context-engineering-advisor
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Diagnose context stuffing versus context engineering in AI workflows. It helps determine whether the current setup uses unbounded context or structured, bounded context, and guides the user to implement practices like bounded domains, episodic retrieval, and a Research→Plan→Reset→Implement cycle.
How it works
The skill provides an interactive diagnostic flow:
- Step 0: Gather Context by asking for current AI usage, tasks, context provision, symptoms, and system architecture.
- Step 1: Diagnose Context Stuffing Symptoms by listing observed issues (e.g., pasting entire documents, vague responses, retries, escalating token costs, unbounded agent handoffs) and selecting those that apply.
- Step 2: Diagnostic Question 1 — For each piece of context, determine the specific decision it supports; recommends articulating that decision and trimming non-essential context.
- Step 3: Diagnostic Question 2 — Assess whether information should be persisted or retrieved on-demand, with guidance to implement just-in-time retrieval and a constraints/registry approach.
- Step 4: Diagnostic Question 3 — Determine ownership of the context boundary (solo PM, collaborative team, or unowned) and propose artifacts like a Context Manifest and boundary criteria.
- It references the Protocols from workshop-facilitation and uses an interactive questioning pattern with concrete recommendations.
When to use it
Use when AI outputs are bloated, brittle, or hard to steer; when you paste entire docs and still get vague results; or when you need to design memory and retrieval architecture for an AI product feature. Do not use if you are just getting started and need basic prompts or tool recommendations.
What it can touch
The skill interfaces with an interactive workflow and references tools and conventions from workshop-facilitation. It requires no direct code execution Sunken in the description, but it guides interactions and decisions around context management, retrieval orchestration, and boundary ownership.
Caveats
Licensed as NOASSERTION per the repository; the description emphasizes architecture over prompts and tooling, and advises domain-specific interaction protocols via workshop-facilitation. No explicit tool integration beyond the stated Claude Code tool in the declared tools.
## Purpose Guide product managers through diagnosing whether they're doing **context stuffing** (jamming volume without intent) or **context engineering** (shaping structure for attention). Use this to identify context boundaries, fix "Context Hoarding Disorder," and implement tactical practices like bounded domains, episodic retrieval, and the Research→Plan→Reset→Implement cycle. **Key Distinction:** Context stuffing assumes volume = quality ("paste the entire PRD"). Context engineering treats AI attention as a scarce resource and allocates it deliberately. This is not about prompt writing—it's about **designing the information architecture** that grounds AI in reality without overwhelming it with noise. ## Input **Works best with:** A description of the AI workflow, agent, or prompt setup that feels bloated, brittle, or hard to steer. **Also useful:** What you've already stuffed into context (docs, transcripts, schemas) and where outputs go wrong. Anything supplied with the invocation itself — text after the skill name, a pasted context dump, or an appended `ARGUMENTS:` line — counts as answers already given. Use it and skip whatever it covers; don't re-ask. **Arriving empty-hand
- Purpose
- Input
- Key Concepts
- The Paradigm Shift: Parametric → Contextual Intelligence
- Context Stuffing vs. Context Engineering
- The Anti-Pattern: Context Stuffing
- Real Context Engineering: Core Principles
- The 5 Diagnostic Questions (Detect Context Hoarding Disorder)
- Memory Architecture: Two-Layer System
- The Research → Plan → Reset → Implement Cycle
- Anti-Patterns (What This Is NOT)
- When to Use This Skill
- Facilitation Source of Truth
- Application
What does the context-engineering-advisor skill do?
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
How do I install it?
Run `npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From deanpeters/Product-Manager-Skills, a repository with 6,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.