mcporter

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Quality

81%

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

Quality

Content

87%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.

The body is an exemplary lean command reference: every token is an executable command, syntax variants are covered concretely, and structure is clean for a single-file skill. The only weakness is the absence of verification checkpoints around destructive operations (config removal, logout, auth reset, daemon restart).

Suggestions

Add a validation step for config/auth mutations, e.g. 'After config add/remove or auth changes, verify with `mcporter config list` / `mcporter list <server> --schema`.'

Note that `auth --reset` and `config remove` are destructive and should be confirmed with the user before running.

Show how to check `mcporter daemon status` after `daemon restart` to confirm the restart succeeded.

Dimension	Reasoning	Score
Conciseness	A lean command cheat-sheet: every line is an executable command or a genuinely useful note ('Prefer `--output json` for machine-readable results'), with zero conceptual padding or explanation of things Claude already knows. Not 4: there is nothing left to trim.	5 / 5
Actionability	Fully executable, copy-paste-ready commands covering the common cases — five distinct call syntaxes (selector, function, full URL, stdio, JSON payload) plus auth, config, daemon, and codegen invocations with realistic arguments ('linear.list_issues team=ENG limit:5'). Not 4: no gaps in the concrete guidance.	5 / 5
Workflow Clarity	Sequencing is implicit in the section organization (quick start → call → auth/config → daemon → codegen), but the skill includes destructive operations — 'config remove', 'logout', 'auth ... --reset', 'daemon restart' — with no validation or verification steps, which caps workflow clarity at 3 per the guidelines. Not 4: the destructive-operation cap takes precedence; not 2: the steps that are present are concrete and coherent.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no external references needed — no references/, scripts/, or assets/ bundle files exist and the body points to none — and its well-organized sections (Quick start, Call tools, Auth + config, Daemon, Codegen, Notes) satisfy the simple-skill guideline for a top score. Not 4: nothing is inlined that belongs in a separate file.	5 / 5
	Total	18 / 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.

The description is highly specific and distinctive, enumerating concrete capabilities without fluff, but it omits any 'Use when...' trigger clause, which both caps completeness and slightly weakens natural trigger-term coverage. Adding an explicit usage-trigger sentence with common synonyms would bring it to the top band.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user wants to call, list, or authenticate against MCP (Model Context Protocol) servers or tools directly from the shell.'

Include common synonyms/extensions in the description — 'Model Context Protocol', 'MCP client', 'tool call', '.mcp.json' — so users phrasing the need differently still match.

Clarify the ad-hoc server use case in trigger form, e.g. 'Use when spinning up or testing an MCP server without registering it in config.'

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'list, configure, auth, and call MCP servers/tools directly (HTTP or stdio)', 'ad-hoc servers, config edits, and CLI/type generation' — with comprehensive coverage of the CLI's surface. Not 4: there are no minor gaps in the action inventory.	5 / 5
Completeness	Has a clear 'what' (the full list/configure/auth/call/generate capability set) but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4: the 'when' is entirely absent, not merely implicit.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('MCP servers/tools', 'call', 'auth', 'list') that users would actually say when needing this skill, but a few natural terms are missing — no spelled-out 'Model Context Protocol' or common synonyms like 'MCP client' or 'tool call'. Not 3: the core domain terms are present and well matched; not 5: synonyms/extensions are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche — a dedicated CLI for calling MCP servers/tools directly over HTTP or stdio — with distinct triggers unlikely to fire for unrelated skills. Not 4: no meaningful overlap with other skill domains.	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: huangruiteng/CS-Notes
Path: .trae/openclaw-skills/mcporter/SKILL.md
Commit: 77c775d

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.