fusion-skills

Entrypoint for all Fusion skill lifecycle operations. USE FOR: finding, installing, updating, syncing, or greenkeeping skills; setting up skill automation; creating or authoring a new skill; reporting a bug with a skill. DO NOT USE FOR: resolving GitHub issues, reviewing PRs, planning task breakdowns, or authoring GitHub issues — those are handled by other Fusion skills.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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 concise, well-structured orchestration skill body that routes by intent, signals on-demand references clearly, and includes safety guardrails. It is slightly below the top on actionability and progressive disclosure because routed agent files are referenced but not verifiable in the bundle and guidance is procedural rather than copy-paste code.

Suggestions

Include the referenced agents/*.agent.md files in the bundle (or note they live in a sibling skill) so progressive_disclosure references are all verifiable one level deep.

Add an explicit validate/verify checkpoint for the compound-intent sequential flow (e.g., 'confirm the first agent's output before passing it as context to the second') to strengthen workflow_clarity.

For the migration path, give a concrete copy-paste command pair (apm.yml edit + apm prune) rather than only quoting the user-facing message, to lift actionability toward anchor 5.

Dimension	Reasoning	Score
Conciseness	The body is lean — a routing table, terse bullets, and tightly written safety rules — with no concept-explaining padding; every section earns its tokens and assumes Claude's competence, matching anchor 5.	5 / 5
Actionability	Concrete, executable guidance is present: an intent-to-agent routing table, specific MCP intents, a verbatim single clarifying question, and a quoted migration command, but it is orchestration guidance rather than copy-paste code, fitting anchor 4 with minor gaps.	4 / 5
Workflow Clarity	The sequence (resolve intent, route, engage agent; compound intents run sequentially with loop-prevention) is clear with safety rules substituting for validation checkpoints, matching anchor 4; explicit validate-fix-retry loops are light but the skill delegates destructive work to sub-agents.	4 / 5
Progressive Disclosure	Good structure with well-signaled, one-level-deep, on-demand references ('skill-catalog.md' on MCP failure, 'sync-workflows.md' in setup mode) and an explicit 'Load ONLY the routed agent file' rule; the routed agents/*.agent.md files are not present in the bundle, leaving a minor organization gap that keeps it at 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

78%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, well-scoped orchestrator description that names concrete lifecycle operations, provides explicit USE FOR / DO NOT USE FOR trigger guidance, and stays in third person. The 'what' is slightly abstract and trigger synonym coverage could be richer, keeping it just below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete operations ('finding, installing, updating, syncing, or greenkeeping skills; setting up skill automation; creating or authoring a new skill; reporting a bug') with only minor coverage gaps, matching anchor 4 rather than 5 which expects fuller synonym/extension breadth.	4 / 5
Completeness	Explicitly answers both what ('Entrypoint for all Fusion skill lifecycle operations') and when ('USE FOR: ...'), but the 'what' is somewhat abstract and the trigger phrasing is less concretely user-quoted than the anchor 5 example, placing it at 4.	4 / 5
Trigger Term Quality	Natural user-said phrases like 'finding', 'installing', 'updating', 'syncing', 'creating or authoring', 'reporting a bug' give good coverage, but a few common variations are missing, fitting anchor 4 rather than the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	A clear Fusion-skill-lifecycle niche combined with an explicit 'DO NOT USE FOR' exclusion list minimizes conflict risk and gives distinct triggers, matching anchor 5; third-person voice is maintained so no penalty applies.	5 / 5
	Total	17 / 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-skills/SKILL.md
Commit: bf61e57

Reviewed: 20 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.