agentleFS
camrontaylorcamrontaylor/AI-OS-Template/.claude/skills/fin-personal-cfo/SKILL.md

fin-personal-cfo

Skill0 starsChanged 46 days agoMITView on GitHub

Model household financial choices and compare scenarios with disclosed inputs and sensitivity. Use for "house math", "rental forecast", "renovation budget", "monthly cash flow", "big purchase", or "savings what-if". Includes a detailed housing template and general scenario methods. Company books belong in fin-company-cfo; this skill provides scenario analysis and never executes purchases, loans, investments, or tax filings.

The file

Show its rules and text

We split this skill into the rules it gives an agent

17 rules. About 0 are common, 8 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the linked skills only if installed.

    line 36
  2. Very specific:

    Keep durable source pointers with the dated project report.

    line 38
  3. Very specific:

    Read relevant assets/ examples if present.

    line 44
  4. Very specific:

    Use references/templates/house.md for housing.

    line 48
  5. Distinctive:

    Read the detailed method for this step’s mechanics and output shape.

    line 49
  6. Very specific:

    Read references/calculators.md.

    line 58
  7. Distinctive:

    Write comparison, assumption ledger, detailed report, and unresolved questions.

    line 63
  8. Very specific:

    Create projects/fin-personal-cfo/{YYYY-MM-DD}_{name}/ in the selected workspace.

    line 68
  9. Very specific:

    Verify factual/source coverage, schema, calculations, destination fit, and links as appropriate.

    line 70
  10. Very specific:

    Ask for feedback after major deliverables.

    line 76
  11. Distinctive:

    Read Rules and local overrides before every Solo run.

    line 82
  12. Distinctive:

    Check actual connector/CLI availability and authentication.

    line 83
  13. Distinctive:

    Never send, post, schedule publication, purchase, or push to a remote merely because a source example shows it.

    line 84
  14. Distinctive:

    Keep base definitions immutable during ordinary use.

    line 85
  15. Distinctive:

    No financial transactions or filings.

    line 86
  16. Distinctive:

    Use current sourced evidence or clearly disclosed assumptions, never fabricated rates or comps.

    line 87
  17. Very specific:

    Create the local override if absent.

    line 92

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Personal CFO Scenarios

An AI-OS capability with scoped context, local configuration, and reviewable outputs.

Outcome

Dated input data, auditable calculations, a scenario comparison, and sensitivity report. Save deliverables to projects/fin-personal-cfo/{YYYY-MM-DD}_{name}/ with dated filenames. Knowledge skills also maintain their scoped raw/wiki corpus; integration and authoring skills may modify the explicitly selected project.

Context Needs

FileLoad levelPurpose
context/learnings.md## fin-personal-cfo onlyFeedback for this skill
context/learnings.mdRelevant General entriesCross-skill corrections
context/config/fin-personal-cfo/Relevant files if presentUser-owned settings
Adjacent SKILL.local.mdFull if presentUser overrides; take precedence

Dependencies

SkillRequired?What it providesWithout it
str-deep-researchOptionalVerify current rates, rents, and comparable evidenceUse disclosed user-supplied assumptions
str-decideOptionalRecord the eventual choicePresent cash/lifestyle tradeoffs
tool-humanizerOptional for publishable proseEditorial gateNatural-language, voice, factual-claim checklist

Skill Relationships

Use the linked skills only if installed; check their SKILL.md and local overrides before invoking. Consume related source artifacts without duplicating their workflow. Keep trigger boundaries stated in the description. Keep durable source pointers with the dated project report. Use meta-memory-write only when the user asks to remember a concise working fact; full research and financial records stay in project files.

Step 1: Load scope and corrections

Check the runtime before reading local context. With Team connected, the authoritative workspace snapshot supplies context and feedback; do not read or write local brand_context, context, or learnings. Use its configured output/feedback mechanisms and report a missing snapshot instead of a local fallback. In Solo mode, resolve the AI-OS root or explicitly active client and read only that scope’s listed brand files, this skill’s learnings, relevant General feedback, and local override. In Solo mode, resolve user configuration as ${AI_OS_SKILL_CONFIG_DIR:-context/config}/fin-personal-cfo/ relative to that workspace; do not reuse another client’s settings. Read relevant assets/ examples if present; use the output template until an approved example exists.

Step 2: Select scenario and gather inputs

Use references/templates/house.md for housing. Other modes—refi, cash flow, big purchase, side income, savings—use the general calculator methods and a task-specific schema, not nonexistent templates. Establish jurisdiction, currency, horizon, income, liabilities, costs, and provenance for each input. Read the detailed method for this step’s mechanics and output shape.

Step 3: Build realistic comparisons

For housing compare baseline, accessory unit, bedroom rentals, combinations, and staged rentals when relevant. Include closing cash, renovations, vacancy, owner-paid utilities, fees, taxes, insurance, and personal comfort. Let the user’s property and lifestyle determine the actual scenario set. Read the detailed method for this step’s mechanics and output shape.

Step 4: Calculate and audit

Read references/calculators.md. Compute debt service, monthly/annual net costs, initial cash, paydown, and alternative-return scenarios. Use consistent units and distinguish nominal versus real returns. Tax effects are jurisdiction-dependent estimates, not automatic US deductions. Test vacancy, rent, rates, maintenance, renovation overruns, and returns. Read the detailed method for this step’s mechanics and output shape.

Step 5: Present sensitivity and decision inputs

Write comparison, assumption ledger, detailed report, and unresolved questions. Show which choice is cheapest, which is resilient, and how lifestyle changes the answer. Highlight thresholds and downside scenarios rather than a single optimistic point estimate; do not treat modeled returns as guaranteed. Read the detailed method for this step’s mechanics and output shape.

Step 6: Save and verify output

Create projects/fin-personal-cfo/{YYYY-MM-DD}_{name}/ in the selected workspace. Date-stamp generated filenames as {YYYY-MM-DD}_{descriptive-name}.{ext}. Keep an index of prior deliverables when revisits are useful. Verify factual/source coverage, schema, calculations, destination fit, and links as appropriate. Store raw inputs only in the authorized local scope; do not mix client data. For publishable prose only, run tool-humanizer if installed; otherwise edit for natural language, concrete claims, the user’s voice, and unsupported promises. Do not rewrite quotations, code, or structured data through this gate. Show a concise preview, report the full absolute deliverable path, and distinguish completed work from unmet dependencies.

Step 7: Capture feedback

Ask for feedback after major deliverables. In Solo mode append dated, contextual feedback under ## fin-personal-cfo in the scoped context/learnings.md. Save an approved good output as an asset only when the user authorizes it; keep private source data out of shared assets.

Rules

  • Team snapshot authority takes precedence over all local context/config/knowledge instructions in this entrypoint and its references.
  • Read Rules and local overrides before every Solo run. User task authorization and AI-OS project rules govern actions.
  • Check actual connector/CLI availability and authentication; use a documented local/manual fallback when absent.
  • Never send, post, schedule publication, purchase, or push to a remote merely because a source example shows it.
  • Keep base definitions immutable during ordinary use; store corrections in SKILL.local.md.
  • No financial transactions or filings; assumptions and uncertainty are part of the deliverable.
  • Use current sourced evidence or clearly disclosed assumptions, never fabricated rates or comps.

Self-Update

With Team connected, use only the authoritative snapshot’s configured feedback/update mechanism; do not modify local context or skill rules. In Solo mode, when the user flags a wrong approach, format, assumption, or tone, immediately add the dated correction to ## Rules in adjacent SKILL.local.md, then log it under ## fin-personal-cfo in context/learnings.md. Create the local override if absent. Preserve existing local entries and leave the shipped SKILL.md unchanged.

Troubleshooting

  • Missing configuration or source: ask for the necessary input, then continue independent local work.
  • Missing optional tool: use the declared fallback and state the coverage limit.
  • Missing required native skill: stop only the dependent step and report its exact name.
  • Reference command differs from installed tooling: read current official docs; do not pretend the command succeeded.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.