integrating-jupiter

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.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

92%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced integration guide that is dense rather than verbose, with strong workflow and validation guidance for fund-moving operations. The main defect is progressive disclosure: the body advertises four ./examples/ files that are not present in the bundle.

Suggestions

Either add the referenced ./examples/{swap,lend,trigger,price}.md files to the bundle or remove the 'Complete Working Examples' section, since the links currently point to non-existent files.

Reduce trigger-list duplication: the large inline 'Triggers' list overlaps with the per-API 'Triggers' lines — consolidate to avoid redundancy while preserving routing accuracy.

Consider moving the long Swap error-code table and the OpenAPI 'Refs' clusters into a single reference file to slim the SKILL.md overview and deepen progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Dense, API-specific facts with no explanation of concepts Claude already knows; each ~35-line playbook earns its tokens. A score below 3 would apply if padded, but the breadth (13 APIs) justifies the length and per-section content is lean.	3 / 3
Actionability	Provides fully executable TypeScript helpers ('jupiterFetch', 'signAndSend', 'jupiterAction', 'withRetry'), concrete endpoint paths with HTTP methods, and a retryable error-code table — copy-paste ready guidance rather than vague direction.	3 / 3
Workflow Clarity	The Intent Router table sequences first actions per intent; order-based playbooks give explicit multi-step flows (e.g. Trigger's 3-step create, 2-step cancel) with validation checkpoints ('omit taker' for preview, 'reconcile against your quote', Production Hardening #5 validate mints/amounts).	3 / 3
Progressive Disclosure	External docs are well-signaled one-level 'Refs:' links, but the 'Complete Working Examples' section points to ./examples/swap.md, ./examples/lend.md, ./examples/trigger.md, and ./examples/price.md — none of which exist in the bundle — so promised split content is missing and navigation is undermined.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that concisely states the capability set and provides an explicit 'Use for' trigger. It enumerates the concrete API families rather than relying on vague language, with no over-claims or fluff beyond the harmless 'Comprehensive guidance' opener.

Dimension	Reasoning	Score
Specificity	Enumerates 13 concrete API families ('Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio, Lock, Routing') plus specific actions ('endpoint selection, integration flows, error handling, and production hardening').	3 / 3
Completeness	Clearly answers both 'what' (integrating the listed Jupiter APIs) and 'when' via the explicit 'Use for endpoint selection, integration flows, error handling, and production hardening' clause.	3 / 3
Trigger Term Quality	Includes natural terms a developer would say when needing the skill — the API family names ('Swap', 'Lend', 'Perps', 'Trigger') plus 'Jupiter APIs' — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to 'Jupiter APIs' with a distinctive enumerated niche, making it unlikely to trigger for unrelated Solana or generic-crypto skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: jup-ag/agent-skills
Path: skills/integrating-jupiter/SKILL.md
Commit: a2211e3

Reviewed: 17 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.