fusion-code-conventions

Applies and explains code conventions across TypeScript, React, C#, and Markdown. Enforces naming rules, file naming patterns, TSDoc and XML doc standards, inline comment intent (the *why*, not the *what*), code structure, error handling, async patterns, and dead code policy. Also enforces ADR and contributor doc decisions, and flags decisions that appear stale or misaligned with current tooling. USE FOR: convention questions, code review against project standards, applying naming rules, auditing intent comments, checking TSDoc completeness, enforcing recorded ADR decisions, and flagging stale architectural decisions. DO NOT USE FOR: security vulnerability scanning, performance profiling, runtime debugging, or generating net-new code without a review target.

Quality

83%

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

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.

The body is a well-structured orchestrator that routes to per-language references and follow-up files with a clear multi-step workflow and safety gates. The main weakness is the missing agents/*.agent.md files that the routing table depends on.

Suggestions

Include the six agents/*.agent.md files referenced in the 'Agent modes' table and routing rules, or replace those references with inline guidance so navigation is not broken.

Trim the 'When not to use' section since it duplicates the DO NOT USE FOR boundary already stated in the description, keeping only items not covered there.

Add a brief validation checkpoint in Step 4 (e.g., re-run the relevant language agent after edits) to close the minor feedback-loop gap in the correction phase.

Dimension	Reasoning	Score
Conciseness	The body is well-organized and assumes Claude's competence without explaining basic concepts, though the precedence list and the 'When not to use' section (which restates the description's DO NOT USE FOR) add minor padding that could be trimmed.	4 / 5
Actionability	Concrete routing rules map file extensions to specific agents and a clear Required/Recommended/Advisory findings taxonomy gives executable guidance; as an orchestrator skill it intentionally delegates detail to referenced docs rather than inlining code, with only minor gaps.	4 / 5
Workflow Clarity	A clear four-step sequence (Classify → Apply/explain → Present findings → Apply corrections) includes checkpoints ('If language cannot be determined, ask before proceeding' and 'Apply only corrections the user explicitly approves'), with only minor validation gaps in the correction phase.	4 / 5
Progressive Disclosure	Good one-level-deep structure with a well-signaled table pointing to real references/.conventions.md and assets/.follow-up.md files; the only gap is that the six agents/*.agent.md files referenced in the routing table do not exist in the bundle.	4 / 5
	Total	16 / 20 Passed

Description

92%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 concrete, comprehensive, and clearly answers both what the skill does and when to use it, with explicit boundaries reducing conflict risk. It is a strong, well-scoped description that mostly avoids fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across four languages — 'Enforces naming rules, file naming patterns, TSDoc and XML doc standards, inline comment intent… error handling, async patterns, and dead code policy' plus ADR/contributor enforcement — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' ('Applies and explains code conventions across TypeScript, React, C#, and Markdown…') and 'when' with concrete 'USE FOR'/'DO NOT USE FOR' trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger phrases in the 'USE FOR' clause ('convention questions', 'code review against project standards', 'auditing intent comments', 'flagging stale architectural decisions') plus a 'DO NOT USE FOR' boundary, though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (conventions for four named languages plus ADR/constitution), with an explicit 'DO NOT USE FOR' carve-out for security, performance, and debugging that minimizes overlap with adjacent skills.	5 / 5
	Total	19 / 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-code-conventions/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.