skill

Find, install, create, improve, and publish AI agent skills through the Sundial ecosystem. Use when the user wants to find or search for skills, install a skill, create a new skill, improve or evaluate an existing skill, or publish a skill to Sundial Hub. Trigger phrases include "find a skill", "install skill", "create a skill", "make a skill", "improve this skill", "evaluate skill", "publish skill", "push skill", "search for skills".

148 stars

Best use case

skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Find, install, create, improve, and publish AI agent skills through the Sundial ecosystem. Use when the user wants to find or search for skills, install a skill, create a new skill, improve or evaluate an existing skill, or publish a skill to Sundial Hub. Trigger phrases include "find a skill", "install skill", "create a skill", "make a skill", "improve this skill", "evaluate skill", "publish skill", "push skill", "search for skills".

Teams using skill should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/skill/SKILL.md --create-dirs "https://raw.githubusercontent.com/sundial-org/skills/main/skills/skill/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/skill/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How skill Compares

Feature / AgentskillStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Find, install, create, improve, and publish AI agent skills through the Sundial ecosystem. Use when the user wants to find or search for skills, install a skill, create a new skill, improve or evaluate an existing skill, or publish a skill to Sundial Hub. Trigger phrases include "find a skill", "install skill", "create a skill", "make a skill", "improve this skill", "evaluate skill", "publish skill", "push skill", "search for skills".

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Skill — The Sundial Meta-Skill

Find, install, create, improve, and publish skills via [Sundial Hub](https://sundialhub.com).

## 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:
```bash
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:
```bash
npx sundial-hub add --yes --global AGENT_FLAG author/skill-name
```

For project install:
```bash
npx sundial-hub add --yes AGENT_FLAG author/skill-name
```

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

## Create a Skill

1. Ask the user what the skill should do and gather concrete usage examples
2. Ask: project scope or global scope?
3. Read [references/skill-creation-guide.md](references/skill-creation-guide.md) for full guidance on skill anatomy, frontmatter spec, body writing, and design patterns
4. Create the skill directory with SKILL.md containing proper frontmatter (`name` + `description`) and markdown body
5. Add any needed `scripts/`, `references/`, or `assets/` subdirectories
6. Validate by running:
   ```bash
   bash scripts/validate_skill.sh PATH_TO_SKILL
   ```
7. Tell the user: "Publish when ready using the publish workflow below"

For workflow patterns, also consult [references/workflows.md](references/workflows.md) and [references/output-patterns.md](references/output-patterns.md).

## Improve a Skill

1. Locate the SKILL.md to evaluate
2. Read [references/improvement-rubric.md](references/improvement-rubric.md) for the full evaluation framework
3. 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
4. Present findings as a structured report with the score and specific change recommendations
5. After user approval, implement the suggested changes

## Publish a Skill

### Check Authentication

```bash
npx sundial-hub auth status
```

If not authenticated, prompt the user to run:
```bash
npx sundial-hub auth login
```
They can also manage tokens at https://sundialhub.com/settings#tokens

### Validate First

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

For an existing skill update:
```bash
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

## Links

- Browse skills: https://sundialhub.com
- CLI docs: `npx sundial-hub --help`
- Skill spec: [references/skill-creation-guide.md](references/skill-creation-guide.md)

Related Skills

cs448b-visualization

148
from sundial-org/skills

Data visualization design based on Stanford CS448B. Use for: (1) choosing chart types, (2) selecting visual encodings, (3) critiquing visualizations, (4) building D3.js visualizations, (5) designing interactions/animations, (6) choosing colors, (7) visualizing networks, (8) visualizing text. Covers Bertin, Mackinlay, Cleveland & McGill.

training-data-curation

148
from sundial-org/skills

Guidelines for creating high-quality datasets for LLM post-training (SFT/DPO/RLHF). Use when preparing data for fine-tuning, evaluating data quality, or designing data collection strategies.

tinker

148
from sundial-org/skills

Fine-tune LLMs using the Tinker API. Covers supervised fine-tuning, reinforcement learning, LoRA training, vision-language models, and both high-level Cookbook patterns and low-level API usage.

tinker-training-cost

148
from sundial-org/skills

Calculate training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.

skill-to-card

148
from sundial-org/skills

End-to-end workflow that creates a skill from a description and attached files, publishes it to Sundial as a private skill, generates a trading card (front + back with QR code), and sends it to a printer. Use when the user wants to create a skill and get a printed trading card, or says "skill to card", "create and print a skill card", "make me a skill with a card".

project-referee

148
from sundial-org/skills

Critiques ML conference papers with reviewer-style feedback. Use when users want to anticipate reviewer concerns, identify weaknesses, check claim-evidence gaps, or find missing citations.

neuro-symbolic-reasoning

148
from sundial-org/skills

Neuro-symbolic AI combining LLMs with symbolic solvers. Use when exploring neuro-symbolic approaches (ideation, no code) or implementing solver integrations (code).

icml-reviewer

148
from sundial-org/skills

Paper reviewer that evaluates machine learning research projects following official ICML reviewer guidelines. Provides comprehensive reviews with actionable feedback across all key dimensions: claims/evidence, relation to prior work, originality, significance, clarity, and reproducibility. Also provides formative feedback on incomplete drafts, proposals, and research code repositories. MANDATORY TRIGGERS: review paper, ICML review, paper review, evaluate paper, research paper feedback, ML paper review, conference review, academic review, paper critique, NeurIPS review, ICLR review, project proposal, research proposal, paper draft, early feedback, incomplete paper, work in progress, WIP review, review repo, review codebase, research project review

cs-research-methodology

148
from sundial-org/skills

Conduct a literature review and develop a CS research proposal. Use when asked to review a research area, find gaps in existing work, and propose a novel research contribution. The output is a research proposal identifying an assumption to challenge (the "bit flip") and how to validate it.

commit-splitter

148
from sundial-org/skills

Split large sets of uncommitted changes into logical, well-organized commits. Use when the user has many uncommitted changes and wants structured commits, or proactively suggest when detecting a large diff that would benefit from splitting.

codex

148
from sundial-org/skills

Run OpenAI's Codex CLI agent in non-interactive mode using `codex exec`. Use when delegating coding tasks to Codex, running Codex in scripts/automation, or when needing a second agent to work on a task in parallel.

ai-co-scientist

148
from sundial-org/skills

Transform Claude Code into an AI Scientist that orchestrates research workflows using tree-based hypothesis exploration. Triggers on "research project", "scientific experiment", "run experiments", "AI scientist", "tree search experimentation", "systematic study".