Claude Code — "claude", "CLAUDE.md", ".claude/rules", "paths"
All / unknown — "rules", "instructions", "set up AI rules", or no editor specified
Route directly on detected intent. No editor specified → run all three agents.
Loading behavior
Load ONLY the routed agent file. Each agent carries the full workflow and references .system/fusion-rule-author/ assets and templates on demand. Don't preload all agents.
Multi-editor workflow
When targeting multiple editors:
Run first agent's scan and interview (Steps 1–3) in full
Pass scan summary + interview answers as context to remaining agents — they skip Steps 1–3 and start at Step 4 (Classify)
Each agent drafts, reviews, and writes files for its own editor format
Generate parallel files with equivalent content — no duplication within a single editor
What this skill does NOT do
Author skills (SKILL.md) — use fusion-skill-authoring
Author agent definitions (.agent.md) — separate concern
Write CI checks for rule validation — out of scope
Migrate entire legacy codebases — incremental adoption only
Safety
No secrets or credentials in rule files
No overwrites without showing diff and getting approval
No invented conventions — only document what the developer confirms
1---2name: equinor-fusion-skills-fusion-rules3description: Fusion Rules4---56# Fusion Rules78Gateway for AI coding assistant rule authoring. Detects the target editor and routes to the right agent.910## Routing1112| Intent | Agent |13|--------|-------|14| Set up GitHub Copilot instructions / rules | `agents/copilot.agent.md` |15| Set up Cursor project rules | `agents/cursor.agent.md` |16| Set up Claude Code rules / CLAUDE.md | `agents/claude-code.agent.md` |17| Set up rules for all editors / mixed team | Run all three agents sequentially |18| Review or improve existing rules | Route to the agent matching the file format |1920## Intent detection2122Detect target editor from the request:2324- **Copilot** — "copilot", "copilot-instructions", ".github/instructions", "applyTo"25- **Cursor** — "cursor", ".cursor/rules", "mdc", "alwaysApply", "globs"26- **Claude Code** — "claude", "CLAUDE.md", ".claude/rules", "paths"27- **All / unknown** — "rules", "instructions", "set up AI rules", or no editor specified2829Route directly on detected intent. No editor specified → run all three agents.3031## Loading behavior3233Load ONLY the routed agent file. Each agent carries the full workflow and references `.system/fusion-rule-author/` assets and templates on demand. Don't preload all agents.3435## Multi-editor workflow3637When targeting multiple editors:38391. Run first agent's scan and interview (Steps 1–3) in full402. Pass scan summary + interview answers as context to remaining agents — they skip Steps 1–3 and start at Step 4 (Classify)413. Each agent drafts, reviews, and writes files for its own editor format424. Generate parallel files with equivalent content — no duplication within a single editor4344## What this skill does NOT do4546- Author skills (`SKILL.md`) — use `fusion-skill-authoring`47- Author agent definitions (`.agent.md`) — separate concern48- Write CI checks for rule validation — out of scope49- Migrate entire legacy codebases — incremental adoption only5051## Safety5253- No secrets or credentials in rule files54- No overwrites without showing diff and getting approval55- No invented conventions — only document what the developer confirms56- Show drafts before writing any files5758---59> Source: [equinor/fusion-skills](https://github.com/equinor/fusion-skills) — distributed by [TomeVault](https://tomevault.io).60<!-- tomevault:4.0:skill_md:2026-06-16 -->
Run npx skillmds@latest add tomevault-io/equinor-fusion-skills-fusion-rules in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Fusion Rules It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: CAUTION, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.