fastmcp

Build, test, and deploy Python MCP servers.

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/mcp/fastmcp/SKILL.md

Quality

Content

83%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 content is highly actionable with a clear, validated multi-step workflow and good progressive-disclosure signaling, but it references a templates/ directory and three template files that are absent from the bundle, which breaks the scaffold workflow and undermines the otherwise strong structure.

Suggestions

Add the missing templates/ directory with api_wrapper.py, database_server.py, and file_processor.py (or remove those references from 'Included Files' and the scaffold instructions) so the bundle matches the documented structure.

Verify every path cited in the body (templates/*, scripts/scaffold_fastmcp.py, references/fastmcp-cli.md) exists; the scaffold script's TEMPLATE_DIR resolution currently points to a non-existent directory.

De-duplicate the 'pip install fastmcp / fastmcp version' block between Prerequisites and Troubleshooting to tighten conciseness toward 5.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient with actionable command blocks and tight pattern lists, assuming Claude knows Python/MCP basics, with only minor over-explanation (e.g. restating 'pip install fastmcp' in both Prerequisites and Troubleshooting).	4 / 5
Actionability	It provides copy-paste-ready, fully executable commands throughout (scaffold, inspect, list, call, run with HTTP transport, install targets) plus concrete good/weak tool-name examples, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The seven-step workflow is explicitly sequenced with validation checkpoints ('Always run at least one real fastmcp call before claiming the server works'), a dedicated Quality Bar checklist, and a feedback loop in Troubleshooting for CLI-vs-Python mismatches.	5 / 5
Progressive Disclosure	Structure and one-level-deep references (scripts/, references/fastmcp-cli.md) are well signaled, but the body advertises three templates under templates/ that do not exist in the bundle, and the scaffold script depends on that missing templates/ directory, so the actual bundle structure does not match what is referenced.	3 / 5
	Total	17 / 20 Passed

Description

51%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 and names concrete actions plus a clear domain, but it entirely omits any 'when to use' trigger guidance, which caps completeness and limits trigger-term quality. Adding an explicit 'Use when...' clause with natural trigger phrases would lift the two lower dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when creating a new Python MCP server, wrapping an API/database/CLI as MCP tools, or installing a server into Claude Code/Desktop/Cursor.'

Include natural synonyms and concrete triggers users would say (e.g. 'MCP server', 'model context protocol', 'wrap API as MCP tool', 'install MCP server') to improve trigger-term coverage.

Distinguish from sibling skills inline (e.g. 'Use native-mcp when the server already exists') to reduce overlap risk and push distinctiveness toward 5.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Python MCP servers') and lists three concrete actions ('Build, test, and deploy'), which matches the anchor for naming a domain plus 1-2 concrete actions but is not comprehensive enough for a 4.	3 / 5
Completeness	It clearly states what the skill does ('Build, test, and deploy Python MCP servers') but provides no 'when'/'Use when' trigger guidance at all, which the guidelines explicitly cap at 3.	3 / 5
Trigger Term Quality	It contains relevant natural terms ('Python', 'MCP servers') but lacks common variations, synonyms, or file/context triggers users might say, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Python MCP servers' carves a clear niche distinct from generic Python or other MCP skills, with only minor overlap risk against related skills like native-mcp; not a 5 because it lacks explicit distinguishing trigger phrasing.	4 / 5
	Total	13 / 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/fastmcp/SKILL.md
Commit: 6680afb

Reviewed: about 4 hours 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.