example-skill
npx machina-cli add skill MSiccDev/ai-context-kit/skill_template --openclawFiles (1)
SKILL.md
1.9 KB
Example Skill
Purpose
Describe the capability this skill provides and the problem it solves.
When To Use
- Use this skill when the task matches this domain.
- Do not use this skill for unrelated tasks.
Required Inputs
- List required information the assistant needs before applying this skill.
Workflow
- Confirm the task fits the skill scope.
- Gather only the inputs required for this workflow.
- Execute steps in order and verify outputs.
Output Expectations
- Define the expected output format and quality criteria.
- Include any acceptance checks.
Resources
references/for detailed docs loaded on demand.scripts/for optional automation or checks.assets/for reusable static artifacts.
Constraints And Safety
- Keep instructions concise in this file; move large material to
references/. - Use relative paths for all skill-local references.
- Mention risky operations explicitly and require confirmation before running them.
Frontmatter Rules
name(required):- 1-64 characters.
- Lowercase letters, numbers, and hyphens only.
- No leading/trailing hyphen.
- No consecutive hyphens.
- Must match the parent skill directory name.
description(required):- 1-1024 characters.
- Must state what the skill does and when to use it.
license(optional): short license identifier.compatibility(optional):- 1-500 characters.
- Use only for real environment constraints.
metadata(optional): map of string keys to string values.allowed-tools(optional/experimental):- Parseable if present.
- Keep disabled by default unless explicitly enabled by policy.
Source
git clone https://github.com/MSiccDev/ai-context-kit/blob/development/templates/skill_template/SKILL.mdView on GitHub Overview
example-skill helps determine if a task falls within its defined domain and guides the assistant through a structured workflow. It emphasizes collecting only required inputs, executing steps in order, and validating outputs against defined criteria.
How This Skill Works
Technically, the skill defines a confined workflow: confirm task fits the scope, gather only required inputs, and execute steps in order while verifying outputs. Output Expectations and acceptance checks govern the final results, with references to local resources when needed.
When to Use It
- Task clearly belongs to this skill's domain and scope.
- Need to validate task scope before taking action.
- You want to collect only inputs strictly required for the workflow.
- You want to enforce steps in order and verify outputs.
- You must confirm the results meet explicit acceptance criteria.
Quick Start
- Step 1: Confirm the task fits the skill scope.
- Step 2: Gather only inputs required for the workflow.
- Step 3: Execute steps in order and verify outputs against the Output Expectations.
Best Practices
- Confirm the task fits the skill scope before applying it.
- Gather only the inputs required for the workflow.
- Follow the defined steps in order and verify each output.
- Define and respect the Output Expectations and acceptance criteria.
- Reference local resources using relative paths and keep large material in references.
Example Use Cases
- Classify a user task to verify it matches the example-skill domain.
- Prompt the assistant to gather only required inputs before proceeding.
- Execute the stepwise workflow and validate outputs against acceptance checks.
- Provide a structured output using the defined Output Expectations.
- Refer to local resources via references/ and assets/.
Frequently Asked Questions
Add this skill to your agents
