mcporter
Interact with MCP (Model Context Protocol) servers using the mcporter CLI. Use this skill when you need to list available MCP servers, view tool schemas, call MCP tools, manage OAuth authentication, or generate CLI wrappers and TypeScript types for MCP servers.
90
89%
Does it follow best practices?
Impact
88%
1.29xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 a strong skill description that clearly identifies the tool (mcporter CLI), the domain (MCP/Model Context Protocol servers), and provides an explicit 'Use this skill when...' clause with multiple specific trigger scenarios. It lists concrete actions and uses natural keywords that users working with MCP would employ.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: list available MCP servers, view tool schemas, call MCP tools, manage OAuth authentication, generate CLI wrappers and TypeScript types. These are all distinct, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Interact with MCP servers using the mcporter CLI') and when ('Use this skill when you need to list available MCP servers, view tool schemas, call MCP tools, manage OAuth authentication, or generate CLI wrappers and TypeScript types'). Has an explicit 'Use this skill when...' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'MCP', 'Model Context Protocol', 'mcporter', 'CLI', 'tool schemas', 'OAuth authentication', 'TypeScript types', 'MCP servers'. Good coverage of terms a user working with MCP would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — MCP server interaction via the mcporter CLI is highly specific and unlikely to conflict with other skills. The combination of MCP, mcporter, OAuth, and TypeScript type generation creates a clear, unique identity. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
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-structured CLI reference skill that excels at conciseness and actionability, providing concrete, executable commands across all sections without unnecessary explanation. Its main weaknesses are the lack of validation/verification steps (e.g., how to confirm a tool call succeeded or auth completed) and the absence of progressive disclosure for what is a moderately complex multi-feature tool.
Suggestions
Add validation/verification guidance after key operations, e.g., 'After `mcporter auth <server>`, verify with `mcporter auth <server> --status`' or show how to interpret output/errors from tool calls.
Consider splitting code generation and configuration management into separate referenced files (e.g., 'See [CODEGEN.md](CODEGEN.md) for full code generation guide') to keep the main skill focused on core tool calling.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It assumes Claude knows what MCP servers, CLI tools, OAuth, and TypeScript are without explaining any of these concepts. Every section delivers concrete commands without padding. | 3 / 3 |
Actionability | Every section provides copy-paste ready CLI commands with concrete examples including realistic arguments (e.g., team=ENG, limit:5, title="Bug"). Multiple syntax variants are shown with executable examples. | 3 / 3 |
Workflow Clarity | The Quick Start provides a clear 3-step sequence for basic usage, but there are no validation checkpoints or error recovery guidance. For operations like auth reset, config changes, or daemon management, there's no feedback loop (e.g., verify auth succeeded, check config after import). | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and logical grouping, but everything is inline in a single file. For a skill of this size (~80 lines) covering multiple distinct areas (calling tools, auth, config, daemon, codegen), some content could be split into referenced files for advanced topics like code generation or configuration management. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
47823e3
- 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.