mm

Market making - two-sided quoting with inventory management

Quality

56%

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 ./src/skills/bundled/mm/SKILL.md

Quality

Content

79%

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

This is a well-crafted, actionable skill with excellent conciseness and concrete examples covering both CLI and programmatic usage. Its main weaknesses are the lack of validation/error-handling guidance in the workflow (what happens when orders fail, how to verify the MM is functioning correctly) and the absence of progressive disclosure to separate the detailed API reference and flag documentation from the core overview.

Suggestions

Add validation/error-recovery steps: what to check after starting (e.g., verify orders appear on book), how to diagnose common failures (insufficient balance, invalid market ID), and what auto-halt recovery looks like.

Split the API usage and detailed flags table into separate referenced files (e.g., API.md, CONFIG_REFERENCE.md) to keep SKILL.md as a concise overview with navigation links.

Dimension	Reasoning	Score
Conciseness	The content is lean and well-structured. It avoids explaining what market making is conceptually, assumes Claude understands trading concepts, and every section (flags table, examples, API) earns its place with concrete reference material.	3 / 3
Actionability	Provides fully concrete chat commands, a comprehensive flags table with defaults, multiple executable examples covering different scenarios, and a complete TypeScript API usage example with typed config. Copy-paste ready throughout.	3 / 3
Workflow Clarity	The 'How It Works' section provides a clear 6-step sequence of the internal logic, and examples show lifecycle commands (start/config/stop). However, there are no explicit validation checkpoints — no guidance on verifying orders were placed correctly, no error recovery steps if quoting fails, and no verification after config changes take effect.	2 / 3
Progressive Disclosure	The content is well-organized with clear sections (commands, flags, examples, API), but it's all inline in one file. The API usage section and the extensive flags table could be split into referenced files. No external references are provided despite the import paths suggesting a larger codebase.	2 / 3
	Total	10 / 12 Passed

Description

32%

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 a terse phrase that identifies the domain of market making but lacks concrete actions, explicit trigger guidance, and natural keyword variations. It reads more like a topic label than a functional skill description, making it difficult for Claude to confidently select this skill from a large pool. Adding a 'Use when...' clause and expanding the list of specific capabilities would significantly improve it.

Suggestions

Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks about market making strategies, bid-ask spread optimization, quote management, or inventory risk in trading.'

List specific concrete actions the skill performs, such as 'Calculates optimal bid-ask spreads, adjusts quotes based on inventory position, manages risk exposure, and simulates market making P&L.'

Include natural keyword variations users might say, such as 'bid-ask', 'spread', 'liquidity provision', 'order book', 'MM', 'hedging', and 'position management'.

Dimension	Reasoning	Score
Specificity	Names the domain (market making) and two specific concepts (two-sided quoting, inventory management), but doesn't list concrete actions like 'calculate bid-ask spreads', 'adjust quotes based on position', or 'manage risk limits'.	2 / 3
Completeness	Provides a brief 'what' (market making with two-sided quoting and inventory management) but completely lacks any 'when' clause or explicit trigger guidance, which per the rubric should cap completeness at 2, and the 'what' itself is quite thin, warranting a 1.	1 / 3
Trigger Term Quality	Includes relevant terms like 'market making', 'quoting', and 'inventory management' that a user in this domain might use, but misses common variations like 'bid-ask spread', 'order book', 'liquidity provision', 'MM strategy', or 'hedging'.	2 / 3
Distinctiveness Conflict Risk	The combination of 'market making' with 'two-sided quoting' and 'inventory management' is fairly specific to a niche domain, but could overlap with broader trading or quantitative finance skills without clearer boundaries.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: alsk1992/CloddsBot
Commit: e71a5f6

Reviewed: 2 months 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.