CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dflow-phantom-connect

Build Solana wallet-connected apps with Phantom Connect SDKs and DFlow spot trading. Use when user asks to connect a Phantom wallet, integrate Phantom in React, React Native, or vanilla JS, sign messages or transactions, build token-gated pages, mint NFTs, accept crypto payments, or swap/stream tokens with DFlow. Covers @phantom/react-sdk, @phantom/react-native-sdk, @phantom/browser-sdk, and DFlow spot trading and market-data streaming. Do NOT use for Ethereum or EVM wallet integrations, or non-DFlow DEX routing.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

78%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-structured routing skill: the body stays a concise index that defers detail to nine real, well-scoped reference files, with clear sequencing and a genuine error-recovery section. Weaknesses are minor — some duplicated API-key guidance and no explicit confirmation checkpoint in the workflow.

Suggestions

Consolidate the DFlow API-key guidance (dev host is rate-limited, prod key URL, keep the key on the backend) into one place — Step 3 or Step 4 — instead of repeating it in both.

Add an explicit validation checkpoint in Step 4 or Step 5, e.g. 'only report success after the transaction signature is confirmed on-chain', so the happy path has a hard verification step.

Use markdown links (e.g. [react-sdk.md](references/react-sdk.md)) in Step 2 instead of bare backtick paths so the reference routing is directly navigable.

DimensionReasoningScore

Conciseness

The body is a lean router with no explanations of concepts Claude already knows, but the DFlow API-key guidance is stated twice — Step 3 asks 'Do you have a DFlow API key? ... Prod key: pond.dflow.net/get-started/api-key' and Step 4 repeats 'production requires a key from pond.dflow.net/get-started/api-key'. This fits the 4 anchor ('efficient; minor instances of over-explanation that could be trimmed'); it is not the 5 anchor because the duplication is a real, if small, token cost.

4 / 5

Actionability

Guidance is concrete: named reference files per domain, specific rules ('atomic units, base58 mints, quote-without-wallet'), a WebSocket subscribe payload shape ('{ op: "subscribe", base_mint, quote_mint }'), and step-by-step example action lists. It stops short of the 5 anchor because the body itself contains no executable code or copy-paste commands — that detail lives entirely in the reference files — which is the 'minor gaps' of the 4 anchor, not the vagueness of the 3 anchor.

4 / 5

Workflow Clarity

The five steps (identify domain → read references → ask questions → implement → handle errors) are clearly sequenced, and Step 5 provides real recovery guidance ('retry with backoff or get a production API key', route_not_found diagnosis, 'Reconnect and re-subscribe on drop'). It is not the 5 anchor because there is no explicit validation checkpoint on the happy path — 'confirm' is mentioned in passing but no step verifies a transaction confirmed before reporting success — which is the 'minor validation gaps' of the 4 anchor.

4 / 5

Progressive Disclosure

The body is purely an overview: Step 2 lists all nine reference files, each with a one-line scope annotation ('references/react-sdk.md: React hooks, components, theming, PhantomProvider'), and every referenced file exists in references/ with substantive content one level deep (references point only to sibling files and MCP doc paths, not to further nested files). This matches the 5 anchor: clear overview, well-signaled one-level-deep references, content appropriately split.

5 / 5

Total

17

/

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.

An exemplary description: concrete capability list, natural trigger phrases with platform synonyms and package names, explicit 'Use when' guidance, and explicit negative boundaries. Nothing vague or padded; third-person/imperative voice is consistent.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'connect a Phantom wallet, integrate Phantom in React, React Native, or vanilla JS, sign messages or transactions, build token-gated pages, mint NFTs, accept crypto payments, or swap/stream tokens' — giving comprehensive coverage of the skill's capabilities with no filler. This matches the 5 anchor ('lists multiple specific concrete actions; comprehensive coverage') and exceeds the 4 anchor only in breadth of coverage, which is genuinely present.

5 / 5

Completeness

Both parts are explicit: what — 'Build Solana wallet-connected apps with Phantom Connect SDKs and DFlow spot trading'; when — 'Use when user asks to connect a Phantom wallet... or swap/stream tokens with DFlow'. This mirrors the 5 anchor example that pairs a capability list with a concrete 'Use when...' trigger clause, and additionally adds exclusion guidance, so it is clearly not the 4 anchor where the 'when' 'could be more explicit'.

5 / 5

Trigger Term Quality

Natural user phrasings ('connect a Phantom wallet', 'mint NFTs', 'accept crypto payments', 'swap/stream tokens') are combined with platform synonyms (React, React Native, vanilla JS) and concrete package identifiers ('Covers @phantom/react-sdk, @phantom/react-native-sdk, @phantom/browser-sdk') that act like file-extension triggers. Coverage is comprehensive with synonyms; not the 4 anchor, where 'a few natural terms missing' — nothing a user would plausibly say in this domain is absent.

5 / 5

Distinctiveness Conflict Risk

The niche is sharply defined (Solana + Phantom + DFlow) and the explicit negative boundary — 'Do NOT use for Ethereum or EVM wallet integrations, or non-DFlow DEX routing' — removes the main overlap risks with generic wallet or DEX skills. Minimal conflict risk remains; the 4 anchor ('minor overlap risk') would apply only if some near-neighbor skill were still plausible to mis-trigger, which the exclusions largely preclude.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository

internet-court/internet-court-skill

Path

vendored/dflow/dflow-phantom-connect/SKILL.md

Reviewed

Table of Contents

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.