surf

Use this skill — NOT browser or web_fetch — for ALL Surf crypto-data calls. 83 endpoints at localhost:8402/v1/surf/* covering CEX/DEX markets, on-chain SQL over 80+ ClickHouse tables (Ethereum, Base, Arbitrum, BSC, TRON, HyperEVM, Tempo), 100M+ labeled wallets, prediction markets (Polymarket + Kalshi), social/CT intelligence, news, project + DeFi metrics, token analytics, unified search, VC fund intelligence. x402-gated via ClawRouter's local wallet — no Surf account or API key required.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/surf/SKILL.md

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 strong, highly actionable API skill body with concrete executable examples and clear multi-step workflows, weakened mainly by inlining the full 83-endpoint catalog rather than splitting it into a separate reference file. Conciseness is good given the necessary reference density.

Suggestions

Move the full per-domain endpoint catalog tables into a references/ file (e.g., references/endpoints.md) and keep only a domain summary plus the highest-value examples inline in SKILL.md.

Add an explicit validate->fix->retry feedback loop for the on-chain SQL flow (e.g., on 400 missing_params, re-issue with the listed required params; on timeout, add LIMIT and retry).

Promote a short 'Quick start' section with the 3-4 most common calls above the full catalog so the highest-frequency path is reachable without scrolling.

Dimension	Reasoning	Score
Conciseness	Information-dense endpoint catalog with minimal concept over-explanation; the length is justified by 83 endpoints across 12 domains, with only minor soft spots (x402 wallet-flow prose, the 'by design' rationale).	4 / 5
Actionability	Fully executable, copy-paste-ready curl commands with real URLs, params, and example values (vitalik.eth, a real contract address, a real SQL query), plus per-endpoint required params and several worked multi-step flows.	5 / 5
Workflow Clarity	Multi-step flows are clearly sequenced (schema-fetch-then-SQL with caching; resolve-slug-then-mindshare) with an explicit pre-settlement param-validation checkpoint, though these are advisory cautions rather than full validate->fix->retry feedback loops.	4 / 5
Progressive Disclosure	Well-organized into 12 domain sections with headers and tables and no nested references, but the entire 83-endpoint catalog is inlined in SKILL.md with no bundle files; bulk API reference that would belong in a separate reference file is inline.	3 / 5
	Total	16 / 20 Passed

Description

71%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 highly specific, well-differentiated description that explicitly states both what it does and when to use it, with minor weakness in natural trigger-term phrasing. The technical/infra framing (localhost port, x402, ClawRouter) slightly dilutes user-facing keyword quality.

Suggestions

Lead with a few concrete user-facing trigger phrases (e.g., 'Use when the user asks for crypto prices, on-chain wallet labels, or prediction-market data') before the endpoint inventory.

Trim infra-specific jargon (localhost:8402, x402-gated, ClawRouter) from the description or move it to the body; it does not help a user recognize when to invoke the skill.

Add common synonyms users actually say ('crypto API', 'onchain data', 'wallet labels', 'token holders') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists many concrete capabilities and domains (83 endpoints, CEX/DEX markets, on-chain SQL over 80+ ClickHouse tables, 100M+ labeled wallets, Polymarket+Kalshi, social/CT, DeFi metrics, VC fund intelligence), but enumerates domains rather than discrete actions and includes capability-adjacent infra detail.	4 / 5
Completeness	Clearly states 'what' (extensive capability list) and includes an explicit 'when' clause ('Use this skill — NOT browser or web_fetch — for ALL Surf crypto-data calls'), though the trigger is generic rather than concrete phrases.	4 / 5
Trigger Term Quality	Some natural terms appear ('crypto-data calls', 'on-chain SQL', 'prediction markets', 'labeled wallets') but the body leans technical ('localhost:8402/v1/surf/*', 'ClickHouse tables', 'x402-gated', 'ClawRouter') and misses common user-facing synonyms.	3 / 5
Distinctiveness Conflict Risk	Clear niche (Surf crypto API via ClawRouter) with an explicit differentiation from browser/web_fetch, giving minimal conflict risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: BlockRunAI/ClawRouter
Path: skills/surf/SKILL.md
Commit: bd13340

Reviewed: 5 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.