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.

1.42x

Quality

84%

Does it follow best practices?

Impact

94%

1.42x

Average score across 2 eval scenarios

Securityby

Passed

No findings from the security scan

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 skill body is well-structured: a clear multi-step workflow with explicit validation gates, concise instruction over explanation, and clean progressive disclosure into one-level-deep references. The main gap is that referenced agents/*.md helper files are described in the body but not bundled, slightly weakening actionability and disclosure.

Suggestions

Either bundle the four referenced helper agents (agents/scoper.md, agents/reviewer.md, agents/trigger-tuner.md, agents/devils-advocate.md) or soften the body's references to mark them as optional/runtime-dependent so referenced paths always resolve.

Tighten Steps 1 and 7, which restate several constraints already covered in 'Core behavior to preserve' and 'Safety & constraints', to trim a few redundant tokens.

Add one fully executable validation command example in Step 7 (e.g., the catalog inventory/schema command) rather than only naming the validation class, to push actionability toward copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes agent competence throughout ('Prefer concise, specific instructions over background explanation'), with only minor instances of over-explanation; it does not reach the fully lean 5-anchor because some step descriptions could still be tightened.	4 / 5
Actionability	Provides concrete, executable guidance with real file paths, validation commands, and worked examples ('Use assets/follow-up-questions.md', 'check skills-lock.json'), with minor gaps where scripts/ and agents/ are described but not bundled.	4 / 5
Workflow Clarity	An explicit 8-step sequence with validation checkpoints and recovery loops (Step 7 validate -> review representative requests -> fix; installed-copy provenance check before editing) matches the top anchor for clear sequencing with feedback loops.	5 / 5
Progressive Disclosure	Content is well split into one-level-deep, clearly signaled references (references/skill-template-baseline.md, references/validation-signals.md, assets/), with content appropriately placed; it is just short of 5 because helper agents/.md files are referenced in the body but not present in the bundle.	4 / 5
	Total	17 / 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.

The description is strong: it states concrete capabilities, provides explicit USE FOR / DO NOT USE FOR trigger guidance, and carves out a distinct niche with anti-triggers that reduce conflict risk. It falls just short of top specificity and trigger-term breadth due to a few missing synonyms.

Dimension	Reasoning	Score
Specificity	Lists several specific concrete actions ('Creates or modernizes repository skills', 'clear activation cues', 'purposeful support files', 'practical review loops') with only minor gaps in coverage, fitting the 'lists several specific actions' anchor rather than the comprehensive 5-anchor.	4 / 5
Completeness	Explicitly answers both what (creates/modernizes skills with activation cues, support files, review loops) and when via concrete USE FOR / DO NOT USE FOR trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	USE FOR names natural phrases users would say ('creating a new skill', 'tightening an existing skill', 'improving discovery wording') with good keyword coverage, but a few natural synonyms are missing, so it sits just below the comprehensive 5-anchor.	4 / 5
Distinctiveness Conflict Risk	Clear niche scoped to skill authoring under skills/, with explicit DO NOT USE FOR anti-triggers (product-code changes, copy edits outside skills/) minimizing conflict risk, matching the distinct-niche top anchor.	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: 5b70066

Reviewed: 2 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.