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

73%

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

76%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 lean, highly actionable command reference with excellent executable examples, weakened by a workflow that lacks validation steps and by reference-grade detail inlined in SKILL.md. Adding verification checkpoints (e.g., confirm the tool exists in the schema output before calling) and offloading reference detail to a references file would lift the weakest dimensions.

Suggestions

Add validation checkpoints to the durable-skill workflow, e.g., after `list <server> --schema`, verify the desired tool and its argument names appear in the JSON output before calling.

Move the auth/config, daemon, and codegen command reference into a `references/` file, keeping only the quick start and durable-skill workflow in SKILL.md.

Tighten the credential-handling section — the three long bullets can be compressed to rules without restating context Claude can infer.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense command lists that assume competence ("Selector: `mcporter call linear.list_issues team=ENG limit:5`"), but the credential-handling bullets and OpenClaw preamble run long and could be tightened.	4 / 5
Actionability	Commands are fully executable and copy-paste ready across all call modes (selector, function syntax, full URL, stdio, JSON payload) plus auth, config, daemon, and codegen — covering the common cases.	5 / 5
Workflow Clarity	The durable-skill workflow has a clear two-step sequence ("first inspect the server schema... Then call the selected tool with explicit arguments") but includes no validation checkpoints or error-recovery guidance.	3 / 5
Progressive Disclosure	No bundle files exist and the body (~85 lines) uses clear section headers; however, the auth/daemon/codegen reference detail and the long credential-handling section could be split into a references file rather than inlined.	4 / 5
	Total	16 / 20 Passed

Description

71%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 dense, highly specific description that comprehensively names the CLI's actions, but it lacks an explicit "Use when..." trigger clause and broader synonym coverage. Adding explicit trigger guidance would raise completeness substantially.

Suggestions

Add an explicit "Use when..." clause (e.g., "Use when the user wants to call or inspect an MCP server/tool, manage MCP config or auth, or build an MCP-backed skill").

Include common synonyms and file names users might say, such as "Model Context Protocol", "MCP client", or ".mcp.json".

Clarify the niche phrase "MCP-backed skills that need a durable command path" — it is jargon-heavy and weak as a trigger signal.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, CLI/type generation" — giving comprehensive coverage of the CLI's capabilities.	5 / 5
Completeness	The "what" is clearly stated (list, configure, auth, call MCP servers/tools), but there is no explicit "Use when..." clause; "MCP-backed skills that need a durable command path" only weakly implies when, capping completeness at 3.	3 / 5
Trigger Term Quality	Natural terms like "MCP servers/tools", "auth", "configure", "call", and "stdio" are present, but common variations such as "Model Context Protocol", "MCP client", or config file names are missing.	4 / 5
Distinctiveness Conflict Risk	Naming the specific CLI with transport modes carves a distinct niche, but generic MCP terms like "MCP servers/tools" carry minor overlap risk with broader MCP tooling skills.	4 / 5
	Total	16 / 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: 9bb1c42

Reviewed: 5 days 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.