Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/skillscatalog/registry/skill-validatornpx skills add SkillsCatalog/registry --skill skill-validatorgit clone --depth 1 https://github.com/SkillsCatalog/registryWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00027 | $0.00622 |
| Opus 5 | $0.00014 | $0.00311 |
| Sonnet 5 | $0.00005 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
skill-validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
Use this skill to validate any Agent Skill directory against the specification before publishing. The validator checks:
- SKILL.md presence - Required manifest file exists
- Frontmatter format - Valid YAML frontmatter with required fields
- Name validation - 1-64 chars, lowercase, hyphens only, starts with letter
- Name-directory match - Name field matches the directory name
- Description validation - 1-1024 characters, non-empty
- Structure validation - Valid folder organization
When to Use
- Before submitting a skill for publication
- After making changes to SKILL.md
- To diagnose why a skill was rejected
- As part of CI/CD pipelines
How to Use
Validate a skill directory:
Validate the skill at /path/to/my-skill
Get JSON output for CI integration:
python3 validate_skill.py /path/to/my-skill --json
Output
✓ Skill Validation Report
Skill: pdf-tools
Status: COMPLIANT (100/100)
Checks:
✓ SKILL.md exists
✓ Valid frontmatter
✓ Name format valid (pdf-tools)
✓ Name matches directory
✓ Description valid (45 chars)
✓ Structure valid
No issues found.
Or if issues are found:
✗ Skill Validation Report
Skill: My-Skill
Status: NON-COMPLIANT (40/100)
Checks:
✓ SKILL.md exists
✓ Valid frontmatter
✗ Name format invalid
✗ Name doesn't match directory
✓ Description valid
✓ Structure valid
Issues:
- Name must be lowercase with hyphens only (got "My-Skill")
- Name 'My-Skill' doesn't match directory 'my-skill'
Examples
Basic validation:
User: Validate the skill at ./document-skills/pdf
Agent: Running validation on ./document-skills/pdf...
✓ Skill is compliant (100/100)
Fix validation errors:
User: Why is my skill failing validation?
Agent: Let me check... Running validator...
The name field uses underscores. Change "pdf_tools" to "pdf-tools".
Limitations
- Does not validate skill functionality (only structure/format)
- Does not run safety scans (use skill-safety-scanner for that)
- Requires local filesystem access to the skill directory
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 110 lines · 27 tokens per session scan A c662b1e1bc68
skill-validator is a skill published in the GitHub repository SkillsCatalog/registry (1 stars, last pushed 8mo ago), licensed MIT. It adds 27 tokens to every session and 622 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
aap-lint
Skill "aap-lint" from automateyournetwork/netclaw, covering ansible lint operations, mcp server, available tools (9), key concepts and workflow: pre-deployment playbook validation.
huawei-cloud-skill-audit
Audit Huawei Cloud skills for quality, security, and compliance using a two-check pipeline: skillspector (AI security) and gitleaks (credential leak). Generates structured reports with issue details and fix strategies. Triggers include: "审计技能","技能审计","检查技能质量","扫描技能问题","技能安全审计", "audit skill","check skill…
adversarial-thinking
五维对抗验证 — 蒙多攻击自己的计划，在建造前摧毁.
devops-tooling
Git operations, shell scripting, CI/CD pipelines, and terminal automation. Use for conventional commits, PowerShell/Bash scripting, configuring GitHub Actions, or automating development tooling workflows.
Validation Engine
Checks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rules.