agentleFS
tusharagg1tusharagg1/aifolimizer/.claude/skills/tax-loss-review/SKILL.md

tax-loss-review

Skill2 starsChanged 5 months agoMITView on GitHub

Canadian tax-loss harvesting review. Use when the user asks about tax-loss harvesting, "should I sell my losers?", capital losses, superficial loss rules, or year-end tax moves. Fetches loss candidates via aifolimizer MCP.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Call mcp__aifolimizer__get_profile - identify which account holds each position (TFSA/RRSP losses NOT deductible)

    line 10
  2. Very specific:

    Call mcp__aifolimizer__get_personal_context - use derived.marginal_tax_rate_pct + province to compute each loss's after-tax value (loss × …

    line 11
  3. Very specific:

    Call mcp__aifolimizer__get_tax_loss_candidates with threshold_pct=-5.0 (or stricter -10.0 for clearer picks)

    line 12
  4. Distinctive:

    TFSA / RRSP / FHSA losses are NOT deductible: - only non-registered accounts qualify

    line 17
  5. Distinctive:

    Superficial loss rule (30 days): if you (or spouse) buy back same security or "substantially identical" one within 30 days before or after …

    line 18
  6. Distinctive:

    Never recommend selling TFSA/RRSP position for tax reasons

    line 34
  7. Distinctive:

    Always flag 30-day superficial loss risk

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Tax-Loss Harvesting Review (Canadian rules)

How to run

  1. Call mcp__aifolimizer__get_profile - identify which account holds each position (TFSA/RRSP losses NOT deductible)
  2. Call mcp__aifolimizer__get_personal_context - use derived.marginal_tax_rate_pct + province to compute each loss's after-tax value (loss × 50% inclusion × marginal rate), so picks are ranked by real tax savings not gross loss. If present=false, mark the dollar value as an estimate and suggest running profile-setup.
  3. Call mcp__aifolimizer__get_tax_loss_candidates with threshold_pct=-5.0 (or stricter -10.0 for clearer picks)
  4. For each candidate, check account placement matters for tax

Key Canadian rules to enforce

  • TFSA / RRSP / FHSA losses are NOT deductible - only non-registered accounts qualify
  • Superficial loss rule (30 days): if you (or spouse) buy back same security or "substantially identical" one within 30 days before or after sale, loss is denied
  • Capital losses in non-registered accounts offset capital gains (current year, carry back 3 years, carry forward indefinitely)
  • Substitute trades: typically different but similar ETF (e.g., sell VFV → buy XUS as non-identical S&P 500 proxy) - though "substantially identical" is judgment

Output structure

  1. Account-by-account breakdown - tax-loss-eligible (non-reg) vs not (TFSA/RRSP/FHSA)
  2. Ranked list of eligible loss candidates by unrealized loss size
  3. Per top candidate: ticker, unrealized loss $, %, suggested substitute ETF
  4. Superficial loss warnings: candidates conflicting with recent buys
  5. Total deductible loss vs total realized gains YTD (ask user if unknown)
  6. Action plan: sell list, reinvest list, calendar (avoid 30-day window)

Rules

  • Under 400 words
  • Never recommend selling TFSA/RRSP position for tax reasons
  • Always flag 30-day superficial loss risk
  • Suggest substitutes avoiding "substantially identical" designation

Gotchas

  • Superficial loss rule covers user AND spouse/common-law partner AND any controlled corp - ask before assuming buy-back window is clean.
  • 30-day window is 30 calendar days BEFORE and AFTER sale - both sides count.
  • Same-class ETFs tracking same index (e.g. VFV ↔ VOO) likely "substantially identical" per CRA - recommend different index proxy (e.g. VFV → XUS uses different index methodology, safer).
  • TFSA losses are PERMANENT - contribution room not restored. Mention when discussing TFSA exits.
  • USD-denominated cost basis must be converted at transaction-date FX rate, not current - get_tax_loss_candidates may show CAD-converted loss that misstates actual ACB. Flag and recommend user verify with broker statement.
  • Capital losses cannot offset interest/dividend income - only capital gains. Don't suggest harvesting to "offset T5 income".

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.