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), client SDK usage, nginx reverse proxy deployment, Prefab Apps, and testing. Grounded in local v3.1 docs — zero speculation.
71
86%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies its niche (FastMCP v3 Python MCP servers), lists numerous specific capabilities and trigger terms, and opens with an explicit 'Use when...' clause. The description is information-dense without being verbose, and the named features (CodeMode, PropelAuth, MultiAuth, Prefab Apps) make it highly distinctive. The note about being grounded in local v3.1 docs adds useful context about the skill's reliability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: building/extending/debugging FastMCP v3 servers, tool/resource/prompt creation, provider and transform implementation with named examples (CodeMode, Tool Search), auth setup (MultiAuth, PropelAuth), client SDK usage, nginx reverse proxy deployment, Prefab Apps, and testing. | 3 / 3 |
Completeness | Explicitly answers both 'what' (building/extending/debugging FastMCP v3 Python MCP servers with specific capabilities listed) and 'when' (opens with 'Use when...' clause listing clear activation triggers). Also notes grounding in local v3.1 docs. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: FastMCP, MCP servers, tool/resource/prompt creation, auth, PropelAuth, MultiAuth, nginx reverse proxy, client SDK, Prefab Apps, testing, CodeMode, Tool Search. These are highly specific terms a developer working with FastMCP would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific technology (FastMCP v3) with named features (CodeMode, PropelAuth, MultiAuth, Prefab Apps) that are unlikely to overlap with any other skill. The niche is extremely clear. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured routing/index skill that excels at progressive disclosure and actionability, serving as an effective dispatch layer for a complex library. Its main weakness is the lack of explicit validation/verification steps in workflows — it delegates entirely to reference files without summarizing key checkpoints. The mermaid flowcharts, while visually helpful, consume significant tokens for information that could be more concisely expressed.
Suggestions
Add a brief validation/verification step to the quick-start examples (e.g., 'Run `fastmcp list server.py:mcp` to verify tools are registered') to improve workflow clarity.
Consider replacing the three mermaid flowcharts with compact decision tables to save tokens while preserving the same routing information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and diagrams, but the mermaid flowcharts add significant token cost for information that could be conveyed more compactly as decision tables. The version gating section and reference file listing are somewhat verbose, though they do provide useful information. | 2 / 3 |
Actionability | The quick-start examples are fully executable and copy-paste ready with correct Python syntax. The trigger matrix provides concrete file references for every use case, the v3 API corrections table gives specific wrong→right patterns, and the environment detection commands are immediately runnable. | 3 / 3 |
Workflow Clarity | The trigger matrix clearly sequences 'match intent → load reference file → build', and the decision flowcharts guide provider/transport/auth selection well. However, there are no explicit validation checkpoints or feedback loops for multi-step processes like server composition, deployment, or auth setup — the skill delegates entirely to reference files without summarizing verification steps. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: the SKILL.md serves as a concise routing layer with a trigger matrix pointing to 13+ well-organized reference files, all one level deep. Navigation is clear with both the table-based trigger matrix and the categorized reference file listing at the bottom. Related skills are also clearly signaled. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Jamie-BitFlight/claude_skills
- Commit
4e61312
- 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.