skills.rest
SalesforceLabs
SalesforceLabsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

skill-authoring

Create, register, and validate AI-agent skills with discovery metadata and indexes.

5|3|Updated Sep 9, 2026
Search Tags:#documentation#markdown#validation#ai agents#skill authoring#yaml frontmatter#cursor rules
One-click install
npx skills add https://github.com/SalesforceLabs/revenue-cloud-foundations --skill skill-authoring-salesforcelabs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-authoring
Source: https://github.com/SalesforceLabs/revenue-cloud-foundations/tree/main/.cursor/skills/skill-authoring
Command: npx skills add https://github.com/SalesforceLabs/revenue-cloud-foundations --skill skill-authoring-salesforcelabs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Maintaining a library of AI-agent skills requires consistent structure, discovery metadata, and registration across multiple indexes and manifests; this Skill defines the full lifecycle so skills stay discoverable by Cursor, Claude Code, Copilot, Codex, and other file-capable agents. ## Core Features & Use Cases - Skill Lifecycle Guidance: Rules for creating, updating, splitting, and retiring skills, including required sections (Quick Rules, DO NOT, Entry Conditions, Examples, Validation Checks) and YAML frontmatter constraints. - Registration Checklists: Step-by-step updates for .cursor/skills/README.md, AGENTS.md, .claude/skill-manifest.yml, native discovery symlinks, and Cursor rules. - Validation Workflow: Commands such as python scripts/ai/analyze_agent_tooling.py check and skill_manifest.py --check to gate metadata, links, and byte ceilings before commit. - Use Case: When adding a new skill for pricing waterfall authoring, follow this Skill to create the entry point, register it in all indexes, add symlinks, and run the validation checks in one change. ## Quick Start Ask the agent to read the skill-authoring SKILL.md and create a new skill with proper frontmatter, registration, and validation checks.

Frequently Asked Questions about skill-authoring

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a new AI-agent skill in a repository?▼

Create a directory under .cursor/skills/ with a SKILL.md containing YAML frontmatter with name and description, plus Quick Rules, DO NOT, Entry Conditions, Examples, and Validation Checks sections. Then register it in the skill README, AGENTS.md, and the manifest.

What frontmatter does a SKILL.md file require?▼

SKILL.md requires YAML frontmatter with a name matching the directory (1-64 lowercase letters, digits, or hyphens) and a description of at most 1,024 characters describing the capability and task triggers. Plain, quoted, folded, and literal scalar styles are accepted.

When should I split a skill into sub-files?▼

Split a sub-file when the skill approaches a few hundred lines, when only some tasks need the content, or when material changes on a different cadence. Link each sub-file from the parent SKILL.md, since that list is the only registry.

Does this skill system work with agents other than Cursor?▼

Yes, skills are plain markdown readable by Claude Code, Copilot, Codex, Windsurf, and Aider. Native discovery uses directory symlinks in .agents/skills/ and .claude/skills/ pointing to the canonical .cursor/skills/ directories.

How do I validate skill changes before committing?▼

Run python scripts/ai/analyze_agent_tooling.py check to gate discovery metadata, symlink targets, and the AGENTS.md byte ceiling, plus skill_manifest.py --check when the manifest changes. Also verify index tables and plain-file readability for non-Cursor agents.

Related Skills

Explore More Software Engineering Skills→
brucebanner010198-commitsbrucebanner010198-commits

skill-creator

Author new agent and skill files using AGENTS.md templates.

Community
Advanced
junnv93junnv93

verify-implementation

Execute all registered verify-* skills sequentially and generate a unified verification report.

Community
Intermediate
ormastesormastes

Llm Process Domain Expert

Define ownership boundaries for host state and shared LLM process assets.

Community
Basic
ar4mirezar4mirez
7

generate-agents-md

Generate AGENTS.md files from CLAUDE.md for cross-tool AI coding compatibility.

Community
Intermediate