rulesync

Other Community

Repo stars 0
Author repo skills-registry

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: >- Use when this capability is needed. Rulesync generates and synchronizes AI rule configuration files across 20+ coding tools (…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Quick Start”, “Core Workflow”, “Key Commands”, “Detailed Reference”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name rulesync directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Quick Start / Core Workflow / Key Commands” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Rulesync

Rulesync generates and synchronizes AI rule configuration files across 20+ coding tools (Claude Code, Cursor, Copilot, Windsurf, Cline, Gemini CLI, and more) from a single set of unified rule files in .rulesync/.

Quick Start

# Install
npm install -g rulesync

# New project: initialize config, rules, and directory structure
rulesync init

# Import existing AI tool configs into unified format
rulesync import --targets claudecode    # From CLAUDE.md
rulesync import --targets cursor        # From .cursorrules
rulesync import --targets copilot       # From .github/copilot-instructions.md

# Generate tool-specific configs from unified rules
rulesync generate --targets "*" --features "*"

Core Workflow

Init - rulesync init creates rulesync.jsonc config and .rulesync/ directory with sample rules
Write rules - Add shared AI rules in .rulesync/rules/, MCP configs in .rulesync/mcp/, commands in .rulesync/commands/
Generate - rulesync generate produces tool-specific files (CLAUDE.md, .cursorrules, .github/copilot-instructions.md, etc.)
Verify - rulesync generate --dry-run previews changes; --check validates files are up to date (useful in CI)

Key Commands

Command	Purpose
`rulesync init`	Scaffold project with config and sample rules
`rulesync generate --targets "" --features ""`	Generate all tool configs from unified rules
`rulesync import --targets <tool>`	Import existing tool config into unified format
`rulesync fetch owner/repo --features skills`	Fetch rules or skills from a remote repository
`rulesync install`	Install skill sources declared in rulesync.jsonc
`rulesync generate --check`	CI check that generated files are up to date
`rulesync generate --dry-run`	Preview changes without writing files

Detailed Reference

Source: codekiln/beans — distributed by TomeVault.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: Other
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @tomevault-io · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Plug-and-play
External API key: No requirement detected
Detected OS requirements: macOS · Linux · Windows
Runtime requirements: Unspecified
Detected file/system behavior: Read-only
Write / modify
Detected network behavior: External requests
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview rulesync.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# Rulesync

Rulesync generates and synchronizes AI rule configuration files across 20+ coding tools (Claude Code, Cursor, Copilot, Windsurf, Cline, Gemini CLI, and more) from a single set of unified rule files in `.rulesync/`.

## Quick Start

```bash
# Install
npm install -g rulesync

# New project: initialize config, rules, and directory structure
rulesync init

# Import existing AI tool configs into unified format
rulesync import --targets claudecode    # From CLAUDE.md
rulesync import --targets cursor        # From .cursorrules
rulesync import --targets copilot       # From .github/copilot-instructions.md

# Generate tool-specific configs from unified rules
rulesync generate --targets "*" --features "*"
```

## Core Workflow

1. **Init** - `rulesync init` creates `rulesync.jsonc` config and `.rulesync/` directory with sample rules
2. **Write rules** - Add shared AI rules in `.rulesync/rules/`, MCP configs in `.rulesync/mcp/`, commands in `.rulesync/commands/`
3. **Generate** - `rulesync generate` produces tool-specific files (CLAUDE.md, .cursorrules, .github/copilot-instructions.md, etc.)
4. **Verify** - `rulesync generate --dry-run` previews changes; `--check` validates files are up to date (useful in CI)

## Key Commands

| Command                                          | Purpose                                          |
| ------------------------------------------------ | ------------------------------------------------ |
| `rulesync init`                                  | Scaffold project with config and sample rules    |
| `rulesync generate --targets "*" --features "*"` | Generate all tool configs from unified rules     |
| `rulesync import --targets <tool>`               | Import existing tool config into unified format  |

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> Quick Start → Core Workflow → Key Commands → Detailed Reference
terms    -> Init · Write rules · Generate · Verify
files/cmd -> .rulesync/ · rulesync init · rulesync.jsonc · .rulesync/rules/ · .rulesync/mcp/ · .rulesync/commands/ · rulesync generate · rulesync generate --dry-run
body sha256 -> a8daa273ea85