cow-swap

CoW Swap MEV-protected DEX aggregator. Batch auctions for best execution and surplus sharing.

Quality

52%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./public/skills/0xterrybit/cow-swap/SKILL.md

Quality

Discovery

40%

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 identifies a clear niche (CoW Swap protocol) with distinctive terminology, but reads more like a tagline than a functional skill description. It lacks concrete actions a user would perform and entirely omits trigger guidance ('Use when...'), making it difficult for Claude to know when to select this skill from a large pool.

Suggestions

Add a 'Use when...' clause with trigger terms like 'Use when the user asks about CoW Swap, token swaps, DEX trading, MEV protection, or batch auction orders'.

List specific concrete actions the skill enables, such as 'Place token swap orders, check order status, compare execution prices, and configure slippage settings'.

Include common user-facing synonyms and related terms like 'swap tokens', 'trade', 'DeFi', 'decentralized exchange', 'Ethereum' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (CoW Swap DEX aggregator) and mentions some features (batch auctions, MEV protection, surplus sharing), but doesn't list concrete user-facing actions like 'place trades', 'swap tokens', 'check order status'.	2 / 3
Completeness	Describes what the skill is about at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also weak, so this scores 1.	1 / 3
Trigger Term Quality	Includes relevant terms like 'CoW Swap', 'DEX aggregator', 'MEV-protected', and 'batch auctions', but misses common user terms like 'swap tokens', 'trade', 'DeFi', 'token exchange', 'Ethereum', or 'ERC-20'.	2 / 3
Distinctiveness Conflict Risk	CoW Swap is a very specific protocol/product, and terms like 'batch auctions', 'MEV-protected', and 'surplus sharing' create a clear niche that is unlikely to conflict with other skills.	3 / 3
	Total	8 / 12 Passed

Implementation

64%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a functional API reference skill with strong actionability through concrete curl examples covering the full CoW Swap order lifecycle. Its main weaknesses are the lack of an explicit multi-step workflow with validation checkpoints (e.g., verify token approval before order, validate quote before signing) and some verbosity in marketing-style content and reference tables that Claude doesn't need inline. The partner fee configuration is prominently featured but adds bulk.

Suggestions

Add an explicit numbered workflow section that sequences the steps (check allowance → get quote → display to user → sign → create order → poll status) with validation checkpoints between each step.

Remove or significantly trim the Features bullet list, Order Types table, and Order Status table — Claude already understands these concepts and can infer them from the API responses.

Integrate the Safety Rules directly into the workflow as validation checkpoints (e.g., after getting a quote, validate price impact before proceeding to order creation).

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient with concrete API examples, but includes some unnecessary content like the features bullet list (marketing-style), explanations of order types/statuses that Claude already knows, and the partner fee section is somewhat verbose with its breakdown and emoji-heavy formatting.	2 / 3
Actionability	Provides fully executable curl commands with proper variable substitution, jq output formatting, and covers the complete workflow from quote to order creation to status checking and cancellation. The commands are copy-paste ready with clear placeholder variables.	3 / 3
Workflow Clarity	The implicit workflow (get quote → create order → check status) is present but not explicitly sequenced with numbered steps or validation checkpoints. There's no feedback loop for handling failed quotes, expired orders, or verifying token approval before order creation. The safety rules section lists checks but doesn't integrate them into the workflow sequence.	2 / 3
Progressive Disclosure	Content is reasonably organized with clear sections, but it's a monolithic file with reference tables (error handling, order statuses, supported chains) that could be separated. Links to external docs are provided but there are no bundle files for advanced topics. The AppData structure section feels like it belongs in a reference file.	2 / 3
	Total	9 / 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 — 9 / 11 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

	Total	9 / 11 Passed

Repository: Demerzels-lab/elsamultiskillagent
Commit: f45fcb5

Reviewed: 22 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.