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

71%

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 ./.agents/skills/fusion-mcp/SKILL.md

Quality

Content

81%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, actionable instruction skill: it avoids teaching concepts Claude already knows, defers concrete config and payload detail to real reference files, and includes explicit validation and troubleshooting feedback loops. Remaining weaknesses are minor — some duplication between Instructions and Expected output, and imperfect signaling of the mcp-call-snippets.md reference.

Suggestions

State the validation checklist once (either in Instructions step 4 or Expected output) and cross-reference it from the other location to remove the duplicated pass-criteria text.

Add a direct link to references/mcp-call-snippets.md where verification or 'script snippets' are mentioned, so the JSON-RPC execution path is one click from the body.

The bug report template asks for 'Docker version' and 'MCP transport mode (stdio)' fields that contradict the hosted-server-only guidance in SKILL.md — align the template with the recommended setup path.

Dimension	Reasoning	Score
Conciseness	The body is efficient — tight lists, numbered steps, and appropriately deferred detail — with only minor redundancy: validation criteria appear in both Instructions step 4 and Expected output, and the 'When to use' triggers partially reprise the frontmatter description.	4 / 5
Actionability	Concrete guidance throughout: named tools ('initialize', 'tools/list', 'search'), a symptom-to-fix troubleshooting map ('401 Unauthorized → re-authenticate via VS Code account settings'), and pass criteria ('non-empty content or structuredContent'). The main gap is that mcp-call-snippets.md is only obliquely signaled ('script snippets when user asks') without a direct pointer, leaving the verification steps without an inline execution path.	4 / 5
Workflow Clarity	The workflow is clearly sequenced (explain → set up → authenticate → validate → troubleshoot → bug report) with explicit validation checkpoints and pass criteria in step 4, feedback loops via the documented troubleshooting order, and a checklist repeated in Expected output.	5 / 5
Progressive Disclosure	SKILL.md stays at overview size with real, verified one-level-deep bundle files and a References section linking references/README.md and assets/bug-report-template.md, plus inline pointers to references/vscode-mcp-config.md. Slightly below a 5 because mcp-call-snippets.md is reachable only through the README and a vague 'script snippets' mention rather than a clearly signaled link.	4 / 5
	Total	17 / 20 Passed

Description

62%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, in third person, and clearly answers what the skill does, but it undersells the skill's actual coverage (verification, troubleshooting, bug reporting) and its when-clause is circular rather than trigger-anchored. It is serviceable but sits below the strong examples that enumerate concrete actions alongside explicit user-facing triggers.

Suggestions

Enumerate the concrete actions the skill performs, e.g. 'Explain what Fusion MCP is, guide setup of the hosted production server in VS Code, verify the connection, and troubleshoot sign-in or tool errors.'

Replace the circular when-clause with explicit trigger phrases users would naturally say: 'Use when the user asks what Fusion MCP is, or wants to install, configure, or troubleshoot Fusion MCP in VS Code / Copilot.'

Add the missing natural keyword variations ('install', 'configure', 'VS Code') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Fusion MCP', 'Copilot workflows') and two concrete actions ('Explain what Fusion MCP is', 'guide users through setting it up'), but stops short of the fuller action inventory (install, configure, verify, troubleshoot) the skill actually covers.	3 / 5
Completeness	Both 'what' ('Explain what Fusion MCP is and guide users through setting it up') and 'when' ('when they need Fusion-aware MCP capabilities in Copilot workflows') are explicitly stated, but the when-clause is circular — a user unfamiliar with Fusion MCP cannot tell when they need it — so it could be more explicit and specific.	4 / 5
Trigger Term Quality	Natural phrases like 'what Fusion MCP is', 'setting it up', and 'Copilot workflows' are present, but common variations users would actually say — 'install', 'configure', 'troubleshoot', 'VS Code' — are missing.	3 / 5
Distinctiveness Conflict Risk	'Fusion MCP' is a clear niche trigger with minimal conflict risk, though the generic tail 'Fusion-aware MCP capabilities in Copilot workflows' leaves minor overlap with sibling skills like fusion-research or generic MCP-setup skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: equinor/fusion-framework
Path: .agents/skills/fusion-mcp/SKILL.md
Commit: e026972

Reviewed: 5 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.