hyperliquid-reader

Read Hyperliquid (app.hyperliquid.xyz) perp and spot market data through opencli and Hyperliquid's public info API: mark, oracle, and mid prices, 24h change, funding rates (hourly and annualized APR), open interest, volume, the L2 order book, OHLCV candles, funding history, and cross-venue funding comparisons (Hyperliquid vs Binance vs Bybit) for funding arbitrage. Use this skill whenever the user mentions Hyperliquid (HL, HL DEX, hyperliquid.xyz) or asks about its perps, spot pairs such as PURR, funding, open interest, order book, or candles. Read-only market data: no account, order, or transfer operations.

Quality

96%

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

92%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.

A well-engineered skill body: executable commands with concrete flags and output schemas, a setup→diagnose workflow with validation checkpoints, and clean delegation to one reference file. The only weakness is repetition of the read-only disclaimer and the install command across multiple sections.

Suggestions

State the read-only boundary once (e.g. in the intro) and remove the repeats in Key rule 8 and the setup table to save tokens.

Keep the plugin-install command in one place (Step 1) and have the Error Reference point back to it instead of repeating it verbatim.

Dimension	Reasoning	Score
Conciseness	The body is dense and table-driven with no explanations of concepts Claude already knows, but the read-only boundary is stated three times (intro, Key rule 8, error table) and the plugin-install command is repeated in three places, which is minor over-explanation that could be trimmed. Not 5 because of this redundancy; not 3 because there is no padded or unnecessary conceptual explanation.	4 / 5
Actionability	Every subcommand appears as a copy-paste-ready invocation with its flags, defaults, output formats, and enumerated output columns (e.g. 'opencli hyperliquid candles --coin BTC --interval 4h --limit 50 -f csv'), covering all common cases per the top anchor.	5 / 5
Workflow Clarity	Steps 1–5 are clearly sequenced with explicit validation (the READY/SETUP_NEEDED environment check, the Step 5 BTC-row diagnostic) and error-recovery feedback loops (the Error Reference cause→fix table with retry guidance). The skill is read-only, so the destructive/batch validation cap does not apply.	5 / 5
Progressive Disclosure	SKILL.md is an overview that summarizes each command and delegates full flags, output schemas, and workflows to a single clearly-signaled, one-level-deep reference ('references/commands.md — Every command with all flags, output schemas, and analyst workflows'), which exists in the bundle and matches its description.	5 / 5
	Total	19 / 20 Passed

Description

100%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.

A strong description: concrete capability list, explicit trigger clause with venue synonyms and domain terms, and a clear scope boundary marking it read-only. It is on the long side but every clause carries information rather than padding.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete capabilities — 'mark, oracle, and mid prices, 24h change, funding rates (hourly and annualized APR), open interest, volume, the L2 order book, OHLCV candles, funding history, and cross-venue funding comparisons' — which is comprehensive coverage of the skill's actions, matching the top anchor rather than the 'minor gaps' level 4 example.	5 / 5
Completeness	It explicitly answers both 'what' (the enumerated market-data reads) and 'when' via an explicit 'Use this skill whenever the user mentions Hyperliquid ... or asks about its perps' clause with concrete trigger phrases, matching the level 5 anchor exactly.	5 / 5
Trigger Term Quality	Natural trigger terms include venue synonyms ('Hyperliquid (HL, HL DEX, hyperliquid.xyz)') and domain terms users would actually say ('perps, spot pairs such as PURR, funding, open interest, order book, or candles'), giving comprehensive coverage with synonyms as in the level 5 anchor.	5 / 5
Distinctiveness Conflict Risk	It occupies a clear niche — read-only market data for one named venue via opencli — with distinct triggers and an explicit boundary ('no account, order, or transfer operations'), so overlap risk with other skills is minimal.	5 / 5
	Total	20 / 20 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: himself65/finance-skills
Path: plugins/data-providers/skills/hyperliquid-reader/SKILL.md
Commit: 7fe9185

Reviewed: 6 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.