fusion-mcp

Explain what Fusion MCP is and guide users through setting it up when they need Fusion-aware MCP capabilities in Copilot workflows.

Quality

51%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/fusion-mcp/SKILL.md

Quality

Discovery

40%

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 too vague and relies on jargon ('Fusion-aware MCP capabilities') without explaining what concrete actions the skill performs. It lacks an explicit 'Use when...' clause and doesn't enumerate specific setup steps or capabilities, making it difficult for Claude to confidently select this skill over others.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Explains Fusion MCP architecture, walks through installation steps, configures server connections, and validates setup'.

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about Fusion MCP, wants to set up MCP servers for Copilot, or mentions Fusion integration/configuration'.

Define what 'Fusion-aware MCP capabilities' means in plain terms so the description is self-contained and distinguishable from other MCP or Copilot skills.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'explain what Fusion MCP is' and 'guide users through setting it up' without listing concrete actions. It doesn't specify what capabilities Fusion MCP provides, what setup steps are involved, or what 'Fusion-aware MCP capabilities' actually means.	1 / 3
Completeness	It partially answers 'what' (explain and guide setup) and has an implied 'when' ('when they need Fusion-aware MCP capabilities in Copilot workflows'), but there is no explicit 'Use when...' clause with clear trigger conditions. The when is embedded but not clearly delineated.	2 / 3
Trigger Term Quality	It includes some relevant keywords like 'Fusion MCP', 'Copilot workflows', and 'MCP capabilities', but these are fairly niche/technical terms. It misses natural variations users might say, such as 'install', 'configure', 'Fusion setup', or specific tool/integration names.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Fusion MCP' and 'Copilot workflows' provides some specificity, but the description is vague enough that it could overlap with other MCP-related or Copilot setup skills. The lack of concrete actions makes it harder to distinguish from general setup/configuration skills.	2 / 3
	Total	7 / 12 Passed

Implementation

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides a well-structured workflow for Fusion MCP setup with clear sequencing, explicit validation checkpoints, and symptom-mapped troubleshooting. Its main weaknesses are the lack of concrete, copy-paste-ready configuration examples (relying on external references that aren't bundled) and moderate verbosity in sections like 'When to use' and 'When not to use'. The progressive disclosure structure is reasonable but cannot be fully validated without bundle files.

Suggestions

Inline a minimal copy-paste-ready MCP configuration JSON block (e.g., the `"type": "http"` config with server URL) directly in the Instructions section rather than deferring entirely to `references/vscode-mcp-config.md`.

Trim the 'When to use' and 'When not to use' sections — Claude can infer most of these triggers from context; keep only the non-obvious boundaries like the `fusion-research` handoff note.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some sections that could be tightened. The 'When to use' trigger examples and 'When not to use' sections add moderate value but are somewhat verbose. The 'Required inputs' section is useful but the overall document could be more compact without losing clarity.	2 / 3
Actionability	The skill provides structured guidance with specific steps (e.g., run `initialize`, run `tools/list`, check `tools/call`), but lacks concrete executable code snippets or copy-paste-ready configuration blocks. It references `references/vscode-mcp-config.md` for the actual config but doesn't inline even a minimal example. The troubleshooting steps are specific but still somewhat descriptive rather than executable.	2 / 3
Workflow Clarity	The multi-step process is clearly sequenced: explain → setup → authenticate → validate → troubleshoot → bug report. The validation checklist in step 4 has explicit pass criteria, and the troubleshooting in step 5 is mapped to specific error symptoms with remediation steps. The bug report step includes a feedback loop for when setup fails.	3 / 3
Progressive Disclosure	References to `references/vscode-mcp-config.md`, `references/README.md`, and `assets/bug-report-template.md` are well-signaled and one level deep. However, no bundle files were provided to verify these exist, and the main SKILL.md is somewhat long with all content inline rather than splitting detailed troubleshooting or authentication flow into separate reference files.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	10 / 11 Passed

Repository: equinor/fusion-framework
Commit: 060e3af

Reviewed: about 8 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.