agent-payments

Agent skill for payments - invoke with $agent-payments

3.70x

Quality

Does it follow best practices?

Impact

100%

3.70x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-payments/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is critically underspecified. It provides no concrete actions, no trigger guidance, and no distinguishing details—just a vague domain label ('payments') and an invocation command. It would be nearly impossible for Claude to reliably select this skill from a pool of similar skills.

Suggestions

List specific concrete actions the skill performs, e.g., 'Processes payment transactions, issues refunds, queries payment status, and manages recurring billing.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about processing payments, checking transaction status, issuing refunds, or managing invoices.'

Include natural keyword variations users might say, such as 'pay', 'charge', 'refund', 'transaction', 'billing', 'invoice', '.payment' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description says 'Agent skill for payments' which is extremely vague. No concrete actions are listed—it doesn't describe what it does with payments (process them, refund them, query them, etc.).	1 / 3
Completeness	The description barely addresses 'what' (just 'payments') and completely lacks any 'when' guidance. There is no 'Use when...' clause or equivalent explicit trigger guidance.	1 / 3
Trigger Term Quality	The only relevant keyword is 'payments', which is very generic. It lacks natural variations users might say like 'pay', 'invoice', 'charge', 'refund', 'transaction', 'billing', etc. The '$agent-payments' invocation syntax is technical jargon, not a natural trigger term.	1 / 3
Distinctiveness Conflict Risk	'Payments' is extremely broad and could overlap with billing skills, invoicing skills, financial reporting skills, or any other money-related skill. There is nothing to distinguish this from other payment-adjacent skills.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

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

This skill reads more like a product specification or marketing document than an actionable skill for Claude. While it provides useful MCP function signatures, the majority of the content is descriptive fluff about responsibilities, strategies, and pricing that doesn't help Claude execute specific tasks. Critical workflows for payment processing and credit management lack step-by-step sequences and validation checkpoints.

Suggestions

Replace the descriptive responsibility lists with concrete workflows: e.g., 'When a user asks to add credits: 1. Check balance with mcp__flow-nexus__check_balance() 2. Create payment link with mcp__flow-nexus__create_payment_link({amount}) 3. Confirm link was generated 4. Verify balance updated'

Remove the persona framing ('You are a...'), quality standards, and cost optimization strategy lists—these are either obvious to Claude or belong in separate reference files

Add expected return values and error handling for each MCP function call, so Claude knows what success/failure looks like

Move static reference data (pricing tiers, credit earning opportunities) to a separate REFERENCE.md file and link to it from the main skill

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive explanations of concepts Claude doesn't need spelled out (pricing tiers, credit earning opportunities, cost optimization strategies, quality standards). Much of this reads like marketing copy or a product spec rather than actionable instructions. The 'You are a...' persona framing and lists of responsibilities add significant token bloat.	1 / 3
Actionability	The toolkit section provides concrete function signatures with parameters, which is useful. However, the functions are presented as a reference list without context on when to use each one, error handling, or expected return values. The rest of the content is descriptive rather than instructive—listing strategies and responsibilities without executable guidance.	2 / 3
Workflow Clarity	There are no clear multi-step workflows for payment processing, credit management, or tier upgrades. The numbered list under 'financial management approach' describes abstract responsibilities, not sequenced steps. For financial operations involving payments and billing—inherently risky/destructive—there are zero validation checkpoints or error recovery flows.	1 / 3
Progressive Disclosure	All content is in a single monolithic file with no references to external documentation. Pricing tiers, credit earning details, cost optimization strategies, and quality standards could all be split into separate reference files. The content is a wall of lists with no clear navigation hierarchy.	1 / 3
	Total	5 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Commit: 398f7c2

Reviewed: 3 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.