Context Engineering Advisor
技能 已验证 活跃Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
To help product managers and AI practitioners diagnose and fix issues related to context stuffing in AI workflows, leading to more efficient, reliable, and higher-quality AI outputs.
功能
- Diagnose context stuffing vs. context engineering
- Identify context boundaries and architectural issues
- Guide implementation of tactical context practices
- Prevent context rot in AI workflows
- Promote efficient token usage and AI attention allocation
使用场景
- My AI outputs are mediocre even though I'm giving it lots of information — diagnose what's wrong
- I want to architect context properly for a multi-step AI workflow in my product team
- My AI workflow feels bloated, brittle, or hard to steer reliably
- I suspect I'm 'context stuffing' but don't know how to fix it
非目标
- Choosing specific AI tools (e.g., Claude vs. ChatGPT)
- Writing better prompts (focus is on information architecture)
- Adding more tokens or pursuing 'infinite context' narratives
- Replacing human judgment; instead, amplifying it
工作流
- Gather context about current AI usage and symptoms.
- Diagnose context stuffing via key symptoms and 5 diagnostic questions.
- Define memory architecture (short-term vs. long-term, retrieval strategy).
- Implement the Research → Plan → Reset → Implement cycle.
- Synthesize an action plan and define next steps.
实践
- Context Design
- AI Workflow Architecture
- Information Architecture
安装
请先添加 Marketplace
/plugin marketplace add deanpeters/Product-Manager-Skills/plugin install context-engineering-advisor@pm-skills质量评分
已验证类似扩展
Context Engineering
98Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.
Ops Yolo
100YOLO mode. Spawns 4 parallel C-suite agents (CEO, CTO, CFO, COO). Each analyzes the business from their perspective using ALL available data. Produces unfiltered Hard Truths report. After user types YOLO, autonomously runs the business for a day using /loop.
Context Optimization
100This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.
Context Compression
100This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Init
100创建或优化存储库的 AGENTS.md 文件，提供最少、高信号的说明，涵盖代理无法从代码库推断的不可发现的编码约定、工具怪癖、工作流偏好和项目特定规则。在为新存储库设置代理说明或 Claude 配置时，当现有的 AGENTS.md 文件过长、通用或过时，当代理反复犯可避免的错误，或当存储库工作流发生变化且需要修剪代理配置时使用。应用可发现性过滤器—省略 Claude 可从 README、代码、配置或目录结构中学到的任何内容—并应用质量门，以验证每行是否仍然准确且具有操作意义。
Drive Motivation
100Design motivation systems using Autonomy, Mastery, and Purpose (AMP) for products and teams. Use when the user mentions "intrinsic motivation", "gamification isnt working", "team incentives", "autonomy", "mastery", "purpose-driven", "employee engagement", or "reward systems". Also trigger when designing onboarding progression systems, fixing broken gamification, or building team structures that sustain high performance. Covers why carrot-and-stick fails and how to build progress systems. For habit-forming product loops, see hooked-ux. For retention behavior design, see improve-retention.