context-engineering-advisor — Claude Code skill: how to install
An interactive advisor that pinpoints why agent workflows degrade under heavy prompts and helps structure memory retrieval.
npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor -a claude-codeWhat context-engineering-advisor 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.
What it helps with
- 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 for the agent
- 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.
How to install context-engineering-advisor
1Skills CLI (Vercel)
npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor -a claude-code2Manually: put the files in place
~/.claude/skills/context-engineering-advisor/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/context-engineering-advisor/
1Skills CLI (Vercel)
npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor -a codex2Manually: put the files in place
.agents/skills/context-engineering-advisor/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor -a cursor2Manually: put the files in place
.cursor/skills/context-engineering-advisor/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install deanpeters/Product-Manager-Skills context-engineering-advisor2Manually: put the files in place
.github/skills/context-engineering-advisor/SKILL.md1Skills CLI (Vercel)
npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor -a gemini-cli2Platform CLI
gemini skills install https://github.com/deanpeters/Product-Manager-Skills --path skills/context-engineering-advisorManually: put the files in place
.devin/skills/context-engineering-advisor/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about context-engineering-advisor
How do I install context-engineering-advisor in Claude Code?
Run npx skills add deanpeters/Product-Manager-Skills --skill context-engineering-advisor -a claude-code. The skill file is placed in ~/.claude/skills/context-engineering-advisor/SKILL.md.
What does context-engineering-advisor do?
It assesses prompt workflows that feel brittle or bloated, diagnosing context hoarding patterns and helping you replace brute-force token dumps with targeted retrieval.
How long does a diagnostic session take?
The interactive consultation typically takes between 15 and 20 minutes.