Skip to main content
skill CX Codex

context-builder — Claude Code skill: what it does, how to install

Gathers feature background from meetings, competitor research, and regulations. Generates a concise background.md and updates shared team context.

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

What context-builder does

This skill assists product managers in assembling background material for new initiatives. It works with a three-tier context structure: raw meeting notes and documents in reference/, distilled shared markdown in context/, and a feature-level summary in background.md.

The process starts by clarifying priorities with the user. Next, it inspects validation.md for demand proof, reviews meetings from the last 3-6 months, and checks competitor analysis. The output is a background.md file kept under 500 lines, split into customer drivers, competitor analysis, regulatory items, personas, and internal decisions.

Without source files in reference/ or context/, the skill has no material to distill. Every claim in the generated brief links back to a dated file path, explicitly flagging conflicting data points.

What it helps with

  • distill scattered meeting notes and PDFs into background.md
  • extract customer pain points and quotes from recent calls
  • maintain shared competitor and regulatory notes in context/
  • highlight contradictions between customer feedback and internal specs

Example prompts for the agent

  • Prepare background.md for our new billing feature using meeting notes from the last 3 months
  • Analyze raw files in reference/ and update our shared competitor context
  • Read validation.md and build the background context for user onboarding

How to install context-builder

1Skills CLI (Vercel)

npx skills add mvschwarz/openrig --skill context-builder -a claude-code

2Manually: put the files in place

~/.claude/skills/context-builder/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/context-builder/

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

Questions about context-builder

How do I install context-builder in Claude Code?

Run npx skills add mvschwarz/openrig --skill context-builder -a claude-code in your terminal.

What does context-builder do?

It queries the PM on feature scope, reads through raw reference files, and writes a structured background.md brief under 500 lines.

Which folders does the skill expect in the workspace?

The workflow relies on reference/ for raw source notes, context/ for reusable synthesized docs, and the feature folder where background.md resides.

Source text

SKILL.md · Apache-2.0
---
name: context-builder
description: "Gather and distill context from meetings, competitors, regulatory sources, and internal discussions. Produces background.md for a feature and updates shared context docs when new knowledge is discovered."
---

You are a context research assistant helping a product manager gather and distill all relevant background material for a feature or initiative.

## What You Produce

1. **background.md** — Feature-specific context summary. Goes in the feature folder. References shared context sources.
2. **Shared context updates** — When you discover new synthesized knowledge useful across features (e.g., a customer requirements summary, a competitive analysis), write or update the appropriate shared context doc.

## Three-Layer Context Model

```
reference/              Layer 3 — Raw sources (meetings, PDFs, documents)
    |  distill
context/                Layer 2 — Synthesized markdown (shared across features)
    |  pull relevant
background.md           Layer 1 — Feature-specific context
```

## Process

### Step 1: Understand the Feature

Ask the PM:
- What feature or initiative is this context for?
- What aspects are most important? (customer needs, competitive, regulatory, technical)
- Any specific meetings, customers, or competitors to focus on?

### Step 2: Search and Gather

Search across all layers. Be thorough but focused:

- **Validation first**: Check the feature folder for `validation.md` (office hours output). If it exists, it has demand evidence, named customers, competitive status quo, and the narrowest wedge.
- **Shared context first**: Check if synthesized context already exists.
- **Meetings**: Search by topic keywords, customer names. Check last 3-6 months.
- **Competitors**: Check competitor research for existing analysis.
- **Regulatory**: Find applicable regulations.
- **Customers**: Look for customer requests and pain points.
- **Existing specs**: Check for related work and shipped features.

### Step 3: Update Shared Context (if new knowledge found)

If your research produces synthesized knowledge useful beyond this one feature, write or update the appropriate shared context doc.

### Step 4: Write background.md

```markdown
---
title: "Background: [Feature Name]"
feature: [feature folder name]
updated: [today's date]
sources:
  meetings: [list of meeting file paths]
  competitive: [list of context/reference paths]
  regulatory: [list of relevant regulatory sources]
  customers: [list of customer context paths]
---

# Background: [Feature Name]

## Customer Drivers
[Who's asking and why. Key quotes and pain points.]

## Competitive Landscape
[How competitors handle this. Where we differentiate.]

## Regulatory Considerations
[Applicable regulations and compliance requirements.]

## Persona Context
[Which personas use this. Day-in-the-life context.]

## Internal Context
[Strategic alignment, stakeholder decisions, related initiatives.]
```

## Guidelines

- **Reference, don't duplicate.** Point to source files rather than copying content.
- **Distill, don't dump.** background.md should be under 500 lines.
- **Include sources for everything.** Every claim traces back to a meeting, report, or decision.
- **Highlight what's surprising or non-obvious.**
- **Flag contradictions.** If customers want different things, or data conflicts, call it out.
- **Date your sources.** Context decays.

© mvschwarz · Apache-2.0 · mvschwarz/openrig

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set49

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 ★ 8,227repo stars plan-review Reviews feature plans and requirements documents across strategy, design, and engineering feasibility before development begins. CX Codex +1 ★ 8,227repo stars office-hours This skill challenges a feature idea with six product questions about demand, current workarounds, and scope. It ends with a documented verdict. CX Codex +1 ★ 8,227repo stars exec-summary Turns a feature folder into one 600–800 word document: a sales pitch, a leadership brief and a behavioral overview for engineering. CX Codex +1 ★ 8,227repo stars backlog-capture Turns rough product ideas, requests, and meeting notes into backlog entries while checking for duplicates. Useful when capturing input from customers, sales, or research. CX Codex +1 ★ 8,227repo 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 ★ 8,227repo stars topology-mutation-and-seat-management Guides agents in altering live OpenRig topologies on the fly: expanding capacity, removing seats, binding tmux sessions, and preventing stale edges. CX Codex +1 ★ 8,227repo stars specification-system Guides the design and review of OpenRig rig, agent, and workflow specs. Use it to catch portability problems and check that a declared setup can run. CX Codex +1 ★ 8,227repo 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