Skip to main content
skill CX Codex

exec-summary — Claude Code skill: a 1–2 page feature summary

Turns a feature folder into one 600–800 word document: a sales pitch, a leadership brief and a behavioral overview for engineering.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add mvschwarz/openrig --skill exec-summary -a claude-code
Open on GitHub

What exec-summary does

The skill reads SPEC.md, background.md, validation.md and the ASCII mockups in supporting/, then writes executive-summary.md into the feature folder. Everything is in present tense, as if the feature already shipped. The outline is fixed: problem, solution, audience, why now, how it works, key decisions, visual preview, what you are not building, dependencies, success metrics and a FAQ split by audience.

Two sections carry the weight. Key Decisions asks for non-obvious business rules, not the ones everyone already knows. What We're NOT Building wants out-of-scope items with a short reason. The skill pulls only from those feature files, so a folder without them gives it nothing to work from. Core content is capped at two pages, with the FAQ allowed a third.

Handy when a feature is ready for development and sales or leadership keeps asking what it actually does. One file instead of three retellings.

What it helps with

  • write one feature document for sales, leadership and engineering
  • pin down non-obvious business rules before development starts
  • list out-of-scope items with reasons to avoid later arguments
  • show cross-feature dependencies and shipping order
  • answer recurring feature questions without scheduling a call

Example prompts for the agent

  • Generate an executive summary for the feature in billing-export
  • Write executive-summary.md from this feature's SPEC.md and background.md
  • Summarize this feature: problem, solution, key decisions and what we're not building

How to install exec-summary

1Skills CLI (Vercel)

npx skills add mvschwarz/openrig --skill exec-summary -a claude-code

2Manually: put the files in place

~/.claude/skills/exec-summary/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/exec-summary/

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

Questions about exec-summary

How do I install exec-summary in Claude?

Run npx skills add mvschwarz/openrig --skill exec-summary -a claude-code. The skill file lands at ~/.claude/skills/exec-summary/SKILL.md.

What does exec-summary do?

It reads the feature files and writes a 600–800 word executive-summary.md: problem, solution, audience, key decisions, out-of-scope, dependencies, metrics and a FAQ for sales, leadership and engineering.

Which files does the skill need?

SPEC.md, background.md, validation.md and the ASCII mockups in supporting/. Without them there is no context to summarize.

Source text

SKILL.md · Apache-2.0
---
name: exec-summary
description: "Generate a 1-2 page executive summary for a feature — orients sales, leadership, and engineering from a single document."
---

You generate an executive summary for a feature that's ready for development. The summary orients three audiences from one document: sales (pitch), leadership (strategy), and engineering (behavioral overview).

## What You Produce

A single `executive-summary.md` file in the feature folder. 600-800 words excluding mockups and FAQ. Written in present tense as if the feature already exists.

## Sources to Read

Before writing, silently gather all context from the feature folder:

1. **SPEC.md** — acceptance criteria, business rules, scope, user stories
2. **background.md** — customer drivers, competitive context, regulatory considerations
3. **validation.md** — demand evidence, status quo, desperate user, narrowest wedge
4. **supporting/mockup-ascii.md** — visual mockups (pull 2-3 key screens)

## Output Structure

```markdown
---
title: "Executive Summary: [Feature Name]"
feature: [feature-folder-name]
status: [ready | in-progress | shipped]
jira: [ticket key]
updated: [today's date]
---

# [Feature Name]

## The Problem
[2-3 sentences. Customer pain in their language. Name real customers/prospects.]

## The Solution
[2-3 sentences. What we built, present tense. No jargon.]

## Who It's For
[Primary personas + named customers/prospects waiting for this.]

## Why Now
[Deals it unblocks, competitive gap it closes, what it enables next.]

## How It Works
[5-8 key capabilities. Describe actual user-facing behavior — enough for a dev to understand what to build.]

## Key Decisions
[5-8 non-obvious business rules and design choices. Focus on surprising or counter-intuitive ones.]

## Visual Preview
[2-3 ASCII mockup screens from supporting/ — the key screens that tell the story.]

## What We're NOT Building
[5-8 key out-of-scope items with brief reason.]

## Dependencies & Sequencing
[What must ship first. Cross-feature dependencies. Prerequisites.]

## Success Metrics
[2-4 measurable outcomes. Mix of usage and business metrics.]

## FAQ

### For Sales
[2-3 questions. When available, what to tell prospects, competitive positioning.]

### For Leadership
[2-3 questions. Opportunity cost, strategic fit, risks.]

### For Engineering
[2-3 questions. Dependencies, known risks, what's deferred, data model implications.]
```

## Writing Guidelines

- **Present tense throughout.** Write as if the feature exists.
- **Customer-readable language.** A prospect should understand sections 1-5.
- **Be specific, not vague.** Name deals, dollar amounts, competitors.
- **Key Decisions should surprise.** Don't list obvious things.
- **Mockups are curated.** Pick the 2-3 that tell the story.
- **FAQ answers should be direct.** No hedging.
- **Hard cap: 2 pages** for core content. FAQ can be a third page.

© mvschwarz · Apache-2.0 · mvschwarz/openrig

Similar skills

Everything for Writing and docs →

From the same set14

agent-operated-software A skill for designing and debugging applications whose live backend or control loop includes OpenRig agents. CX Codex +1 ★ 8,172repo stars context-engineering A skill about how an agent's context window gets filled, pruned and shared. Useful when an agent drifts or forgets constraints mid-task. CX Codex +1 ★ 8,172repo stars orchestration-team An orchestration skill: it splits work into assignments, dispatches them, and watches for idle or blocked agents instead of doing the implementation itself. CX Codex +1 ★ 8,172repo stars requirements-writer Talks a product manager through rough feature notes and turns them into a single SPEC.md with observable acceptance criteria and explicit scope. CX Codex +1 ★ 8,172repo stars watchdog A skill for configuring rig watchdog policies: it picks the right intervention when an agent goes idle, drifts, or needs a checkpoint. CX Codex +1 ★ 8,172repo stars session-source-fork A skill for authoring rig specs: it starts a new managed seat from a prior Claude or Claude conversation without claiming the old seat continued. CX Codex +1 ★ 8,172repo stars openrig-upgrade Walks an agent through an OpenRig CLI and daemon upgrade one step at a time: inspect, mutate, observe. Useful when live seats matter. CX Codex +1 ★ 8,172repo stars messaging-the-human This skill covers the mechanics of an agent messaging a human through rig: filing a decision request or a quiet update, then handling the reply. CX Codex +1 ★ 8,172repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor