agent-agentic-payments
Agent skill for agentic-payments - invoke with $agent-agentic-payments
40
7%
Does it follow best practices?
Impact
100%
2.22xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-agentic-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 is an extremely weak description that essentially only provides an invocation command. 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.
Suggestions
Add specific 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 command from the description (it belongs elsewhere) and replace with functional content that helps Claude distinguish this skill from others.
| 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 overview or README for an agentic payments platform than an actionable skill for Claude. It is heavily padded with explanatory content about use cases, security features, and protocol descriptions that don't help Claude execute tasks. The tool call examples are the strongest element but lack error handling, response formats, and conditional logic needed for real-world use.
Suggestions
Remove the 'Real-world use cases', 'Security standards', 'Payment protocol standards', and 'Quality standards' sections entirely—these describe the system rather than instruct Claude on how to use it.
Add explicit validation checkpoints to the workflow: e.g., verify mandate signature after signing, check payment status after authorization, handle consensus timeout/failure scenarios.
Include expected response formats for each MCP tool call so Claude knows how to parse results and handle errors.
Restructure into a concise quick-start section with the most common flow (create mandate → sign → authorize → check status) and move multi-agent consensus and advanced features to a referenced file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Heavily verbose with extensive explanatory text Claude doesn't need. Sections like 'Real-world use cases you enable', 'Security standards', and 'Quality standards' are padded descriptions that don't provide actionable guidance. The 'Payment protocol standards' section explains concepts rather than instructing. Marketing-style language ('tamper-proof', 'zero-delay cancellation', '<1ms verification') wastes tokens. | 1 / 3 |
Actionability | The JavaScript code examples showing MCP tool calls with parameters are concrete and useful, but they are illustrative rather than executable—they show function signatures with example data but lack context on when to use each tool, error handling, or expected response formats. The workflow steps are descriptive rather than instructional. | 2 / 3 |
Workflow Clarity | The 6-step workflow is a high-level description without validation checkpoints or error recovery. For a system involving cryptographic signing, payment authorization, and multi-agent consensus—all potentially destructive/irreversible operations—there are no feedback loops, no 'if X fails, do Y' guidance, and no verification steps between stages. | 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 essentials and advanced topics. Everything from basic mandate creation to Byzantine consensus to security standards is dumped into a single flat document with no navigation structure. | 1 / 3 |
Total | 5 / 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.