mcporter

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, CLI/type generation, and MCP-backed skills that need a durable command path.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/mcporter/SKILL.md

Quality

Content

82%Weight 40%Scale 1-5

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

A highly actionable, well-structured CLI skill body with copy-paste commands and a clear inspect-then-call workflow. Its main gaps are a missing validation/recovery checkpoint in the main workflow and references to bundle files that don't exist.

Suggestions

Add an explicit validation/verification step to the durable-skill workflow (e.g., after calling a tool, check the JSON output for an error field and retry with corrected args before proceeding).

Either create the referenced bundle files (mcp.json, references/, scripts/) or reword the 'Skill-first MCP shape' section so it does not read as a pointer to files that are absent.

Tighten the credential-handling bullets into shorter imperative sentences to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command lists and sectioned guidance that assumes Claude's competence (no explanation of what MCP or a CLI is); the credential-handling bullets are wordy with long compound sentences that could be tightened, keeping it just below the 'lean/every token earns its place' anchor.	4 / 5
Actionability	It provides copy-paste-ready, fully executable commands across the common cases — schema inspection, tool calls with selector/function/URL/stdio/JSON variants, auth, config, daemon, and codegen — matching the 'fully executable; covers common cases' anchor.	5 / 5
Workflow Clarity	The durable-skill workflow gives a clear, justified two-step sequence ('first inspect the server schema... Then call the selected tool with explicit arguments'), but it lacks an explicit validation/verification checkpoint or recovery loop, so it sits below the 5 anchor.	4 / 5
Progressive Disclosure	The body is well-organized into clear sections (Skill-first MCP shape, Credential handling, Quick start, Call tools, Auth + config, Daemon, Codegen, Notes) and self-contained; however, the references/scripts/mcp.json structure it describes does not exist as actual bundle files, so the signaled navigation is conceptual rather than real, keeping it below the 5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

75%Weight 40%Scale 1-5

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

A specific, well-scoped description tied to a named tool, but it lacks an explicit 'Use when...' trigger clause, which caps completeness. Adding concrete trigger phrases would raise the completeness and trigger-term dimensions.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when the user wants to call or configure an MCP server, inspect an MCP tool schema, or build a durable MCP-backed skill').

Include a few more natural synonyms users might say (e.g., 'MCP', 'model context protocol', 'MCP tools') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description lists many concrete actions — 'list, configure, auth, and call MCP servers/tools' plus 'ad-hoc servers, config edits, CLI/type generation' — giving comprehensive coverage of the tool's surface, matching the 'multiple specific concrete actions; comprehensive coverage' anchor.	5 / 5
Completeness	The 'what' is explicit ('Use the mcporter CLI to list, configure, auth, and call...') but there is no explicit 'Use when...' trigger clause; the 'when' is only weakly implied by 'MCP-backed skills that need a durable command path', so per the missing-trigger guidance it caps at 3.	3 / 5
Trigger Term Quality	Natural MCP-domain terms are present ('MCP servers/tools', 'call', 'auth', 'list', 'configure', 'HTTP or stdio') with good coverage, but it lacks a few common synonyms/variations a user might say, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	It names a specific CLI (mcporter) and a specific protocol (MCP servers/tools), carving a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: trpc-group/trpc-agent-go
Path: openclaw/skills/mcporter/SKILL.md
Commit: ba4a78e

Reviewed: 1 day 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.