agent-agentic-payments

Agent skill for agentic-payments - invoke with $agent-agentic-payments

2.22x

Quality

Does it follow best practices?

Impact

100%

2.22x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-agentic-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 is an extremely weak description that functions more as an invocation instruction than a skill description. It fails on every dimension: it describes no concrete capabilities, includes no natural trigger terms, answers neither 'what' nor 'when', and provides no distinguishing characteristics. It is essentially unusable for skill selection among multiple options.

Suggestions

Add concrete actions the skill performs, e.g., 'Processes payments, handles refunds, manages subscriptions, and tracks transaction history.'

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

Remove the invocation instruction ('invoke with $agent-agentic-payments') from the description and replace it with functional content that helps Claude decide when to select this skill.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for agentic-payments' is entirely vague and does not describe what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states the invocation command, providing no functional or contextual information.	1 / 3
Trigger Term Quality	The only keyword is 'agentic-payments' which is technical jargon, not a natural term a user would say. There are no natural trigger terms like 'payment', 'invoice', 'charge', 'billing', etc.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it provides no clear niche. Without knowing what the skill does, it could conflict with any payment-related or agent-related skill.	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 marketing document or product overview than actionable agent instructions. It is bloated with explanatory content Claude doesn't need (security feature descriptions, use case lists, protocol name definitions) while lacking the critical workflow details, validation steps, and error handling that would make it operationally useful. The tool call examples provide some value but are undermined by the absence of concrete decision logic and chained workflows.

Suggestions

Remove the 'Real-world use cases', 'Security standards', and 'Payment protocol standards' sections entirely—these describe the product, not how to use it. Replace with a concise workflow showing when to use each tool.

Add explicit validation checkpoints and error handling to the workflow, e.g., 'After authorize_payment, check response status; if mandate_exceeded, inform user of remaining balance and options.'

Create a clear decision tree for when multi-agent consensus is needed vs. single-agent authorization, with specific threshold amounts and conditions.

Structure content with a quick-start section (create mandate → sign → authorize) and reference sections for advanced features (consensus, revocation), ideally split into separate files.

Dimension	Reasoning	Score
Conciseness	The skill is highly verbose with extensive explanatory text that Claude doesn't need. Sections like 'Real-world use cases you enable', 'Security standards' bullet points explaining what Ed25519 is, and 'Quality standards' are padding that don't add actionable value. The parenthetical explanations (e.g., '(prevents single compromised agent attacks)', '(zero-delay cancellation)') are unnecessary for Claude.	1 / 3
Actionability	The tool call examples with concrete parameters are helpful and mostly copy-paste ready, but they are illustrative rather than executable—there's no real workflow showing how to chain these calls together with actual decision logic. The code block is more of an API reference than actionable guidance for specific scenarios.	2 / 3
Workflow Clarity	The 6-step workflow is a high-level description without validation checkpoints or error handling. For a system involving cryptographic signing, payment authorization, and multi-agent consensus—all potentially destructive/irreversible operations—there are no feedback loops, no error recovery steps, and no explicit validation gates between steps.	1 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files and no clear separation between quick-start material and advanced/reference content. Everything from basic mandate creation to Byzantine consensus details is dumped into a single file with no navigation structure.	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: 619b263

Reviewed: about 10 hours 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.