clawrouter

Hosted-gateway LLM router — save 88% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 71 models from OpenAI, Anthropic, Google, DeepSeek, xAI, NVIDIA, and more. 5 free NVIDIA models included. Also exposes realtime market data (global stocks, crypto, FX, commodities), Twitter/X intelligence, prediction-market data across Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow + UMA oracle resolution + wallet identity & clustering, phone-number intelligence (carrier + SIM-swap fraud detection) plus AI-powered outbound voice calls (Twilio + Bland.ai), AND the Surf unified crypto data API (84 endpoints — CEX/DEX, on-chain SQL over 80+ ClickHouse tables, 100M+ labeled wallets, prediction markets, social/CT mindshare, news, VC fund intel) as built-in agent tools. Not a local-inference tool — prompts are sent to the blockrun.ai gateway.

Quality

75%

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

Fix and improve this skill with Tessl

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

Quality

Content

67%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.

The body is a well-structured, actionable reference with concrete commands and validation gating on the destructive real-money flow, and it navigates cleanly to sibling skills. Its main weakness is conciseness: routing internals, supply-chain, and key-storage detail could be trimmed or split into reference files.

Suggestions

Move the routing-scorer internals (15-dimension scorer, tier taxonomy) and the supply-chain integrity section into a referenced doc to slim the core SKILL.md.

Add at least one full invocation example for a representative data tool (e.g. a blockrun_predexon_* or blockrun_stock_price call with parameters and a sample response) to close the actionability gap.

Pull the bulk tool/price catalog into a references/ file (e.g. TOOLS.md) and keep SKILL.md as an overview with one-line summaries plus links, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with dense, useful tool/price tables and concrete commands, but sections like the routing-scorer internals, supply-chain integrity, and key-storage enumeration could be trimmed or moved; some explanatory padding ('Treat prompts the same way you'd treat prompts sent to any hosted LLM API') could be tightened.	3 / 5
Actionability	Provides copy-paste-ready install/setup commands, slash commands ('/cr-call +1<E.164> "<task>"'), and CLI invocations, plus exact tool names and prices; minor gaps in that most tools are tabulated without a full call-syntax example.	4 / 5
Workflow Clarity	Install→setup→use is a clear simple sequence, and the destructive real-money Polymarket flow has explicit validation gating ('confirm:true is hard-required', dry-run preview, per-order/session caps), so it avoids the destructive-cap; full flows are delegated to sibling skills.	4 / 5
Progressive Disclosure	Clearly signals one-level-deep references to sibling skills ('See the phone skill', 'the predexon skill', 'the polymarket-trading skill', 'the surf skill') and docs/routing-profiles.md with good section structure; the inlined bulk tool catalog is the main organization gap, and no bundle files ship in this skill's directory.	4 / 5
	Total	15 / 20 Passed

Description

82%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.

The description is richly specific with comprehensive trigger terms and a distinct niche, but it is an overstuffed run-on paragraph that lacks any explicit 'when to use' guidance and leans on an over-claim ('save 88%'). Completeness is capped at 3 because no 'Use when...' clause is present.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g. 'Use when routing prompts to the cheapest capable model, or when the user mentions LLM cost savings, blockrun, x402 USDC payments, or the bundled market/crypto/phone/prediction-market tools').

Split the single dense paragraph into a tight capability sentence plus a trigger sentence; move the long enumeration of data APIs into the body to reduce description bloat.

Soften the hard 'save 88%' claim or qualify the workload mix it is measured against, to avoid an over-claim that the body itself cautions against quoting per-tier.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model', 'exposes realtime market data', 'AI-powered outbound voice calls', 'on-chain SQL over 80+ ClickHouse tables' — covering the surface comprehensively.	5 / 5
Completeness	The 'what' is clear and detailed, but there is no explicit 'Use when...' clause or equivalent trigger guidance in the description, which caps completeness at 3 per the judging guideline.	3 / 5
Trigger Term Quality	Comprehensive natural-term coverage including 'LLM router', 'save 88% on inference costs', 'prediction-market', 'Polymarket', 'Kalshi', 'voice calls', 'SIM-swap fraud detection', 'crypto', 'wallet labels', though mixed with product-specific jargon.	5 / 5
Distinctiveness Conflict Risk	Highly specific to the blockrun.ai gateway / ClawRouter / x402 USDC niche with named providers and tools, giving it a clear niche and minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	12 / 16 Passed

Repository: BlockRunAI/ClawRouter
Path: skills/clawrouter/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.