CtrlK
BlogDocsLog inGet started
Tessl Logo

mcp-builder

MCP (Model Context Protocol) server and client engineering. Protocol design, schemas, transports, extensions, security, and migration.

60

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/mcp-builder/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a well-structured, concise, and actionable MCP engineering reference that assumes competence and includes validation checkpoints via its testing and review sections. It scores consistently at 4, held below 5 by mild framing verbosity, the absence of runnable code, and the lack of any external reference-file split.

Suggestions

Trim the opening blockquote and ASCII architecture diagram, and de-duplicate rules repeated between the migration checklist and earlier sections, to push conciseness toward 5.

Add a short explicit validate→fix→retry loop to the §8 migration checklist (e.g., 'after each change, re-run the §9 contract/security tests; only proceed when green') to lift workflow clarity to 5.

Optionally split the testing matrix and migration checklist into a references/ file and link to them from the overview to move progressive disclosure toward the overview-plus-references anchor 5.

DimensionReasoningScore

Conciseness

The body is dense, rule-oriented, and assumes competence ('Core requests are stateless and self-contained', terse tables) without explaining basics, but the opening blockquote, ASCII architecture diagram, and some repetition between the migration checklist and earlier sections are mild padding, keeping it just below the lean anchor 5.

4 / 5

Actionability

Concrete, specific directives an engineer can apply directly ('Servers must implement server/discover', 'Reject schemas with unresolved external references', 'reject loopback, link-local, and private addresses', specific codes -32002/-32602), but as an instruction-only skill it lacks runnable code/commands, so it sits below the copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

A clear sequenced flow exists (§8 migration checklist → §9 testing matrix → §10 review checklist) with validation checkpoints present, so the destructive-operation cap does not apply; it falls short of anchor 5 only because the migration steps lack an explicit validate→fix→retry feedback loop.

4 / 5

Progressive Disclosure

Well-organized into 10 clearly headed numbered sections with tables and no nested references, but as a ~200-line single self-contained file with no external reference split it matches the good-structure anchor 4 rather than the overview-plus-one-level-references anchor 5.

4 / 5

Total

16

/

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 specific and highly distinct, naming a clear MCP engineering niche with strong natural trigger terms. Its main weakness is the missing 'Use when' trigger clause in the description field itself, which caps completeness at 3.

Suggestions

Append an explicit 'Use when' clause to the description (e.g., 'Use when building or reviewing MCP servers/clients, designing MCP tools/resources/prompts, migrating protocol versions, or validating MCP security') to lift completeness above 3.

Add concrete verb-led actions and natural synonyms (tool, resource, prompt design) to push specificity and trigger-term quality from 4 to 5.

DimensionReasoningScore

Specificity

Quotes 'server and client engineering' and 'Protocol design, schemas, transports, extensions, security, and migration' — six named activity areas, but framed as activity nouns rather than verb-led concrete actions, placing it just below the comprehensive anchor 5.

4 / 5

Completeness

The description field has a clear 'what' but no 'Use when...' trigger clause; per the rubric a missing explicit trigger clause caps completeness at 3, so it cannot reach anchor 4.

3 / 5

Trigger Term Quality

Includes natural technical terms a user would say ('MCP', 'Model Context Protocol', 'server', 'client', 'schemas', 'transports', 'security', 'migration') with good coverage, but misses some natural synonyms like tool/resource/prompt design, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

'MCP (Model Context Protocol) server and client engineering' names a sharply defined, specialized protocol niche with minimal overlap risk, matching the clear-niche anchor 5.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
vudovn/ag-kit
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.