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

65%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.

An exceptionally actionable API catalog with concrete, runnable examples and precise parameter tables. Its weaknesses are the absence of progressive disclosure (no reference file for the full endpoint catalog) and the lack of explicit error-recovery feedback loops for batch and SQL workflows.

Suggestions

Move the full endpoint catalog into a referenced file (e.g. ENDPOINTS.md) and keep SKILL.md as a concise overview with one-level-deep links, improving both conciseness and progressive disclosure.

Add explicit validate→fix→retry loops for the on-chain SQL and wallet-labels/batch workflows (e.g. on 400 missing_params, list the required params and retry; on query timeout, reduce the scan window and re-run with LIMIT).

De-duplicate the base URL and pricing-tier definitions between the intro, the catalog tables, and the 'How calls are paid' section.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of concept-explanation Claude already knows, but ~225 lines of inline endpoint reference with minor redundancy (base URL restated in 'How calls are paid'; pricing tiers described then reused as table tags) leaves it tighten-able rather than lean.	2 / 3
Actionability	Fully executable curl examples with real URLs, query params, and JSON bodies, plus endpoint tables giving exact paths, HTTP methods, and required params, make the guidance copy-paste ready.	3 / 3
Workflow Clarity	Multi-step flows (schema→cache→POST SQL; resolve-slug→mindshare) are sequenced with checkpoints (400 pre-check, LIMIT, multi-statement rejection), but there is no structured validate→fix→retry recovery loop for the batch (labels/batch ≤200) and SQL operations, matching the 'sequence present but checkpoints implicit' anchor.	2 / 3
Progressive Disclosure	No bundle files exist, so the entire 83-endpoint catalog lives inline in SKILL.md — matching the anchor-2 example of '200 lines of API reference that could be in a separate file' — though section organization is clear enough to avoid anchor 1.	2 / 3
	Total	9 / 12 Passed

Description

85%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 highly specific, well-disambiguated description that clearly states both capability and trigger conditions. Its main weakness is embedding infrastructure jargon (ClickHouse, x402, ClawRouter) where natural user-facing terms would improve trigger matching.

Suggestions

Replace infrastructure jargon ('x402-gated via ClawRouter's local wallet', 'ClickHouse') with user-facing phrasing so natural trigger terms lead the description.

Front-load the most common user asks (price lookups, wallet labels, on-chain queries) before the endpoint-count and table detail.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities with hard numbers ('83 endpoints', 'on-chain SQL over 80+ ClickHouse tables', '100M+ labeled wallets', 'prediction markets (Polymarket + Kalshi)'); no first/second-person pronouns are used, so the voice penalty does not apply.	3 / 3
Completeness	Explicitly answers both what (enumerated coverage across 12 domains) and when ('Use this skill … for ALL Surf crypto-data calls'), satisfying the explicit-trigger requirement that would otherwise cap completeness at 2.	3 / 3
Trigger Term Quality	Broad crypto-domain coverage ('markets', 'prediction markets', 'social/CT intelligence', 'news', 'token analytics') is diluted by technical jargon users would not naturally say ('ClickHouse', 'x402-gated', 'ClawRouter', 'HyperEVM', 'Tempo'), matching the 'some relevant keywords but jargon' anchor rather than the fully-natural anchor 3.	2 / 3
Distinctiveness Conflict Risk	'NOT browser or web_fetch' actively disambiguates from sibling tools and the Surf niche (localhost:8402/v1/surf/*) is sharply scoped, making wrong-skill triggering unlikely.	3 / 3
	Total	11 / 12 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: c6587c1

Reviewed: 11 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.