SkillAgentSearch skills...

trader-tax

Tax Optimizer. Tracks cost-basis lots for every position (FIFO, highest cost first, or specific lots), shows unrealized gains and losses by lot with short or long term, works out what a sale would realize before you sell, finds tax-loss harvesting candidates over a loss threshold, checks the wash sa…

Install / Use

npx skills add Jakeschincariol/trader-skill --skill trader-tax

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

86/100

Supported Platforms

Zed

Tags

Our assessment of trader-tax

trader-tax scores 86/100 on our quality scale, 2412th of 4,728 Development & Engineering skills we index.

Its SKILL.md is 5.4 KB long, split into 7 sections with 1 code example: a solid amount of guidance for an agent.

With 1,772 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
15/20
Description
15/15
Adoption
14/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 34 days ago, so trader-tax is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

trader-tax compared with similar skills

All 4 of these similar skills score higher than trader-tax; compare them before choosing.

SkillScoreStarsUpdatedFormat
trader-tax (this skill)by Jakeschincariol861.8k34d agoSKILL.md
taste-skillby Leonxlnx100118.1k9d agoCLAUDE.md
hyperframesby heygen-com10086.2ktodayCLAUDE.md
ai-job-searchby ai-job-search-dev10072.4k1d agoCLAUDE.md
claude-howtoby luongnv8910047.4k3d agoCLAUDE.md

Frequently asked questions

How do I install trader-tax?
Run npx skills add Jakeschincariol/trader-skill --skill trader-tax. The install tabs above show the steps for each supported agent.
Which AI agents does trader-tax work with?
It is written for Zed, as a SKILL.md file. Other agents that read the same format can often use it too.
Is trader-tax safe to use?
It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is trader-tax still maintained?
The repository was last updated 34 days ago, so trader-tax is actively maintained.

name: trader-tax description: >- Tax Optimizer. Tracks cost-basis lots for every position (FIFO, highest cost first, or specific lots), shows unrealized gains and losses by lot with short or long term, works out what a sale would realize before you sell, finds tax-loss harvesting candidates over a loss threshold, checks the wash sale rule (30 days before and after, GOOG and GOOGL as one family), and writes harvest sells only as proposals. Not tax advice. Use when the user says "what are my gains", "cost basis", "tax lots", "tax-loss harvest", "what would selling cost me in tax", "short or long term", "wash sale", or before selling anything. argument-hint: "[ticker]"

trader-tax

The Tax Optimizer does the arithmetic on the user's lots so nobody sells blind. It never decides what is right for the user's taxes. This is not tax advice: a tax professional decides what applies to them. Say that once, early, in every answer that uses this skill.

${CLAUDE_SKILL_DIR} below is this skill's folder (where this SKILL.md lives).

python3 "${CLAUDE_SKILL_DIR}/lots.py" report --lots              # every lot, gain or loss, term
python3 "${CLAUDE_SKILL_DIR}/lots.py" sell KO 2 --price 90.11    # what a sale would realize (FIFO)
python3 "${CLAUDE_SKILL_DIR}/lots.py" sell KO 2 --method specific --lots KO-2
python3 "${CLAUDE_SKILL_DIR}/lots.py" harvest --min-loss 100     # candidates, with wash-sale checks
python3 "${CLAUDE_SKILL_DIR}/lots.py" harvest --min-loss 100 --write
python3 "${CLAUDE_SKILL_DIR}/lots.py" wash KO                    # is buying KO today a wash sale?

What it reads and writes

| file | what | | --- | --- | | trader/portfolio.json | positions with lots: {"id", "date", "shares", "cost"} (cost = total basis); shape: portfolio.example.json here | | trader/prices.json | current prices (trader-alerts: alerts.py quote --holdings --write) | | trader/orders.json | planned buys count for wash sales; harvest --write replaces it with sell proposals | | trader/state/tax.json | the realized sales it logs with sell --record |

Lots come from the fills trader-broker records (ticket.py fill), or from the user's broker statement. If a position has shares but no lots, ask for the purchase dates and costs. Never invent a cost basis.

The rules it applies (US federal, arithmetic only)

  • Term: long term if sold more than one year after the purchase date, otherwise short term. report --lots shows the date each lot turns long term.
  • Lot methods: fifo (oldest first, what most brokers do by default), hifo (highest cost first) and specific (named lots). The order sent to the broker does not carry lot ids: to sell specific lots the user must choose them in the broker's own tax-lot setting, or the broker uses its default method.
  • Wash sale: a loss is disallowed to the extent the same or a substantially identical stock is bought within 30 days before or after the sale. The tool checks the other lots still held, planned buys in trader/orders.json and the loss sales it has logged. It cannot see an IRA, a spouse's account or another broker, and those count too. Say so.

Steps

  1. Refresh prices, then lots.py report --lots. Show gains and losses by stock, and which lots are short or long term.
  2. Before any sell (rebalance, a stop, a change of mind), run lots.py sell with the planned shares and method and show what it would realize.
  3. For harvesting: lots.py harvest --min-loss 100 (and --min-pct if the user wants a percent threshold). For each candidate show the estimated loss, short and long term split, any wash-sale conflict, and the first day they could buy it back. Candidates with a conflict are not proposed.
  4. Only if the user wants proposals: harvest --write, then /trader-risk, then /trader-broker, one yes per order.
  5. After a sale fills, lots.py sell ... --record updates the lots and logs the realized result for the year.

Example: the reel's portfolio

The copy portfolio bought on 2026-10-13 (AAPL $1,250, AXP $1,119, GOOGL $823, KO $708, BAC $600) has one lot per stock, all short term until 2027-10-14. If BAC later trades below its $600 basis, harvest --min-loss 25 lists the BAC-1 lot with its loss and "do not buy BAC again before" a date 31 days after the sale. If the user also has a BAC buy planned in trader/orders.json, it flags a wash sale instead of proposing the sell.

What it never does

It never files anything, never gives a tax rate or a tax bill, never tells the user what they owe, never places an order, and never proposes a harvest that it can see would be a wash sale.

Safety

  • Not tax advice, and education and tooling, not financial advice. Check with a tax professional.
  • Paper trading by default ("paper": true). Going live is the user's own decision, in their own config.
  • Nothing in this pack places an order except trader-broker, and only when all three hold: trader-risk passed that exact order today, the user typed an explicit yes for that one order in the chat, and the user clicked Allow once on Claude's own card because the order tool is set to "Needs approval" (Customize > Connectors > tool permissions). Never set an order tool to "Always allow".
  • No options, margin, short selling or leverage unless the config allows it and the user confirms.
  • Broker keys live in environment variables or the Claude Desktop config, never in the chat.

Related Skills

View on GitHub
GitHub Stars1.8k
CategoryDevelopment
Updated1mo ago
Forks376

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions