Tessl • The package manager for agent skills

The body is an exemplary lean command reference: fully executable examples, minimal prose, and logical section flow from setup through advanced usage. Its only notable gaps are the absence of validation/error-recovery guidance and reference-style sections that could be moved to bundle files for tighter progressive disclosure. Neither gap is severe given the skill's simplicity.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely executable commands with terse one-line comments; the only prose ("mcporter auto-discovers servers configured by other MCP clients (Claude Desktop, Cursor, etc.)") conveys non-obvious, tool-specific facts rather than concepts Claude already knows. Every token earns its place.	5 / 5
Actionability	Every section provides copy-paste-ready commands covering the common cases: listing with schema details, multiple call syntaxes (key=value, function, JSON payload, ad-hoc HTTP and stdio), auth, config management, daemon lifecycle, and code generation, plus the machine-readable `--output json` recommendation.	5 / 5
Workflow Clarity	The section ordering (Prerequisites → Quick Start → Discovering → Calling → Auth/Config → Daemon → Code Generation → Notes) gives a clear progression from setup to usage, and the Notes flag the interactive-auth pitfall. It falls short of a 5 because there are no explicit validation checkpoints or error-recovery guidance (e.g. what to do when a call fails or auth doesn't complete), though no destructive/batch operations trigger the cap at 3.	4 / 5
Progressive Disclosure	As a single self-contained file with no bundle directories, the skill is well-organized into clearly labeled sections and stays lean (~108 lines of terse reference). It is not a 5 because the auth/config, daemon, and code-generation sections are reference-style material that could be split into one-level-deep bundle files to keep SKILL.md as a tighter overview.	4 / 5
	Total	18 / 20 Passed

Description

70%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 concise, concrete, and clearly scoped to MCP server/tool operations, with good trigger terms and minimal conflict risk. Its main weakness is the absence of any "Use when..." trigger guidance, which caps completeness and leaves invocation conditions entirely implicit. Spelling out "Model Context Protocol" once would also improve keyword coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions MCP, Model Context Protocol, or wants to call/list tools on an MCP server from the terminal."

Spell out "Model Context Protocol" at least once so the skill triggers for users who say the full protocol name instead of "MCP".

Consider mentioning one or two more capabilities (e.g. "manage config") so the description's coverage matches the body's scope.

Dimension	Reasoning	Score
Specificity	"List, auth, and call" names three concrete actions against a specific domain ("MCP servers/tools from the terminal"), matching the anchor for several specific actions with minor gaps — coverage omits config, daemon, and code-generation capabilities present in the body. It is not a 5 because the action list is not comprehensive, and not a 3 because it goes beyond 1-2 actions.	4 / 5
Completeness	The "what" is clearly answered ("List, auth, and call MCP servers/tools from the terminal"), but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3. It is not a 2 because the "what" is concrete rather than vague.	3 / 5
Trigger Term Quality	"MCP servers/tools", "auth", and "call" are natural terms a user would say when needing this skill. It falls short of a 5 because the spelled-out "Model Context Protocol" and common synonyms like "connect" or "add an MCP server" are missing, but coverage is good rather than partial.	4 / 5
Distinctiveness Conflict Risk	The description targets a clear niche — MCP server/tool operations from the terminal — with distinct trigger terms ("MCP", "servers/tools", "auth"), making conflict with other skills minimal.	5 / 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: NousResearch/hermes-agent
Path: optional-skills/mcp/mcporter/SKILL.md
Revision: ed728c5

Reviewed: 17 days ago

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.

mcporter

Table of Contents

Is this your skill?