Generate and update SKILL.md frontmatter and templates for AI agent skills.
npx skills add https://github.com/galligan/skillstash --skill skills-authoring
Please help me install this Agent Skill. Skill: skills-authoring Source: https://github.com/galligan/skillstash/tree/main/.agents/skills/skills-authoring Command: npx skills add https://github.com/galligan/skillstash --skill skills-authoring
Creates or updates skills with proper YAML frontmatter, progressive disclosure, and best practices per the open Agent Skills specification. Supports simple, tool-restricted, multi-file, and script-based skills. Use when creating new skills, authoring skills, extending agent capabilities, or when --create-skill or --new-skill flag is mentioned.
templates/:
simple-skill.md - Single SKILL.md filetool-restricted-skill.md - Limited tool accessmulti-file-skill.md - With supporting filesscript-based-skill.md - Includes executable scriptsreferences/, scripts/, or assets/ when neededtemplates/ (e.g., simple-skill.md).name in frontmatter.SKILL.md with frontmatter and instructions.references/, scripts/, or assets/ to extend capabilities.High-intent search queries and answers about installing and using this skill.
Create a skill by selecting a template from `templates/` (simple, tool-restricted, multi-file, or script-based), generate a kebab-case directory name matching the frontmatter `name` field, write SKILL.md with YAML frontmatter and instructions, then optionally add `references/`, `scripts/`, or `assets/` directories. The frontmatter must include name, description, and follow Agent Skills specification requirements.
Simple skills use a single SKILL.md file. Tool-restricted skills limit agent tool access. Multi-file skills include supporting files in `references/`, `scripts/`, or `assets/`. Script-based skills include executable scripts. Choose based on your skill's complexity and whether it needs external resources or tool constraints.
Keep SKILL.md lean with core instructions and frontmatter, then move detailed content to supporting files: `references/` for documentation, `scripts/` for executables, `assets/` for other resources. Progressive disclosure ensures the skill page remains scannable while details are available when needed, following Agent Skills specification best practices.
Skill authoring validates YAML frontmatter syntax, enforces third-person descriptions, requires trigger keywords, checks kebab-case naming conventions, verifies tool restrictions are compatible across tools, and ensures directory names match the frontmatter `name` field. Validation confirms compliance with the open Agent Skills specification.
Yes. The skill authoring process supports creating new skills and updating existing ones with proper frontmatter, progressive disclosure, and Agent Skills specification compliance. Use it when adding new agent capabilities or when flags like `--create-skill` or `--new-skill` are invoked.
Skill names must be lowercase kebab-case (hyphens only, no underscores or spaces) and the directory name must exactly match the `name` field in SKILL.md frontmatter. This ensures consistency and cross-tool compatibility within the Agent Skills ecosystem.
NoizAIProvide a reusable blueprint for authoring Agent Skills with structured documentation.
karchthoAutomate API testing across REST and GraphQL services with Postman MCP integration.
notqueCompare filesystem tools against README and docs to detect documentation drift.
vhqtvnCreate structured SKILL.md templates for reusable AI agent skills.