CG Pension Planning Hub
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md and install @user_88e00a20/chengeng-pension-planning.
About this skill
The Problem
Pension planning is often split into estimate benefits, model cash flow, close the gap, and design the solution, but real execution usually fails on unclear stage routing, missing fields, and manual calculation drift: a client may ask about social security balances, retirement living costs, and asset transfers at the same time, and an LLM can present estimates as conclusions or collapse four stages into one long report.
How It Works
This skill acts as the entry point for the four-step pension workflow and focuses on stage detection, data validation, and orchestration:
- Routes prompts to chengeng-pension-basic-estimate, chengeng-pension-lifestyle-cashflow, chengeng-pension-source-gap, or chengeng-pension-solution-design.
- Checks required inputs such as age, social security base, contribution years, personal account balance, retirement lifestyle standard, fixed income sources, and pension-eligible assets.
- When data is sufficient, it prefers the built-in scripts/ calculation pipeline; numbers should follow script output, while LLM arithmetic is only for cross-checking and interpretation.
- After each step, key conclusions are explicitly passed to the next step, and the default deliverable is four staged reports, with a summary report only as a backup.
Boundaries
It does not promise actuarial results, recommend specific products, or invent wage anchors, CPI, income, contribution years, or account balances. If key fields are missing, it should list confirmation items first; if scripts are unavailable, it must mark the output as a manual calculation without script cross-validation.
Use Cases
- When a client asks about retirement readiness, decide whether to start with benefit estimation, cash flow, gap, or solution design
- When inputs are incomplete, list missing fields such as social security location, contribution years, account balance, and living costs
- During full pension planning, produce four staged reports and pass each step's key conclusions to the next stage
- If local scripts cannot run, label the output as manually calculated and avoid presenting estimates as confirmed client data
Best For
- Wealth advisors who need to classify a client's retirement inquiry and collect missing fields
- Financial planners who need to split pension estimates, cash flow, gap, and design into staged reports
- AI application engineers who need to orchestrate multiple pension step skills into a four-stage workflow
- Individual users planning retirement cash flow who need stepwise field checks and less manual calculation drift
Related Skills
Local workflow memory with matching and SOP updates.
An OpenClaw live streaming executor that initializes TRTC streaming, starts a real-time dashboard, generates viewer URLs, and continuously reports live events.
Breaks down physical supply chains for super-trends to identify second- and third-layer bottlenecks, runs valuation and reverse checks, and maintains trackable reports.
A token-saving compression mode for Chinese LLMs with lite, full, ultra, and classical tiers, preserving code and technical terms while handling edge cases.