agent-payments
Agent skill for payments - invoke with $agent-payments
43
11%
Does it follow best practices?
Impact
100%
3.70xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-payments/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically underspecified. It provides no concrete actions, no trigger guidance, and no distinguishing details—just the word 'payments' and an invocation command. It would be nearly impossible for Claude to reliably select this skill from a pool of even a few related skills.
Suggestions
List specific concrete actions the skill performs, e.g., 'Processes payments, issues refunds, queries transaction history, generates invoices.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about payments, refunds, billing, invoices, transactions, or charges.'
Remove or de-emphasize the invocation syntax ('$agent-payments') and instead focus on describing capabilities and triggers that help Claude match user intent.
| 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 'what' is essentially absent beyond the word 'payments', and there is no 'when' clause or explicit trigger guidance whatsoever. Both dimensions are very weak. | 1 / 3 |
Trigger Term Quality | The only keyword is 'payments', which is generic. There are no natural user terms like 'pay', 'invoice', 'refund', 'transaction', 'billing', or file types. The '$agent-payments' invocation syntax is technical jargon, not a natural trigger. | 1 / 3 |
Distinctiveness Conflict Risk | 'Payments' is broad enough to conflict with any billing, invoicing, transaction, or financial skill. There is nothing to distinguish this skill's specific niche or scope. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
22%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 tool signatures, the majority of the content is descriptive padding about pricing tiers, earning opportunities, and quality standards that don't help Claude execute tasks. It lacks concrete workflows, validation steps, and executable examples beyond the basic tool call signatures.
Suggestions
Replace descriptive sections (credit earning opportunities, quality standards, cost optimization strategies) with concrete workflows showing step-by-step sequences, e.g., 'To process a payment: 1. Check balance with mcp__flow-nexus__check_balance(), 2. If insufficient, create payment link, 3. Verify payment completed, 4. Confirm updated balance.'
Add validation checkpoints and error handling for financial operations—e.g., what to do when a payment fails, how to verify a tier upgrade succeeded, how to handle insufficient credits.
Remove the persona description and responsibility lists; instead, lead with the tool reference and concrete usage patterns with expected outputs.
Move static reference data (pricing tiers, credit earning rates) into a separate reference file or condense into a compact table to reduce token usage in the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is highly 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 product documentation rather than actionable instructions. The persona preamble ('You are a Flow Nexus Payments Agent, an expert in...') and lists of responsibilities are padding. | 1 / 3 |
Actionability | The JavaScript code block provides concrete MCP tool calls with parameter examples, which is useful. However, the rest of the content is descriptive rather than instructive—it lists what the agent should do conceptually (e.g., 'Track credit usage and predict refill needs') without specifying how to execute those tasks or providing concrete workflows with expected outputs. | 2 / 3 |
Workflow Clarity | There are no clear multi-step workflows, no sequencing of operations, and no validation checkpoints. The numbered list under 'financial management approach' describes abstract responsibilities, not actionable steps. For payment processing and credit management—operations that involve financial transactions—the absence of any verification steps or error handling guidance is a significant gap. | 1 / 3 |
Progressive Disclosure | The content is organized into labeled sections which provides some structure, but it's essentially a monolithic document with no references to external files. Given the volume of content (pricing tiers, earning opportunities, optimization strategies), much of this could be split into reference files. However, there are no bundle files, so the inline approach is the only option—but the content could still be better organized with a concise overview. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
100%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/claude-flow
- Commit
9d4a9ea
- Reviewed
Table of Contents
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.