ship something real, today

The operator has just met you (via `/operator-setup`). Now give them proof of work: a real
artifact they can use today. This is what satisfies the "ship something real, fast" promise
on day one, instead of making them wait for a longer pipeline.

## The menu

Offer these three. **Lead with the two zero-dependency tasks** so the win never stalls
waiting on an inbox connection or any login beyond their Claude account:

1. **Turn your last post into a week of social posts.** (zero-dependency, default)
   Ask them to paste their most recent newsletter, blog post, or even a few sentences about
   what they do. Produce five to seven platform-ready posts in their voice, each with a clear
   hook. If they have nothing to paste, use the known-good example below so they still get a
   result.

2. **Turn a rough idea into a structured plan.** (zero-dependency, default)
   Ask for the idea in a sentence. Produce a structured plan: the outcome, the steps in order,
   the first action they can take today, and what "done" looks like. Concrete, not generic.

3. **Today's three priorities from your inbox.** (only if connected)
   If an inbox connector is set up, summarize their inbox into three priorities for today. If
   not, they paste a handful of emails or notes and you do the same thing. **Never block on
   OAuth or a connector.** This task always has the paste-in fallback.

## Delivery

- Produce the artifact directly in the session, formatted cleanly, ready to use or copy.
- Then ask: "Want to tweak it, or save it and move on?" Keep it conversational.

## Known-good example inputs (so a blank-page operator always gets a result)

- For task 1: a short sample post about a local trades bookkeeping practice, which you turn
  into a week of social posts as a demonstration, then offer to redo it with their real
  content.
- For task 2: "I want to start a weekly email for my customers" as the rough idea, which you
  turn into a structured plan.

## Rules
- Every task ends with a real artifact in hand. No "here's how you could do it" without
  actually doing it.
- Plain-English voice. Show the artifact, not a lecture about how to make one.
- No em-dashes. No emoji. No filler.

© wrg32786 · MIT · wrg32786/aigent-os

Similar skills

All skills for Notes, tasks and projects →

From the same set58

The whole set →
learn-from-failure The learn-from-failure Claude Code skill classifies failures and checks whether their causes have appeared before. Repeated problems lead to a durable artifact meant to prevent another recurrence. CX Codex +1 ★ 26repo stars impeccable The impeccable Claude Code skill guides frontend design, helps establish a project’s visual direction, and can extract components and design tokens. It needs context about users, their tasks, and the brand’s tone. CX Codex +1 ★ 26repo stars humanize-docs humanize-docs is a Claude Code skill that transforms robotic documentation into natural prose. It rewrites technical docs and README files by removing repetitive checklists and rigid section structures. CX Codex +1 ★ 26repo stars Honesty Check The Honesty Check Claude Code skill builds an honesty ledger for completed work. It runs before an agent reports a task as done or prepares it for review. CX Codex +1 ★ 26repo stars First 10 Moves First 10 Moves — a Claude Code skill for exploring an unfamiliar repository before changing code. It starts when a task involves tracing a bug, locating a module, or finding a place to begin. CX Codex +1 ★ 26repo stars find-weakness find-weakness — a skill for Claude Code and Codex isolates the single strongest objection and the riskiest unstated assumption in any architectural choice or claim. CX Codex +1 ★ 26repo stars Envelope The Envelope Claude Code skill sorts requests into three actions: proceed, ask one question, or propose a plan first. It activates when an agent must decide whether to act or pause for clarification. CX Codex +1 ★ 26repo stars dream The dream Claude Code skill synthesizes session evidence into lessons and proposed changes. Run it to review recent sessions, consolidate notes, or spot recurring patterns. CX Codex +1 ★ 26repo stars

Project sponsors

Companies that keep this analytics open