defi-yield

DeFi yield analysis and optimization — lending rates, LP yields, staking returns, yield farming strategies, risk-adjusted yield comparison, and protocol-level sustainability assessment.

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/defi-yield/SKILL.md

Quality

Content

58%Weight 40%Scale 1-5

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

The content is actionable with solid executable code and useful reference tables, but it is a single long document with no progressive disclosure and lacks an explicit sequenced workflow with validation checkpoints for its time-sensitive data.

Suggestions

Split large reference tables (lending protocols, data sources, output template) into a separate reference file and link to it from SKILL.md to improve progressive disclosure.

Add an explicit numbered workflow (1. pull current rates, 2. compute net/IL-adjusted yields, 3. assess sustainability, 4. risk-adjust and rank, 5. render report) with a validation step that checks data is recent given the hours-level volatility.

Trim general-knowledge exposition (e.g. definitions of impermanent loss, generic protocol blurbs) since Claude already knows these; keep only the skill-specific formulas and thresholds.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable, on-point code blocks, but several tables and prose sections restate general DeFi knowledge Claude already knows (e.g. explaining what impermanent loss is, generic protocol descriptions) that could be trimmed.	3 / 5
Actionability	Provides several concrete, executable Python functions (impermanent_loss, net_lp_yield, risk_adjusted_yield) and clear evaluation tables, with only minor gaps (some inputs are undefined protocol objects rather than self-contained snippets).	4 / 5
Workflow Clarity	The skill frames a multi-step analytical process (gather rates → compute IL/net yield → assess sustainability → risk-adjusted comparison → produce report) but the steps are not explicitly sequenced and there is no validation checkpoint confirming data freshness despite the skill's own warning that yields change within hours; the destructive/batch cap is not triggered but checkpoint absence limits the score.	3 / 5
Progressive Disclosure	Single monolithic 265-line SKILL.md with no bundle files or external references; section headers give some structure but content that could live in separate files (protocol tables, output template) is all inlined.	3 / 5
	Total	13 / 20 Passed

Description

61%Weight 40%Scale 1-5

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

The description is specific and covers the DeFi yield domain well with natural trigger terms, but it lacks an explicit "Use when..." trigger clause, capping completeness at 3 and leaving trigger guidance implicit.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks about DeFi yields, lending rates, LP returns, staking rewards, or yield farming strategies.'

Use active third-person verbs (e.g. 'Analyzes', 'Compares', 'Assesses') instead of noun-phrase lists to sharpen specificity.

Include common synonyms or shorthand users say (APY, liquidity mining, restaking) to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several specific concrete capabilities — "lending rates, LP yields, staking returns, yield farming strategies, risk-adjusted yield comparison, and protocol-level sustainability assessment" — giving broad coverage with only minor gaps (no mention of extraction/manipulation verbs, mostly noun phrases).	4 / 5
Completeness	Clearly answers "what" (the listed analysis capabilities) but provides no "Use when..." clause or equivalent trigger guidance; per the rubric a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Contains natural user-facing terms ("lending rates", "LP yields", "staking returns", "yield farming") that a user would plausibly say, though it omits synonyms and file-extension-style variants and leans slightly technical.	4 / 5
Distinctiveness Conflict Risk	The DeFi-yield niche is fairly distinct (lending/LP/staking/yield farming) and unlikely to collide with non-crypto skills; only minor overlap risk with a broader crypto-analytics skill.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/defi-yield/SKILL.md
Commit: f9cb061

Reviewed: 3 days 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.