Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Galleon Defi Portfolio

ASecurity

Reconcile cross-chain DeFi holdings, protocol positions, debt and cash flows into a sourced portfolio report or rebalance plan. Use when assessing exposure, net asset value, performance or treasury monitoring while avoiding receipt-token double counts and confusing price changes with investment profit.

2 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsgoapiperformance

Works with

api

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add galleonlabs/crypto-defi-skills --skill galleon-defi-portfolio --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Galleon Defi Portfolio?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Galleon Defi Portfolio
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/galleonlabs-galleon-defi-portfolio/badge)](https://www.skillsdirectory.com/skills/galleonlabs-galleon-defi-portfolio)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: galleon-defi-portfolio
description: Reconcile cross-chain DeFi holdings, protocol positions, debt and cash flows into a sourced portfolio report or rebalance plan. Use when assessing exposure, net asset value, performance or treasury monitoring while avoiding receipt-token double counts and confusing price changes with investment profit.
license: MIT
compatibility: Portable agent instructions. Optional Zerion, DeBank, CoinGecko, DefiLlama and protocol reads require supported coverage and the user's own access. No custody, transaction execution or recurring scheduler is bundled.
metadata:
  author: Galleon Labs
  version: "0.1.3"
---

# DeFi portfolio and treasury

Answer what the selected accounts own, owe and can access, what changed, and what evidence is missing. A portfolio report or target allocation is not authorization to move funds.

## Start with the requested task

Read [task examples and user configuration](references/task-examples.md) for a completed example and recovery path. Apply only the workflow stages needed by the current request. Reuse supplied preferences and compatible tools; ask only for missing terms that affect this task. Public explanation or comparison does not require transaction fields. Keep any existing authorization within its exact scope.

## Define the scope

Establish included accounts and chains, ownership boundaries, reporting currency, valuation time, comparison period and purpose. Distinguish a watchlist from the user's own holdings. Preserve smart accounts, multisigs, exchange subaccounts and vault positions as separate identities; do not infer access to private exchange balances from an onchain address.

Use [provider interfaces](references/providers.md) to fetch bounded account data through existing official tools. Use filters and pagination deliberately: a wallet-token endpoint may omit protocol positions. Mark unsupported chains, partial pages, delayed indexers and missing accounts as coverage gaps, not zero balances. Record provider retrieval time and position observation time separately.

## Reconcile before aggregating

- Identify each position by chain namespace/ID, account, exact token or native-asset identity, protocol deployment, position ID and valuation block/time. Preserve provider IDs as opaque identifiers; a ticker or cross-chain logo is not a key.
- Represent quantities as base-unit integers plus decimals, or exact decimal strings. Keep conversion rates, units and sources. Avoid binary float rounding when reconciling raw balances or debt.
- Classify wallet holdings, supplied collateral, borrowed liabilities, LP/vault shares, staking/restaking receipts, locked positions, pending withdrawals/bridges and unclaimed rewards separately.
- Choose a valuation representation: receipt shares or their attributable underlying exposure. Never add both to equity. Break an LP position into underlying exposures for allocation without also counting its total value again. Reconcile provider overlap and internal account transfers.
- Show gross assets, debt and net equity. Keep leverage/notional exposure separate from equity; a derivative's notional is not cash value. Price stablecoins from evidence rather than assuming a dollar peg.

For receipt tokens, debt, pending states and performance calculations, apply [accounting rules](references/accounting.md). Corroborate material quantities and time-sensitive risk with chain or protocol state at a recorded block. Market APIs provide marks; they do not establish custody or immediate exit proceeds.

## Explain changes and propose actions

Separate deposits/withdrawals, internal transfers, price movement, fees/rewards, debt interest and trading effects. When cost basis or flow history is incomplete, report mark-to-market change with that limitation rather than inventing realized PnL or returns. Handle missing prices as unpriced exposure; do not quietly drop an asset from the denominator.

Use [report and rebalance workflow](references/reporting.md) to identify concentration, liquidity constraints, debt risk, exit queues and discrepancies. A rebalance plan should include dependencies, estimated costs, slippage limits, timing and the unchanged “do nothing” case. It must not execute, revoke approvals, enroll paid data, create a scheduler or publish private holdings without the user's corresponding request and authority.

## Deliver

Return net equity with its valuation time and coverage, gross assets/debt, allocation/exposure, changes with known flows, material risks and actionable unknowns. Link primary evidence and disclose stale or missing data. Keep private account mappings and snapshots in the user's approved location outside source control. If recurring reporting is requested, use the host's existing scheduler and storage conventions rather than creating a competing agent runtime.

Use [evaluation scenarios](references/evals.md) to test reporting behavior without paid APIs or real account actions.

Attribution

galleonlabsgalleonlabs
View sourceMore from galleonlabs →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →