Investment Policy logo

Investment Policy

Community
JoelLewis
investment-policy

Construct comprehensive Investment Policy Statements governing return objectives, risk tolerance, and portfolio constraints. Use when the user asks about building an IPS, setting return objectives, assessing risk tolerance, defining investment constraints, or establishing rebalancing and benchmark policies. Also trigger when users mention 'investment plan', 'policy portfolio', 'risk capacity vs willingness', 'spending rate for an endowment', 'foundation payout', 'manager selection criteria', or ask how to document their investment strategy.

Overview

PublisherJoelLewis
Repositoryfinance_skills
Skill nameinvestment-policy
Stars
217
Forks
37
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by JoelLewis on GitHub. Read the source before you install it.

Installation

Install the Investment Policy AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/JoelLewis/finance_skills/tree/main/plugins/wealth-management/skills/investment-policy
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/JoelLewis/finance_skills.git /tmp/finance_skills
mkdir -p .claude/skills
cp -r /tmp/finance_skills/plugins/wealth-management/skills/investment-policy .claude/skills/investment-policy
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Investment Policy in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Investment Policy on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Investment Policy is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Investment Policy Statement Construction

Core Concepts

Investment Policy Statement (IPS)

The IPS is the governing document for all investment decisions. It specifies objectives (return and risk), constraints, asset allocation ranges, rebalancing policy, benchmark selection, and review schedule. Every portfolio action should be traceable back to IPS provisions.

Return Objective

The required return is the rate that funds all future liabilities and goals.

  • Required return: Solve for the discount rate that equates the present value of assets to the present value of future liabilities/spending needs.
  • Spending rate (endowments/foundations): Typically set as a percentage of a rolling average of portfolio value (e.g., 5% of 3-year rolling average AUM). The required nominal return must cover spending + inflation + fees.
    • Required nominal return = spending rate + expected inflation + investment management fees

Risk Tolerance

Risk tolerance has two dimensions that must be assessed independently:

  • Ability (financial capacity): Determined by time horizon, wealth relative to liabilities, income stability, and liquidity needs. Longer horizons and greater surplus increase ability.
  • Willingness (psychological comfort): Determined by behavioral assessment, past responses to losses, and stated preferences.
  • Conflict resolution rule: When ability and willingness conflict, the lower of the two governs. A client with high ability but low willingness should be invested conservatively (with education to potentially raise willingness over time).

Constraints (LLTU+U)

Five categories of constraints must be addressed in every IPS:

  • Liquidity: Anticipated cash needs, emergency reserves, near-term spending requirements
  • Legal/Regulatory: ERISA rules, trust provisions, foundation payout requirements, prudent investor standards
  • Time horizon: Single-stage or multi-stage; longer horizons generally permit more risk
  • Tax: Taxable vs tax-deferred vs tax-exempt status; impact on asset allocation and rebalancing
  • Unique circumstances: ESG/SRI restrictions, concentrated stock positions, employer stock, legacy holdings, personal preferences

Asset Allocation Policy

Strategic Asset Allocation (SAA) defines long-term target ranges:

  • Example ranges: equity 50-70%, fixed income 20-40%, alternatives 0-15%
  • Ranges permit tactical tilts within policy bounds
  • Policy allocation is the primary driver of long-term returns (commonly cited as explaining ~90% of return variability across time)

Rebalancing Policy

Specifies when and how the portfolio is brought back to target weights:

  • Calendar-based: Rebalance at fixed intervals (quarterly, semi-annually)
  • Threshold-based (percentage-of-portfolio): Rebalance when any asset class drifts beyond a specified band (e.g., ±5% absolute)
  • Combined: Check at calendar intervals, rebalance only if thresholds are breached
  • Wider bands reduce transaction costs but allow more drift; narrower bands maintain discipline but increase costs

Benchmark Selection

An appropriate benchmark must be:

  • Investable: Represents a viable passive alternative
  • Measurable: Returns can be calculated on a timely basis
  • Specified in advance: Chosen before the evaluation period, not after
  • Appropriate: Matches the portfolio's asset classes, style, and risk profile
  • Owned by the manager: The manager should agree the benchmark is fair

Manager Selection Criteria (The Five Ps)

  • Philosophy: Clear, coherent investment belief system
  • Process: Systematic, repeatable approach consistent with philosophy
  • People: Experienced, stable team with aligned incentives
  • Performance: Track record evaluated against appropriate benchmark over full market cycles
  • Price: Fees competitive relative to peers and value added

Review Schedule

  • Annual IPS review: Reassess objectives, constraints, and circumstances
  • Quarterly performance review: Evaluate returns, attribution, and benchmark comparison
  • Trigger-based review: Major life events, market dislocations, or material changes in circumstances

Key Formulas

FormulaExpressionUse Case
Required nominal returnR_nom = spending_rate + inflation + feesEndowment/foundation return target
Required return (goal-based)Solve: PV(assets) = Σ [CF_t / (1+R)^t]Individual required return
Real return from nominalR_real ≈ R_nom - inflationConverting between real and nominal
Spending amount (rolling avg)Spend = rate × (1/3)(AUM_t + AUM_{t-1} + AUM_{t-2})Endowment annual distribution
Rebalancing triggerw_actual - w_target

Worked Examples

Example 1: IPS for a 45-year-old pre-retiree

Given: Age 45, current portfolio $2M, needs $100K/year (today's dollars) starting at age 65, life expectancy 90, inflation 2.5%, portfolio fees 0.5%. Calculate: Required nominal return and the resulting allocation guidance. Solution:

  1. Time horizon: 20 years to retirement + 25 years in retirement = two-stage horizon.
  2. At retirement, need $100K × (1.025)^20 = $163,862/year in nominal terms.
  3. Required nest egg at 65 (25-year payout, assuming the retirement portfolio earns ~5% real, roughly 7.5% nominal at 2.5% inflation): the inflation-growing withdrawals are a level annuity in real terms, so N = $163,862 × [1 - 1.05^(-25)] / 0.05 = $163,862 × 14.094 ≈ $2.31M (in age-65 dollars).
  4. Required return (no additional contributions): solve $2M × (1+R)^20 = $2.31M → R = (2.31/2.0)^(1/20) - 1 ≈ 0.7% nominal net of fees (≈1.2% gross adding the 0.5% fee). That is below the 2.5% inflation assumption — the required real return is roughly -1.7%.
  5. If the client also contributes $30K/year, the required return falls to essentially zero. Return needs alone do not compel an equity-heavy portfolio.
  6. Allocation logic: ability to take risk is high (20-year accumulation horizon, assets large relative to the goal), so willingness governs the choice within a wide acceptable range. The required return is modest, but a 45-year total horizon, longevity beyond age 90, and inflation risk argue for substantial equities; if willingness is moderate, a 60/40 allocation is comfortable, and the client could de-risk to 40/60 and still expect to meet the goal. Document in the IPS that the equity allocation is held for inflation protection and longevity risk, not because the return target demands it.

Example 2: Endowment spending policy

Given: $50M endowment, 5% spending rule on 3-year rolling average, expected inflation 2.5%, investment fees 0.5%. Calculate: Required nominal return to maintain real value. Solution:

  1. Annual spending = 5% × $50M = $2.5M (assuming stable AUM at $50M).
  2. To maintain purchasing power, the endowment must grow by at least inflation: 2.5%.
  3. Required nominal return = spending rate + inflation + fees = 5.0% + 2.5% + 0.5% = 8.0%.
  4. This implies a growth-oriented allocation (e.g., 70% equity, 20% fixed income, 10% alternatives).
  5. If 8% seems aggressive, the board may need to reduce spending rate or accept gradual real erosion.

Common Pitfalls

  • Setting return objectives higher than risk tolerance allows — the return target must be achievable within the risk budget
  • Ignoring inflation in required return calculations — understating the true return hurdle
  • Not revisiting the IPS when circumstances change — life events, market regimes, and regulatory changes demand updates
  • Confusing risk ability with risk willingness — they are separate assessments and must be reconciled
  • Setting constraints too rigid (reduces flexibility and increases costs) or too loose (provides no discipline)
  • Choosing benchmarks after the fact to make performance look better
  • Ignoring the interaction between constraints (e.g., tax considerations affecting asset allocation ranges)

Cross-References

  • tax-efficiency (wealth-management plugin): asset location and withdrawal sequencing affect IPS constraint section
  • performance-attribution (wealth-management plugin): benchmark selection in IPS directly feeds performance evaluation
  • liquidity-management (wealth-management plugin): liquidity constraint in IPS depends on cash flow analysis
  • savings-goals (wealth-management plugin): return objectives often derived from goal-based planning
  • emergency-fund (wealth-management plugin): emergency reserve requirement feeds into IPS liquidity constraint
  • client-review-prep (advisory-practice plugin): IPS provides the reference framework for evaluating drift and suitability during reviews
  • financial-planning-workflow (advisory-practice plugin): the financial plan informs and is codified in the investment policy statement
  • tax-loss-harvesting (wealth-management plugin): IPS may specify TLH policy parameters (minimum loss threshold, approved replacement pairs)
  • estate-gifting (wealth-management plugin): trust structures and multi-generational transfer objectives feed the IPS legal/regulatory and time-horizon constraints
  • retirement-decumulation (wealth-management plugin): the IPS spending policy documents the withdrawal rate, guardrail rules, and rebalancing discipline used in decumulation

Frequently asked questions

What does the Investment Policy AI skill do?

Construct comprehensive Investment Policy Statements governing return objectives, risk tolerance, and portfolio constraints. Use when the user asks about building an IPS, setting return objectives, assessing risk tolerance, defining investment constraints, or establishing rebalancing and benchmark policies. Also trigger when users mention 'investment plan', 'policy portfolio', 'risk capacity vs willingness', 'spending rate for an endowment', 'foundation payout', 'manager selection criteria', or ask how to document their investment strategy.

Why use Investment Policy on TypingMind?

Because you install it once and use it with any model. Investment Policy is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Investment Policy in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JoelLewis/finance_skills/tree/main/plugins/wealth-management/skills/investment-policy. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Investment Policy?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Investment Policy?

As many as you like. As long as a model supports skills, you can use Investment Policy with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Investment Policy AI skill free?

Yes. It is published on GitHub by JoelLewis under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇