# Create Skill

> Create canonical SKILL.md artifacts with deterministic schema, workflow, safety, and quality checks.

- **Type:** Skill
- **Install:** `agentstack add skill-msiccdev-ai-context-kit-create-skill`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [MSiccDev](https://agentstack.voostack.com/s/msiccdev)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [MSiccDev](https://github.com/MSiccDev)
- **Source:** https://github.com/MSiccDev/ai-context-kit/tree/development/skills/create-skill

## Install

```sh
agentstack add skill-msiccdev-ai-context-kit-create-skill
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Create Skill

## Purpose
Generate complete `SKILL.md` artifacts for one skill folder, with explicit constraints and reusable references.

## When To Use
- Use this skill when creating a new skill folder under `skills/`.
- Use this skill when regenerating a `SKILL.md` file to align with repository skill standards.
- Do not use this skill for validating an existing skill.

## How to Invoke

Load or attach this file's contents into your AI session to activate the workflow (paste, upload, or reference with `#file:skills/create-skill/SKILL.md` in VS Code Copilot Chat). In Claude Projects, add it to project knowledge. See [Invoking Skills](../../README.md#invoking-skills) in the README for full platform guidance.

## Required Inputs
- Skill slug (`name`) and target folder path.
- Capability summary and usage triggers.
- Required inputs, workflow outputs, and failure boundaries.
- Safety and portability constraints.

## Workflow
1. Run discovery sequence in `references/discovery-phases.md`.
2. Apply schema and field rules from `references/field-constraints.md`.
3. Assemble required body sections using `references/output-schema.md`.
4. Apply safety constraints from `references/safety.md`.
5. Produce final artifact using `references/output-format.md`.
6. Validate against `references/quality-checklist.md` before final output.

## Output Expectations
- One complete `SKILL.md` artifact at `skills/{name}/SKILL.md`.
- Frontmatter and folder-name parity are correct.
- Body sections are complete, actionable, and concise.
- Output remains provider-neutral and portable.

## Resources
- Discovery workflow: `references/discovery-phases.md`
- Field constraints: `references/field-constraints.md`
- Output schema: `references/output-schema.md`
- Safety policy: `references/safety.md`
- Output contract: `references/output-format.md`
- Quality checklist: `references/quality-checklist.md`
- Skill template: `../../templates/skill_template/SKILL.md`

## Constraints And Safety
- Keep skill instructions concise and execution-oriented.
- Avoid provider-specific lock-in wording.
- Use relative paths for local references.
- Treat `allowed-tools` as optional/experimental unless explicitly required.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [MSiccDev](https://github.com/MSiccDev)
- **Source:** [MSiccDev/ai-context-kit](https://github.com/MSiccDev/ai-context-kit)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-msiccdev-ai-context-kit-create-skill
- Seller: https://agentstack.voostack.com/s/msiccdev
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.