Skill — The Sundial Meta-Skill

Find, install, create, improve, and publish skills via Sundial Hub.

Agent Detection

Detect the current agent from the skill's load path to set the correct CLI flag:

.claude/ in path → --claude (default)
.cursor/ in path → --agent cursor
.windsurf/ in path → --agent windsurf
Other → --claude

Store the detected flag as AGENT_FLAG for use in CLI commands below.

Find & Install Skills

Searching

Run:

npx sundial-hub find "QUERY" --json --limit 10

Parse the JSON output array. Each result contains: name, author, description, installs, safety, url.

Present results as a numbered list:

1. author/skill-name — Description (installs: N, safety: LEVEL)
   https://sundialhub.com/skills/author/skill-name
2. ...

If no results: "No skills found. Browse all at https://sundialhub.com"

Installing

Ask the user: project scope (local to this project) or global scope (available everywhere)?

For global install:

npx sundial-hub add --yes --global AGENT_FLAG author/skill-name

For project install:

npx sundial-hub add --yes AGENT_FLAG author/skill-name

After install, show the skill's hub page URL.

Create a Skill

Ask the user what the skill should do and gather concrete usage examples
Ask: project scope or global scope?
Read references/skill-creation-guide.md for full guidance on skill anatomy, frontmatter spec, body writing, and design patterns
Create the skill directory with SKILL.md containing proper frontmatter (name + description) and markdown body
Add any needed scripts/, references/, or assets/ subdirectories

Validate by running:

bash scripts/validate_skill.sh PATH_TO_SKILL

Tell the user: "Publish when ready using the publish workflow below"

For workflow patterns, also consult references/workflows.md and references/output-patterns.md.

Improve a Skill

Locate the SKILL.md to evaluate
Read references/improvement-rubric.md for the full evaluation framework
Evaluate the skill across three layers:
- Spec checks (7 pass/fail checks): SKILL.md exists, valid frontmatter, required fields, naming conventions, allowed fields, description constraints
- Best practices (scored out of 100): line count, XML tags, README absence, description structure, actionable instructions, error handling, resource references, trigger phrases, examples
- Expert review (qualitative): progressive disclosure, conciseness, freedom calibration
Present findings as a structured report with the score and specific change recommendations
After user approval, implement the suggested changes

Publish a Skill

Check Authentication

npx sundial-hub auth status

If not authenticated, prompt the user to run:

npx sundial-hub auth login

They can also manage tokens at https://sundialhub.com/settings#tokens

Validate First

bash scripts/validate_skill.sh PATH_TO_SKILL

All checks must pass before publishing.

Gather Publish Details

Ask the user for:

Version (semver, e.g. 1.0.0)
Changelog (brief description of changes)
Visibility: public or private
Categories (e.g. Coding, Writing, Productivity)

Push to Sundial Hub

For a new skill:

npx sundial-hub push SKILL_PATH --version VERSION --changelog "MESSAGE" --visibility public --categories Cat1 Cat2

For an existing skill update:

npx sundial-hub push SKILL_PATH --version VERSION --changelog "MESSAGE"

After publishing, show:

Published skill URL
Share URL (the .md link)

Troubleshooting

npx sundial-hub not found: Ensure Node.js 18+ is installed
Auth failures: Run npx sundial-hub auth login or check https://sundialhub.com/settings#tokens
Validation failures: Run bash scripts/validate_skill.sh SKILL_PATH and fix reported issues
Publish errors: Ensure all spec checks pass and you have write access

skill