Comprehensive guidance for integrating Jupiter APIs (Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio, Lock, Routing). Use for endpoint selection, integration flows, error handling, and production hardening.
60
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/integrating-jupiter/SKILL.mdQuality
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 a clear niche (Jupiter API integration) and enumerates the specific API domains covered, providing good distinctiveness. However, it falls short on explicit trigger guidance (no 'Use when...' clause with user-facing trigger scenarios) and the listed actions are somewhat generic rather than concrete operations. The trigger terms could be expanded to include natural user language beyond API category names.
Suggestions
Add an explicit 'Use when...' clause with natural trigger scenarios, e.g., 'Use when the user asks about Jupiter integration, Solana token swaps, Jupiter SDK, or building DeFi applications with Jupiter.'
Replace generic action phrases like 'integration flows' and 'production hardening' with concrete operations such as 'execute token swaps, set up limit orders, query token prices, manage perpetual positions.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists specific Jupiter API domains (Swap, Lend, Perps, Trigger, etc.) and mentions actions like 'endpoint selection, integration flows, error handling, and production hardening,' but these actions are somewhat generic and not concrete enough to qualify as specific operations (e.g., 'execute token swaps,' 'place perpetual orders'). | 2 / 3 |
Completeness | The 'what' is reasonably covered (guidance for integrating Jupiter APIs across multiple domains). However, the 'when' is only implied through 'Use for endpoint selection, integration flows...' rather than explicitly stating trigger conditions like 'Use when the user asks about Jupiter integration, Solana swaps, or building with Jupiter APIs.' | 2 / 3 |
Trigger Term Quality | It includes relevant keywords like 'Jupiter APIs,' 'Swap,' 'Lend,' 'Perps,' 'Routing,' and 'Price' which users working with Jupiter would naturally use. However, it misses common variations like 'Solana DEX,' 'token exchange,' 'DeFi,' 'Jupiter SDK,' or 'jup.ag' that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Jupiter is a very specific platform (Solana-based DEX aggregator), and the description lists 13 distinct API categories, making it highly unlikely to conflict with other skills. The niche is clearly defined. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, comprehensive API integration skill that serves as an effective routing and reference document for 12+ Jupiter API families. Its greatest strengths are the actionable code examples (fetch helper, error handling, retry logic), the clear intent router table, and excellent progressive disclosure with well-signaled references. The main area for improvement is trimming some verbosity—the extensive trigger keyword list and some redundant explanatory text could be condensed to save tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is dense and information-rich, but some sections include details Claude could infer or look up (e.g., listing every trigger keyword, explaining what prediction markets are). The trigger list alone is very long. However, most content is genuinely novel domain knowledge (endpoint paths, error codes, gotchas) that Claude wouldn't know, so it's mostly efficient but could be tightened. | 2 / 3 |
Actionability | Provides fully executable TypeScript code for the fetch helper, sign-and-send, error handling wrapper, and retry logic. Each API section includes concrete endpoint paths, HTTP methods, and specific parameter details. The error code table with retryable flags is immediately actionable. Examples are linked as separate files for full flows. | 3 / 3 |
Workflow Clarity | The Intent Router table provides clear first-step routing for every user intent. Multi-step workflows are explicitly sequenced (e.g., Trigger's 3-step order creation, Studio's create-tx -> upload -> sign -> submit flow, Swap's order -> sign -> execute). Validation checkpoints are present (re-quote before execution, validate mints/amounts before calls, reconcile async states). The Production Hardening section adds explicit verification steps. Error recovery with retry logic and retryable classification provides feedback loops. | 3 / 3 |
Progressive Disclosure | Excellent structure: the main file serves as a routing overview with concise playbooks, then links to detailed refs (overview docs, OpenAPI specs, examples) that are all one level deep. Working examples are appropriately split into separate files. Each API section has clearly signaled reference links. The Fresh Context Policy even instructs on when to fetch deeper documentation. | 3 / 3 |
Total | 11 / 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 | |
b0a4830
Table of Contents
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.