tessl-skill-index-evals/jup-ag__agent-skills__integrating-jupiter
Comprehensive guidance for integrating Jupiter APIs (Ultra Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio, Lock, Routing).
86
83%
Does it follow best practices?
Impact
91%
1.85xAverage score across 5 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
57%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 effectively identifies its domain (Jupiter APIs) and lists specific API products, making it distinctive. However, it lacks explicit trigger guidance ('Use when...') and could benefit from more natural user-facing keywords. The actions described are somewhat generic development concepts rather than concrete Jupiter-specific operations.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios like 'Use when the user asks about Solana token swaps, Jupiter integration, DeFi trading APIs, or mentions any Jupiter product by name.'
Include more natural user keywords such as 'Solana', 'DeFi', 'token swap', 'crypto exchange API', 'Jupiter SDK' that users would naturally say when needing this skill.
Replace generic actions like 'integration flows' with concrete examples like 'implement token swaps, set up recurring buys, query token prices, or create limit orders'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific API names (Ultra Swap, Lend, Perps, etc.) and mentions actions like 'endpoint selection, integration flows, error handling, and production hardening', but these are somewhat generic development concepts rather than concrete actions specific to Jupiter APIs. | 2 / 3 |
Completeness | Clearly describes what it does (guidance for Jupiter API integration) but lacks an explicit 'Use when...' clause. The 'when' is only implied through the phrase 'Use for endpoint selection...' which doesn't specify user-facing trigger scenarios. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Jupiter APIs', specific API names, and terms like 'integration' and 'endpoint', but misses common user phrases like 'Solana swap', 'DeFi', 'token exchange', 'Jupiter SDK', or 'crypto trading API'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific mention of 'Jupiter APIs' and the enumeration of 12 specific API products. This creates a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exceptionally well-crafted skill that serves as a comprehensive routing guide for Jupiter APIs. It maximizes information density through tables, code blocks, and structured playbooks while maintaining clear navigation to detailed documentation. The Intent Router, API-specific gotchas, and cross-cutting error patterns provide immediately actionable guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely efficient use of tokens - tables, code blocks, and bullet points convey maximum information with minimal prose. No explanations of concepts Claude already knows (Solana basics, what APIs are, etc.). | 3 / 3 |
Actionability | Provides fully executable TypeScript code for the quickstart, complete error handling patterns, and specific endpoint paths with HTTP methods. The Intent Router table gives immediate routing decisions. | 3 / 3 |
Workflow Clarity | Clear multi-step workflows with explicit sequences (e.g., 'create-tx -> upload image -> upload metadata -> sign -> submit'). Production Hardening section provides validation checkpoints and the Fresh Context Policy establishes a clear decision flow. | 3 / 3 |
Progressive Disclosure | Excellent structure with overview-level playbooks that link to detailed refs (Overview, OpenAPI specs, specific docs). One-level-deep references are clearly signaled with 'Refs:' sections for each API family. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents