Validate Skills
- 5.2k installs
- 1.6k repo stars
- Updated July 25, 2026
- callstackincubator/agent-skills
Validate Skills is an agent skill that checks each skills/ directory against agentskills.io rules and Claude Code authoring best practices with PASS/FAIL reports.
About
Validate Skills is a Callstack agent skill that audits every directory under skills/ against the agentskills.io specification and Claude Code authoring best practices. Run it via the /validate-skills command before publishing or merging skill contributions. For each skill it checks name format and directory parity, description length, optional metadata validity, third-person description style, body length under five hundred lines, one-level-deep references, markdown links instead of bare filenames, and redundancy between frontmatter and body. The workflow finds top-level skill folders with fd, reads each SKILL.md, marks PASS or FAIL per rule, and reports in a structured Validation Results block citing concrete violations such as directory name mismatches. Designed for maintainers of agent skill repositories who need consistent spec compliance without manual checklist drudgery. References agentskills.io and Claude Code skill docs as authoritative sources.
- agentskills.io compliance checks for name format, directory match, description length, and metadata fields.
- Claude Code best practices: third-person descriptions, under 500 lines, one-level references, markdown links.
- fd-based discovery of skill directories plus per-file SKILL.md rule evaluation.
- Structured PASS/FAIL report format with concrete violation messages per skill folder.
- Invoked through /validate-skills for repo-wide skill linting before publish.
Validate Skills by the numbers
- 5,233 all-time installs (skills.sh)
- +243 installs in the week ending Jul 28, 2026 (Skillselion tracking)
- Ranked #20 of 826 Skill Development skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
validate-skills capabilities & compatibility
- Capabilities
- verify name format and directory name parity · check description length and optional metadata v · enforce third person descriptions and body under · detect nested reference chains and bare filename · emit structured pass fail validation reports
- Use cases
- documentation · code review
What validate-skills says it does
Validate all skills in `skills/` against the agentskills.io spec and Claude Code best practices.
Directory name must equal `name` field
Body length | Under 500 lines
npx skills add https://github.com/callstackincubator/agent-skills --skill validate-skillsAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 5.2k |
|---|---|
| repo stars | ★ 1.6k |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 25, 2026 |
| Repository | callstackincubator/agent-skills ↗ |
How do we catch invalid skill names, mismatched directories, or non-compliant SKILL.md bodies before publishing to an agent skills repo?
Lint skill directories against agentskills.io spec and Claude Code best practices via /validate-skills.
Who is it for?
Maintainers of agent skill monorepos who need automated agentskills.io and Claude Code compliance before merge or release.
Skip if: Runtime agent behavior testing, semantic skill quality review, or validating code outside the skills/ tree.
When should I use this skill?
User runs /validate-skills, asks to lint SKILL.md files, or needs agentskills.io spec compliance across a skills directory.
What you get
A Validation Results report listing each skill folder with PASS or FAIL per spec and best-practice rule plus concrete fix guidance.
- Spec compliance report
- Validation checklist results
- Pre-commit lint pass or fail
By the numbers
- Enforces skill name length of 1-64 characters
- Validates against official agentskills.io specification
Files
Validate Skills
Validate all skills in skills/ against the agentskills.io spec and Claude Code best practices.
Validation Checklist
For each skill directory, verify:
Spec Compliance (agentskills.io)
| Check | Rule |
|---|---|
name format | 1-64 chars, lowercase alphanumeric + hyphens, no leading/trailing/consecutive hyphens |
name matches directory | Directory name must equal name field |
description length | 1-1024 characters, non-empty |
| Optional fields valid | license, metadata, compatibility if present |
Best Practices (Claude Code)
| Check | Rule |
|---|---|
| Description format | Third person, describes what + when to use |
| Body length | Under 500 lines |
| References one-level deep | No nested reference chains |
| Links are markdown | Use [text](path) not bare filenames |
| No redundancy | Don't repeat description in body |
| Concise | Only add context Claude doesn't already have |
How to Run
1. Find all skill directories:
fd -t d -d 1 . skills/2. For each skill, read SKILL.md and check against the rules above
3. Report issues in this format:
## Validation Results
### skills/example-skill
- [PASS] name format valid
- [FAIL] name "example" doesn't match directory "example-skill"
- [PASS] description length OK (156 chars)References
Related skills
Find SkillsSo their agent can intelligently recommend and install the right modular skills from the open ecosystem when they ask how to do something.3M27k
Lark Skill MakerRapidly create custom skills for Lark (Feishu) that can be invoked by their AI agents and automation workflows.458k
Skill CreatorGenerate, test, and iterate on new reusable agent skills directly inside their Claude or Cursor workflow.324k163k
BrainstormingTurn vague product ideas into clear, approved designs and specifications through guided collaborative dialogue before writing any code.291k260k
Find SkillsInstantly surface the best relevant agent skills, MCP servers, and workflows across multiple registries before starting any new project.226k12
Writing Great SkillsCreate high-quality, reusable agent skills that other developers can discover and install from the Skillselion catalog.223k183kHow it compares
Pick validate-skills over generic markdown linters when the artifact is an agentskills.io SKILL.md with Claude Code-specific authoring rules.
FAQ
What spec does validate-skills enforce?
agentskills.io rules for name format, directory parity, description length, plus Claude Code body length, links, and reference depth.
How are skills discovered for validation?
Find top-level skill directories with fd, then read each SKILL.md and evaluate every checklist rule.
What does the output look like?
A Validation Results section per skill with PASS or FAIL lines such as name format valid or directory mismatch.
Is Validate Skills safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.