Automated summary
Automatically generates the standard boilerplate for a new BSage skill, including YAML, Python, and test files.
Strengths
- Reduces startup time for creating a new skill
- Provides category-appropriate default configurations (input, process, output, meta)
- Includes a unit test skeleton automatically
Limitations
- Generated code is generic and requires custom implementation
- Does not handle external dependency validation
When you need to quickly scaffold a new BSage skill with a consistent structure.
When modifying an existing skill or when your project does not use the BSage framework.
Security analysis
SafeThis skill is a meta-template generator that creates boilerplate files; it does not execute any system commands, network operations, or destructive actions. The provided examples are static and instructional, with no risk of code injection or exfiltration.
No concerns found
How this analysis is madeExamples
/skill input/calendar-input/skill process/garden-writer/skill output/git-outputname: skill description: Create a new BSage Skill with standard boilerplate
Skill Command
Generate a new Skill with standard structure and boilerplate.
Usage
/skill <category>/<skill-name>
Example
/skill input/calendar-input
/skill process/garden-writer
/skill output/git-output
/skill meta/skill-builder
What This Does
- Creates skill directory at
skills/<skill-name>/ - Generates skill.yaml with category-appropriate defaults
- Generates skill.py with
execute(context)boilerplate - Creates test file at
bsage/tests/test_skill_<name>.py
Generated Structure
For /skill input/calendar-input:
skills/
└── calendar-input/
├── skill.yaml # Metadata + trigger config
└── skill.py # execute(context) function
bsage/
└── tests/
└── test_skill_calendar_input.py
Generated Files
skills/calendar-input/skill.yaml
name: calendar-input
version: 1.0.0
author: bslab
category: input
is_dangerous: false
entrypoint: skill.py::execute
trigger:
type: cron
schedule: "*/15 * * * *"
rules:
- garden-writer
description: Google Calendar 일정을 2nd Brain으로 수집
skills/calendar-input/skill.py
from __future__ import annotations
async def execute(context):
"""Google Calendar 일정을 수집하여 seed로 저장."""
context.logger.info("calendar_input_start")
creds = await context.credentials.get("google-calendar")
# Skill 내부에서 직접 API 연결 처리
events = await fetch_calendar_events(creds)
await context.garden.write_seed("calendar", {"events": events})
context.logger.info("calendar_input_complete", event_count=len(events))
return {"collected": len(events)}
bsage/tests/test_skill_calendar_input.py
import pytest
from unittest.mock import AsyncMock, MagicMock
@pytest.fixture
def mock_context():
context = MagicMock()
context.logger = MagicMock()
context.credentials = MagicMock()
context.credentials.get = AsyncMock(return_value={"client_id": "test"})
context.garden = AsyncMock()
context.garden.write_seed = AsyncMock()
return context
@pytest.mark.asyncio
async def test_execute_collects_events(mock_context):
from importlib.util import spec_from_file_location, module_from_spec
spec = spec_from_file_location("skill", "skills/calendar-input/skill.py")
module = module_from_spec(spec)
spec.loader.exec_module(module)
result = await module.execute(mock_context)
assert result["collected"] >= 0
mock_context.garden.write_seed.assert_called_once()
Category Templates
InputSkill
category: input
trigger:
type: cron
schedule: "*/15 * * * *"
rules:
- garden-writer
ProcessSkill
category: process
is_dangerous: false # true if external side effects
OutputSkill
category: output
MetaSkill
category: meta
is_dangerous: false
Next Steps
After generation:
- Fill in skill.py implementation
- Update skill.yaml fields (rules, trigger)
- Add test cases for error paths
- Run tests with
/test - Verify Skill loads correctly with SkillLoader
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/generate-a-bsage-skill-boilerplate-mrwakeog/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/generate-a-bsage-skill-boilerplate-mrwakeog' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/generate-a-bsage-skill-boilerplate-mrwakeog/download' --output '.skill-downloads/generate-a-bsage-skill-boilerplate-mrwakeog/SKILL.md.part' && mv '.skill-downloads/generate-a-bsage-skill-boilerplate-mrwakeog/SKILL.md.part' '.skill-downloads/generate-a-bsage-skill-boilerplate-mrwakeog/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/generate-a-bsage-skill-boilerplate-mrwakeog/SKILL.md' && test -s '.skill-downloads/generate-a-bsage-skill-boilerplate-mrwakeog/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/skill' && cp -R '.skill-downloads/generate-a-bsage-skill-boilerplate-mrwakeog' '.claude/skills/skill'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/generate-a-bsage-skill-boilerplate-mrwakeog'openskills read 'generate-a-bsage-skill-boilerplate-mrwakeog'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/generate-a-bsage-skill-boilerplate-mrwakeog/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.