clawrouter

Hosted-gateway LLM router — save 67% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 55+ models from OpenAI, Anthropic, Google, DeepSeek, xAI, NVIDIA, and more. 8 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

70%

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

72%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.

The body is a well-organized, actionable catalog with strong progressive disclosure to sibling skills and genuine safety controls on its real-money operations. Its weaknesses are verbosity (the inline model dump and dense pricing tables) and a catalog structure that lacks an explicit checkpointed end-to-end workflow.

Suggestions

Move the full 'Available Models' list and the dense per-call pricing tables into a referenced reference file or sibling skill, keeping SKILL.md to the headline routing tiers and a compact tool index.

Add a short numbered quick-start workflow (install → set routing → first call → verify savings) with an explicit verification checkpoint so the core flow reads as a sequenced process rather than a catalog.

Dimension	Reasoning	Score
Conciseness	The content is product-specific rather than Claude-known padding, but it is long: the giant inline 'Available Models' comma-dump and dense per-call pricing tables across many tool families could be tightened or offloaded. Not a level 3 because verbosity remains even though the detail is accurate; not a level 1 because it does not explain concepts Claude already knows.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands — 'openclaw plugins install @blockrun/clawrouter', 'openclaw models set blockrun/auto', the '/cr-call +1<E.164> "<task>"' slash form, and concrete CLI examples — plus a diagrammed data flow. Not a level 2 because the core install/setup/routing guidance is complete and executable rather than pseudocode.	3 / 3
Workflow Clarity	The install→setup→route sequence is present and real-money Polymarket ops carry genuine validate-then-execute controls ('confirm:true is hard-required… omit → dry-run preview', per-order/session caps), but the document is structured as a reference catalog rather than a sequenced workflow with explicit checkpoints for the general flow. Not a level 3 because there is no end-to-end checkpointed workflow; not a level 1 because risky ops do have stated safety/validation controls.	2 / 3
Progressive Disclosure	Keeps an overview inline while clearly signaling one-level-deep references to dedicated sibling skills ('See the `surf` skill for the full endpoint reference', 'See the `predexon` skill', 'the `polymarket-trading` skill'), with source links for verification. Not a level 2 because the references are clearly signaled and only one level deep rather than nested or ambiguous.	3 / 3
	Total	10 / 12 Passed

Description

67%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.

The description is highly specific and distinctive, clearly naming concrete capabilities and disambiguating itself from local-inference tools. Its main weakness is the absence of an explicit 'Use when…' trigger clause and a natural-keyword surface diluted by jargon, which cap completeness and trigger-term quality at 2.

Suggestions

Add an explicit 'Use when…' clause naming the user situations that should activate this skill (e.g., 'Use when you want to cut LLM inference costs via a hosted gateway, or need blockrun's market/phone/crypto data tools').

Surface a few more natural user-facing terms in the description ('openrouter alternative', 'cheapest LLM', 'sim swap check', 'crypto news') to offset the jargon-heavy capability list.

Dimension	Reasoning	Score
Specificity	Lists many concrete, specific actions and capabilities — 'forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model', 'exposes realtime market data', 'phone-number intelligence (carrier + SIM-swap fraud detection)'. Third-person voice is used throughout, so no voice penalty applies.	3 / 3
Completeness	Thoroughly answers 'what does this do' but provides no 'Use when…' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2. Not a level 3 because the 'when' is entirely missing rather than explicit.	2 / 3
Trigger Term Quality	Contains some natural keywords ('LLM router', 'inference costs', 'SIM-swap fraud detection', 'voice calls') but is heavily mixed with jargon ('UMA oracle resolution', 'wallet identity & clustering', 'ClickHouse tables', 'CT mindshare') and misses common user variations. Not a level 3 because the natural-term coverage is diluted by technical terminology; not a level 1 because relevant keywords are present.	2 / 3
Distinctiveness Conflict Risk	Blockrun/x402/USDC-wallet branding plus the explicit 'Not a local-inference tool — prompts are sent to the blockrun.ai gateway' disambiguation give it a clear, distinct niche unlikely to trigger for the wrong skill. Not a level 2 because the framing is highly specific rather than merely 'somewhat specific'.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 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

	Total	13 / 16 Passed

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