# context-engineering-advisor

An interactive advisor that pinpoints why agent workflows degrade under heavy prompts and helps structure memory retrieval.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2700 installs · ★ 7673
- Author: deanpeters
- License: CC-BY-SA-4.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/deanpeters/Product-Manager-Skills/tree/HEAD/skills/context-engineering-advisor/SKILL.md
- Updated: 2026-10-16
- HTML: https://affpapa.org/en/nevibecode/skills/context-engineering-advisor

## What it does

This skill runs an interactive consultation lasting 15 to 20 minutes to audit struggling AI pipelines. It targets setups where models hallucinate, misroute requests, or depend on repeated retries. Instead of dumping massive raw files into the prompt, the advisor identifies why excessive token volume harms outputs and points out missing structural boundaries between agents.

Attention is treated as a finite asset. When prompt size passes 32k tokens, reasoning accuracy drops sharply because models overlook intermediate details amid background clutter. The advisor suggests replacing full-document persistence with focused retrieval, compact information density, and a clear separation between immediate session state and persistent vector storage. Passing unstructured context across chained agents without strict boundaries guarantees compounding errors.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/context-engineering-advisor/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/context-engineering-advisor/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/context-engineering-advisor/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/context-engineering-advisor/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install deanpeters/Product-Manager-Skills context-engineering-advisor
```

2. **Manually: put the files in place**
- File: `.github/skills/context-engineering-advisor/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/deanpeters/Product-Manager-Skills --path skills/context-engineering-advisor
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/context-engineering-advisor/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/deanpeters/Product-Manager-Skills/tree/HEAD/skills/context-engineering-advisor/SKILL.md

## When to use it
- isolate prompt bloat in multi-agent pipelines
- set up two-layer memory dividing session history from vector storage
- stop accuracy degradation in prompts exceeding 32k tokens
- define context boundaries between chained agents

## Example prompts
- Diagnose my setup: our triage agent gets the complete policy document per request and still misroutes edge cases.
- Help me design context boundaries for a multi-step agent pipeline.

## Similar
- [setup-matt-pocock-skills](https://affpapa.org/en/nevibecode/skills/setup-matt-pocock-skills.md) — skill · 1052851 installs
- [ask-matt](https://affpapa.org/en/nevibecode/skills/ask-matt.md) — skill · 766587 installs
- [to-tickets](https://affpapa.org/en/nevibecode/skills/to-tickets.md) — skill · 711230 installs
- [writing-plans](https://affpapa.org/en/nevibecode/skills/writing-plans.md) — skill · 282859 installs
- [caveman-review](https://affpapa.org/en/nevibecode/skills/caveman-review.md) — skill · 411800 installs
- [caveman-compress](https://affpapa.org/en/nevibecode/skills/caveman-compress.md) — skill · 411500 installs

From the same set: [deanpeters/product-manager-skills](https://affpapa.org/en/nevibecode/by/deanpeters/product-manager-skills.md) — 73 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md