
Skill Validator
- 193 installs
- 2 repo stars
- Updated January 25, 2026
- jorgealves/agent_skills
Validate agent SKILL.md files for required sections, trigger phrases, length limits, and packaging rules before publishing skills to a team or marketplace.
About
Reviews and validates Claude Code-style agent skills for structural compliance, clear triggers, safe scope, bundled resources, and consistent metadata so skills load reliably and do not mislead coding agents during real tasks.
- Checks SKILL.md structure against authoring conventions
- Verifies trigger phrases and progressive disclosure
- Flags missing scripts, references, or unsafe patterns
- Enforces naming, scope, and description clarity
- Produces actionable fix lists for skill authors
Skill Validator by the numbers
- 193 all-time installs (skills.sh)
- +8 installs in the week ending Aug 2, 2026 (Skillselion tracking)
- Ranked #187 of 782 Skill Development skills by installs in the Skillselion catalog
- Data as of Aug 2, 2026 (Skillselion catalog sync)
npx skills add https://github.com/jorgealves/agent_skills --skill skill-validatorAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 193 |
|---|---|
| repo stars | ★ 2 |
| Last updated | January 25, 2026 |
| Repository | jorgealves/agent_skills ↗ |
What it does
Validate agent SKILL.md files for required sections, trigger phrases, length limits, and packaging rules before publishing skills to a team or marketplace.
Files
Skill Validator
Purpose and Intent
The skill-validator is the primary quality control tool for this repository. It ensures that every AI Agent Skill is "machine-consumable" by validating it against the agentskills.io standard and the repository's AGENTS.md rules.
When to Use
- During Development: Run this skill every time you create or modify a skill.
- CI/CD Integration: Automatically block Pull Requests that contain non-compliant skill definitions.
- Repository Audits: Periodically scan the entire
agent-skills/directory to ensure long-term compliance as specifications evolve.
When NOT to Use
- Code Logic Validation: This tool does not "run" the skills or verify their internal logic; it only validates the "contract" (the YAML and Markdown).
Error Conditions and Edge Cases
- Invalid YAML: If
skill.yamlcannot be parsed, the validator will fail immediately with a syntax error. - Missing Required Fields: Any missing field defined in the
agentskills.iospecification will result inis_valid: false. - Empty Directories: Folders in
agent-skills/that do not contain askill.yamlwill be flagged as invalid skills.
Security and Data-Handling Considerations
- ReadOnly Access: The skill only requires read permissions for the target directory.
- No External Calls: Validation is performed locally using the embedded schema rules.
name: skill-validator
version: 1.0.0
description: Validates agent skill definitions against agentskills.io and AGENTS.md rules. Use when creating or modifying skills to ensure they are machine-readable and documentation-complete.
inputs:
skill_directory:
type: string
description: Path to the skill folder.
required: true
check_examples:
type: boolean
default: true
outputs:
validation_results:
type: object
properties:
is_valid:
type: boolean
errors:
type: array
capabilities:
- Schema validation for skill.yaml.
- Documentation check for README.md.
- Semantic consistency verification.
constraints:
- Metadata validation only; no logic execution.
security:
- Reads metadata only; safe for CI/CD.
examples:
- input:
skill_directory: "./agent-skills/secret-leak-detector"
output:
validation_results:
is_valid: true
errors: []