tax-loss-harvesting

Identify tax-loss harvesting opportunities across taxable accounts. Finds positions with unrealized losses, suggests replacement securities, and tracks wash sale windows. Triggers on "tax-loss harvesting", "TLH", "harvest losses", "tax losses", "unrealized losses", or "year-end tax planning".

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An action-dense, concise workflow with strong concrete guidance and clean sectioning. The main gap is the execution step: a destructive batch operation (selling/rebuying securities) that lacks an explicit validation/confirmation feedback loop, capping workflow clarity.

Suggestions

Add an explicit validation gate before Step 5 execution (e.g., confirm the wash-sale check passed and the client/advisor approved the harvest amount) with a 'do not proceed until confirmed' checkpoint.

Add a verify-after-execution step — re-check realized loss figures and confirm wash-sale windows are recorded — so the workflow has a fix-and-retry feedback loop rather than ending at execution.

Trim the empty scaffold rows in the Step 1, Step 4, and Step 5 tables to reduce token overhead while keeping the column structure as a template.

Dimension	Reasoning	Score
Conciseness	Lean instruction set that assumes Claude's domain competence; tables and prioritization rules carry the content without explaining what tax-loss harvesting is or how tax law works.	3 / 3
Actionability	Concrete, copy-paste-ready guidance: explicit prioritization rules, named replacement-security pairs with rationale, 30-day wash-sale lookback/forward rules, DRIP checks, and a tax-savings formula.	3 / 3
Workflow Clarity	A clear seven-step sequence with a wash-sale validation checkpoint before execution, but the batch/destructive trade execution (Step 5) lacks an explicit validate→fix→retry feedback loop or a confirm-before-executing gate.	2 / 3
Progressive Disclosure	A single, self-contained file with well-organized, clearly headed sections and no need for external references; content is appropriately inline for this scope.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description that concretely states capabilities, provides natural trigger terms with good variation coverage, and explicitly answers both what and when in third-person voice. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Finds positions with unrealized losses, suggests replacement securities, and tracks wash sale windows' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what it does (first sentence) and when to use it via the 'Triggers on...' clause.	3 / 3
Trigger Term Quality	Natural user-facing terms with good coverage and variations including the 'TLH' abbreviation: 'tax-loss harvesting', 'harvest losses', 'tax losses', 'unrealized losses', 'year-end tax planning'.	3 / 3
Distinctiveness Conflict Risk	A clear niche (tax-loss harvesting across taxable accounts) with distinctive triggers; written in third person and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anthropics/financial-services
Path: plugins/vertical-plugins/wealth-management/skills/tax-loss-harvesting/SKILL.md
Commit: eb0c1ea

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.