Test command

Skill datamaker-kr/synapse-claude-marketplace/plugins/synapse-plugin-helper/skills/test-command

Run the `synapse-plugin-helper:test` workflow from the original Claude slash command. Use when the user asks to run a plugin action locally for testingFrom its SKILL.md

Install

npx -y skills add datamaker-kr/synapse-claude-marketplace --skill test-command

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.0 KB, 694 tokens by cl100k_base, as published. Nobody here has run it

synapse-plugin-helper:test Command Workflow

Codex Adaptation

Treat the user request or explicitly supplied text as the command arguments.
Use the available Codex file, search, terminal, and clarification capabilities that match the workflow.
Do not depend on Claude-only slash command variables or tool names.

Test Synapse Plugin Action

Run a plugin action in local mode for testing and development.

Arguments: the user request or explicit arguments

Workflow

Step 1: Validate Environment

Prerequisites check:

# Check synapse CLI
synapse --version 2>/dev/null || echo "ERROR: synapse-sdk not installed"

If not installed, guide user:

synapse-sdk가 설치되어 있지 않습니다.
설치: uv pip install synapse-sdk (또는 pip install synapse-sdk)

Project check:

Check current directory has config.yaml or synapse.yaml
Verify the action exists in the config
Check dependencies are installed

Step 2: Parse Arguments

$1 - Action name (required)
--params - Parameters as JSON string
--mode - Execution mode: local (default), task, job, or remote

If action name not provided:

Which action do you want to test? Available actions:
[List from config.yaml]

Step 3: Execute Test

Run the plugin action using Synapse CLI:

synapse plugin run [action-name] --mode local --params '{"key": "value"}'

Execution modes:

Mode	Description	Use Case
`local`	Direct Python execution	Development, debugging
`task`	Ray task execution	Integration testing
`job`	Full job execution	Pre-deployment validation
`remote`	Synapse backend execution	Requires `synapse login` + agent

Step 4: Display Results

Show:

Execution status (success/failure)
Output from the action
Any logged messages or metrics
Execution time

Step 5: Handle Errors

If action fails:

Display the error message
Show relevant stack trace
Suggest running /synapse-plugin:debug for detailed analysis
If config is out of sync, suggest /synapse-plugin:update-config

Examples

# Test train action with default params
/synapse-plugin:test train

# Test with specific parameters
/synapse-plugin:test train --params '{"epochs": 10, "batch_size": 32}'

# Test in task mode (uses Ray)
/synapse-plugin:test inference --mode task

# Test in remote mode (requires login + agent)
/synapse-plugin:test deploy --mode remote --params '{"version": "1.0.0"}'

Quick Troubleshooting

ModuleNotFoundError: Check requirements.txt and install dependencies
EntrypointError: Verify entrypoint path in config.yaml matches actual file
ValidationError: Check parameter types match Pydantic schema

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most test skills give in 694 tokens

Counted across 964 of the 1,571 authors here whose files we hold, read 2026-08-07

Close the browser when donein 55 of 964, across 12 files
Wait for network idle statein 51 of 964, across 6 files
Launch Chromium in headless modein 49 of 964, across 6 files
Use descriptive selectors for elementsin 49 of 964, across 6 files
Run provided scripts with help flag firstin 49 of 964, across 6 files
Add appropriate explicit waitsin 48 of 964, across 5 files
Use bundled scripts as black boxesin 46 of 964, across 3 files
Do not read script source codein 46 of 964, across 3 files
Use sync playwright for scriptsin 46 of 964, across 3 files
Inspect dom before executing actionsin 46 of 964, across 3 files
Run the full test suitein 37 of 964
Write the failing test firstin 29 of 964, across 23 files

Said here and by no other author read

treat user request as command arguments
check synapse CLI version
check for config file in current directory
verify action exists in config
prompt for action name if missing
run action via synapse CLI

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.