Skills-Registry-CLI: Skill for Claude Code

.github/skills/skill-validator/SKILL.md

skill-validator is a skill for Claude Code, Codex from shyamsridhar123/Skills-Registry-CLI. It costs 37 tokens per session (1,390 once invoked), scanned A, original, MIT.

A skill for checking SKILL.md files against the GitHub Copilot Agent Skills specification. It verifies required fields, naming rules, encoding, and description limits.

In plain words
What is it for?
Use it to validate a skill directory and its SKILL.md file for format compliance.
Why use it?
It catches invalid skill structure or metadata before a skill is used or shared.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is shyamsridhar123/Skills-Registry-CLI's own configuration. It tells Claude Code and Codex how to work on Skills-Registry-CLI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Skills-Registry-CLI configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shyamsridhar123/Skills-Registry-CLI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/shyamsridhar123/Skills-Registry-CLI/main/.github/skills/skill-validator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/shyamsridhar123/Skills-Registry-CLI

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-validator

README.md
[![agentmods](https://agentmods.dev/badge/skills/shyamsridhar123/skills-registry-cli/skill-validator/github.svg)](https://agentmods.dev/skills/shyamsridhar123/skills-registry-cli/skill-validator)
Your own site
<a href="https://agentmods.dev/skills/shyamsridhar123/skills-registry-cli/skill-validator"><img src="https://agentmods.dev/badge/skills/shyamsridhar123/skills-registry-cli/skill-validator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-validator

Your own site · 80×15
<a href="https://agentmods.dev/skills/shyamsridhar123/skills-registry-cli/skill-validator"><img src="https://agentmods.dev/badge/skills/shyamsridhar123/skills-registry-cli/skill-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,390 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.01390
Opus 5 $0.00018 $0.00695
Sonnet 5 $0.00007 $0.00278
Haiku 4.5 $0.00004 $0.00139

Measured 10d ago against content hash 412d3223db48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 10d ago.

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.

.github/skills/skill-validator/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Validator Skill

This skill provides validation rules and implementation for checking skills against the GitHub Copilot Agent Skills specification.

Validation Rules

SKILL.md Requirements

File Must Exist
  • Path: <skill-directory>/SKILL.md
  • Encoding: UTF-8
YAML Frontmatter

Required format:

---
name: skill-name
description: What the skill does and when to use it
---
Allowed Frontmatter Properties

Per VS Code Agent Skills specification, only these are permitted:

  • name (required)
  • description (required)

Name Validation

Pattern: ^[a-z0-9]([a-z0-9-]*[a-z0-9])?$

Rules:

  • Lowercase letters, digits, and hyphens only
  • Cannot start with hyphen
  • Cannot end with hyphen
  • Maximum 64 characters
  • Minimum 1 character

Valid examples:

  • skill-creator
  • pdf
  • my-awesome-skill-2

Invalid examples:

  • Skill-Creator (uppercase)
  • -skill (starts with hyphen)
  • skill- (ends with hyphen)
  • skill_name (underscore)

Description Validation

  • Must be present
  • Must not be empty
  • Maximum 1024 characters
  • Should describe:
    • What the skill does
    • When to use it

Implementation

Node.js Validator

import { readFile } from 'fs/promises';
import { existsSync } from 'fs';
import { join } from 'path';
import { parse as parseYaml } from 'yaml';

const NAME_PATTERN = /^[a-z0-9]([a-z0-9-]*[a-z0-9])?$/;
// Per VS Code Agent Skills spec: only name and description are documented
const ALLOWED_PROPERTIES = new Set([
  'name',
  'description',
]);

export async function validateSkill(skillPath) {
  const errors = [];
  const warnings = [];
  
  // Check SKILL.md exists
  const skillMdPath = join(skillPath, 'SKILL.md');
  if (!existsSync(skillMdPath)) {
    return {
      valid: false,
      errors: ['SKILL.md not found'],
      warnings: []
    };
  }
  
  // Read content
  const content = await readFile(skillMdPath, 'utf-8');
  
  // Check frontmatter exists
  if (!content.startsWith('---')) {
    errors.push('No YAML frontmatter found');
    return { valid: false, errors, warnings };
  }
  
  // Extract frontmatter
  const endIndex = content.indexOf('---', 3);
  if (endIndex === -1) {
    errors.push('Invalid frontmatter format - missing closing ---');
    return { valid: false, errors, warnings };
  }
  
  const frontmatterText = content.slice(4, endIndex).trim();
  
  // Parse YAML
  let frontmatter;
  try {
    frontmatter = parseYaml(frontmatterText);
    if (typeof frontmatter !== 'object' || frontmatter === null) {
      errors.push('Frontmatter must be a YAML object');
      return { valid: false, errors, warnings };
    }
  } catch (e) {
    errors.push(`Invalid YAML: ${e.message}`);
    return { valid: false, errors, warnings };
  }
  
  // Check for unexpected properties
  for (const key of Object.keys(frontmatter)) {
    if (!ALLOWED_PROPERTIES.has(key)) {
      errors.push(`Unexpected property: ${key}`);
    }
  }
  
  // Validate name
  if (!frontmatter.name) {
    errors.push('Missing required field: name');
  } else if (typeof frontmatter.name !== 'string') {
    errors.push('Name must be a string');
  } else {
    const name = frontmatter.name.trim();
    if (!NAME_PATTERN.test(name)) {
      errors.push('Name must be lowercase with hyphens only');
    }
    if (name.length > 64) {
      errors.push('Name exceeds 64 characters');
    }
  }
  
  // Validate description
  if (!frontmatter.description) {
    errors.push('Missing required field: description');
  } else if (typeof frontmatter.description !== 'string') {
    errors.push('Description must be a string');
  } else {
    const desc = frontmatter.description.trim();
    if (desc.length === 0) {
      errors.push('Description cannot be empty');
    }
    if (desc.length > 1024) {
      errors.push('Description exceeds 1024 characters');
    }
    if (desc.length < 20) {
      warnings.push('Description is very short');
    }
  }
  
  // Check body content
  const body = content.slice(endIndex + 3).trim();
  if (body.length === 0) {
    warnings.push('SKILL.md body is empty');
  }
  
  return {
    valid: errors.length === 0,
    errors,
    warnings
  };
}

Read the full file on GitHub · 233 lines

Changes

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.

  1. 10d ago First seen · 233 lines · 37 tokens per session scan A 412d3223db48

Subscribe to this mod's changes

skill-validator is a skill published in the GitHub repository shyamsridhar123/Skills-Registry-CLI (2 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 1,390 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

work

Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.

automagik-dev/genie · 26 tokens

preview-design

Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…

egregore-labs/egregore · 71 tokens

sw-do

Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".

anton-abyzov/specweave · 41 tokens

done

Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".

anton-abyzov/specweave · 0 tokens

xiaohongshu-image-creator

An image-making assistant for Xiaohongshu, a Chinese social platform for lifestyle, product, and educational posts. It creates vertical covers and supporting images matched to the post’s topic, audience, and visual style.

huangrichao2020/pretty-skills · 121 tokens

atomic-tdd

Test-first discipline. Auto-triggers on "let's implement X", "add feature Y", "fix bug Z", "write a test for", "implement", "build out", and similar pre-code-change phrases. Iron rule: failing test exists before production code. Skip only for pure docs/config changes with an explicit "skipped because:" note. Explicit…

damusix/atomic-claude · 142 tokens