fastmcp-creator

Use when building, extending, or debugging FastMCP v3 Python MCP servers. Activates on FastMCP tool/resource/prompt creation, provider and transform implementation (CodeMode, Tool Search), auth setup (MultiAuth, PropelAuth, KeycloakProvider), client SDK usage, FastMCPApp and Generative UI server building, fastmcp-slim client-only installs, nginx reverse proxy deployment, Prefab Apps, OTEL observability, and testing. Grounded in local v3.3 docs — zero speculation.

Quality

89%

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

86%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 well-architected reference skill with excellent actionability and progressive disclosure: a tight overview routes to a verified bundle of one-level-deep references. The main weakness is inline time-sensitive version/release dating that competes with the token budget.

Suggestions

Move the dated release notes (e.g. "released 2026-03-30", "released 2026-05-15") out of the main Version Gating section into a clearly labeled changelog/deprecated area so the core content stays evergreen and token-lean.

Add an explicit validate→fix→retry feedback loop for at least one fragile operation (e.g. the deployment or migration flow) to lift workflow clarity from a routing matrix toward a true checkpointed workflow.

Tighten the Quick-Start section's inline prose (the 'Before deploying' paragraph) into a numbered pre-deploy checklist so the validation step reads as a structured checkpoint rather than a trailing sentence.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly tables/mermaid decision trees that earn their tokens with minimal concept re-explanation, but it carries time-sensitive dated release notes inline ("FastMCP 3.2 — released 2026-03-30", "3.3 — released 2026-05-15") rather than isolating them in a deprecated/old-patterns section, which the guideline says should penalize conciseness.	4 / 5
Actionability	Quick-Start Examples give copy-paste-ready executable Python with RULE annotations, the Trigger Matrix maps each user intent to a concrete v3 feature and reference file, and the mermaid diagrams specify exact constructor calls, fully covering the common cases per the 5 anchor.	5 / 5
Workflow Clarity	Decision trees and the Trigger Matrix provide a clear routing sequence, and there is an explicit validation checkpoint ("Before deploying: run in-process pytest using the in-memory Client transport"), but beyond that single checkpoint there is no full multi-step validate→fix→retry feedback loop, leaving it just below the 5 anchor.	4 / 5
Progressive Disclosure	SKILL.md is a lean overview that routes to 17 verified one-level-deep reference files via a Trigger Matrix and a dedicated Reference Files section, with decision logic inline and detail externalized, matching the 5 anchor for clear, well-signaled navigation.	5 / 5
	Total	18 / 20 Passed

Description

92%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 strong, specific description that clearly establishes a distinct FastMCP v3 niche with explicit what/when guidance. Its only weakness is a jargon-heavy trigger list that prioritizes internal feature names over natural user phrasing.

Dimension	Reasoning	Score
Specificity	The description lists many concrete actions ("building, extending, or debugging", "tool/resource/prompt creation", "auth setup (MultiAuth, PropelAuth, KeycloakProvider)", "nginx reverse proxy deployment", "OTEL observability, and testing") with comprehensive coverage of the skill's capabilities, matching the 5 anchor.	5 / 5
Completeness	It explicitly answers both "what" (the enumerated FastMCP v3 capabilities) and "when" ("Use when building, extending, or debugging FastMCP v3 Python MCP servers") with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	It opens with a natural "Use when building, extending, or debugging" trigger, but the bulk is dense technical jargon (CodeMode, MultiAuth, PropelAuth, KeycloakProvider, FastMCPApp) users would rarely say verbatim, so it falls just below the comprehensive-synonym bar of 5.	4 / 5
Distinctiveness Conflict Risk	The FastMCP v3 Python MCP-server niche and named v3 features create a clear, specific scope with minimal overlap risk against other skills, matching the 5 anchor.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Jamie-BitFlight/claude_skills
Path: plugins/fastmcp-creator/skills/fastmcp-creator/SKILL.md
Commit: c337daf

Reviewed: 3 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.