Find agent skills by outcome

if not re.match(r'^[a-z0-9-]+$'

name):

if not isinstance(name

str):

return False

Missing 'description' in frontmatter

name = frontmatter.get('name'

'')

return False

Missing 'name' in frontmatter

fUnexpected key(s) in SKILL.md frontmatter: {'

'.join(sorted(unexpected_keys))}.

fAllowed properties are: {'

'.join(sorted(ALLOWED_PROPERTIES))}

return False

fInvalid YAML in frontmatter: {e}

return False

(

ALLOWED_PROPERTIES = {'name'

'description'

return False

Frontmatter must be a YAML dictionary

return False

Invalid frontmatter format

if not isinstance(frontmatter

dict):

return False

SKILL.md not found

return False

No YAML frontmatter found

Writing & Content

match = re.match(r'^---\n(.*?)\n---'

content

For skills where output quality depends on seeing examples

provide input/output pairs:

Follow this style: type(scope): brief description

then detailed explanation.

Here is a sensible default format

but use your best judgment:

Use these patterns when skills need to produce consistent

high-quality output.

Productivity

For complex tasks

break operations into clear

Productivity

For tasks with branching logic

guide Claude through decision points:

Writing & Content

2. Plan reusable skill contents (scripts

references

When creating a new skill from scratch

always run the `init_skill.py` script: