CtrlK
BlogDocsLog inGet started
Tessl Logo

using-mcp

Discover, connect to, and invoke tools on MCP (Model Context Protocol) servers. CRITICAL - When the user message contains [@mcp:...] mention, you MUST load this skill first to use MCP tools correctly.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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-sequenced integration guide with executable code and clear validation checkpoints. It loses points on conciseness (redundant examples) and progressive disclosure (monolithic inline content with no reference files).

Suggestions

Consolidate the five mcp_add_server examples into one stdio and one http example, then show the auth-placeholder variants as a compact diff or inline comment, to cut redundancy and improve conciseness.

Move the detailed output_file_path guidance and the full add-server example set into a references/ file (e.g. REFERENCES.md) and link to it from the main body, so SKILL.md stays a lean overview and earns the progressive-disclosure score.

De-duplicate the discover/connect/schema/call flow: keep one canonical worked example and have the workflow section and pitfalls reference it rather than restating the same four steps.

DimensionReasoningScore

Conciseness

Largely efficient with no padding about concepts Claude already knows, but it repeats the discover/connect/schema/call sequence across the workflow, end-to-end example, and pitfalls, and includes five near-identical mcp_add_server snippets that could be consolidated.

2 / 3

Actionability

Provides fully executable run_sdk_snippet blocks with clearly marked <placeholder> substitution guidance, concrete parameter shapes, and copy-paste-ready examples for every operation.

3 / 3

Workflow Clarity

The standard workflow is an explicitly numbered sequence with status-based branching and concrete validation checkpoints ('ALWAYS check result.ok', 'if not connect.ok: raise SystemExit'), plus an error-recovery rule.

3 / 3

Progressive Disclosure

Sections are well-organized, but the skill is a single monolithic file with no bundle references, and detail that could live in a separate file (the five add-server variants, the output_file_path guidance) is kept inline.

2 / 3

Total

10

/

12

Passed

Description

90%

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 strong, specific description that states concrete capabilities and gives an explicit trigger condition. Its only blemish is the second-person 'you MUST' instruction, which the rubric penalizes on specificity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Discover, connect to, and invoke tools on MCP servers'), which would normally score 3, but the second-person phrasing 'you MUST load this skill first' triggers the rubric's one-point specificity penalty.

2 / 3

Completeness

Clearly answers both what it does (discover/connect/invoke MCP tools) and when to use it via the explicit trigger 'When the user message contains [@mcp:...] mention, you MUST load this skill first'.

3 / 3

Trigger Term Quality

Covers the natural terms a user would actually say when needing this skill — 'MCP', 'MCP servers', 'MCP tools', 'Model Context Protocol' — with good coverage of the domain's common variations.

3 / 3

Distinctiveness Conflict Risk

The MCP-server niche is distinct and the [@mcp:...] trigger is unlikely to fire for an unrelated skill, so conflict risk is low.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
dtyq/magic
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.