fusion-skill-authoring

Creates or modernizes repository skills with clear activation cues, purposeful support files, and practical review loops. USE FOR: creating a new skill, tightening an existing skill, improving discovery wording, and structuring references/assets/optional helper agents when they genuinely add value. DO NOT USE FOR: product-code changes, routine copy edits outside skills/, or documentation that should not become an installable skill.

1.25x

Quality

81%

Does it follow best practices?

Impact

59%

1.25x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

75%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 well-structured, actionable authoring skill with a clear sequenced workflow and explicit safety/validation gates. The main weaknesses are mild internal redundancy, a generic validation-command step, and references to helper-agent files that are not present in the bundle.

Suggestions

Consolidate the helper-agent descriptions: list each agent once (either in Step 7 or the 'Optional helper agents' section) and remove the duplicated catalog.

Either include the four referenced agents/*.md files in the bundle or replace the file-path references with inline role descriptions so no paths dangle.

Tighten 'Core behavior to preserve' by pruning principles already implied by the numbered steps, to pull the file comfortably below the 300-line ceiling it advocates.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept-explanation filler Claude already knows, with concrete constraints ('Keep under 300 lines', 'Files over 500 lines fail CI'); docked one point because helper agents are described twice (Step 7 and the 'Optional helper agents' section) and 'Core behavior to preserve' restates principles already in the steps, and the file sits near its own 300-line ceiling.	4 / 5
Actionability	Highly concrete guidance — specific frontmatter rules (name 1-64 chars, lowercase/hyphens), folder-structure choices, description template example, and resolved asset/reference paths — but Step 7 validation ('Run validation supported by the target environment') stays generic with no concrete commands, leaving a minor gap.	4 / 5
Workflow Clarity	A clearly numbered 8-step sequence with a dedicated validation step, safety gates (installed-copy check, never/always list), and a checklist asset; the validate->fix->retry recovery loop is delegated to references/validation-signals.md rather than stated inline, a minor checkpoint gap.	4 / 5
Progressive Disclosure	Good overview-plus-one-level-deep structure with clearly signaled references that resolve (skill-template-baseline.md, validation-signals.md, follow-up-questions.md, skill-readiness-checklist.md), but the body names four agents/*.md files (scoper, reviewer, trigger-tuner, devils-advocate) that are absent from the bundle, creating navigation gaps despite the optional/runtime hedging.	4 / 5
	Total	16 / 20 Passed

Description

87%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 description that explicitly states both what it does and when to use it, with concrete positive and negative activation cues. The only weakness is that the action verbs lean slightly abstract rather than naming concrete operations.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Creates or modernizes repository skills', 'tightening an existing skill', 'improving discovery wording', 'structuring references/assets' — but the verbs stay higher-level/abstract ('modernizes', 'tightening') rather than concrete operations, with mild quality filler ('clear activation cues, purposeful support files').	4 / 5
Completeness	Explicitly answers both what ('Creates or modernizes repository skills...') and when via concrete USE FOR / DO NOT USE FOR trigger phrases, matching the anchor example.	5 / 5
Trigger Term Quality	Natural trigger phrases users would say are well covered ('creating a new skill', 'tightening an existing skill', 'improving discovery wording', 'product-code changes', 'copy edits'), plus explicit anti-triggers; a few natural synonyms (scaffold, template, catalog) are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche (skill authoring under skills/) with explicit DO NOT USE FOR boundaries for product-code, copy edits, and documentation yields minimal conflict with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 2 missing, 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: equinor/fusion-framework
Path: .agents/skills/fusion-skill-authoring/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.