skill-improver_skill

This skill audits and improves Claude skills to align with the Anthropic guide, ensuring clear steps, handling errors, and readying for distribution.
  • JavaScript

57

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill atrislabs/atris --skill skill-improver

  • SKILL.md4.3 KB

Overview

This skill audits and improves Claude skills to match the Anthropic skill guide standard. It inspects skill metadata, instruction quality, triggers, error handling, examples, and publication readiness for ClawHub. Use it to raise skill quality, fix common faults, and prepare skills for distribution.

How this skill works

The skill runs a mechanical audit followed by a qualitative review of the skill document and folder contents. It checks metadata fields, description clarity, trigger placement, instruction granularity, example coverage, error-handling guidance, and publication checklist items. It then recommends concrete edits and a prioritized remediation plan.

When to use it

  • Creating a new skill and needing a production-ready checklist
  • Improving an existing skill to pass distribution standards
  • After an automated skill audit reports warnings or failures
  • Preparing a skill for ClawHub or other public distribution
  • Validating that a skill’s triggers, examples, and error handling are clear

Best practices

  • Keep the description concise: WHAT it does + WHEN to use + trigger keywords in one place
  • Use kebab-case for the skill name and ensure it matches the folder name exactly
  • Provide numbered, concrete steps rather than vague guidance
  • Include clear input/output examples and explicit error-handling instructions
  • Avoid XML-style angle-bracket tags; use plain text or bracket notation
  • Limit the main skill document length and move long references to a references folder

Example use cases

  • Run a pre-publish audit to catch metadata, trigger, and tagging issues
  • Refactor vague instruction sections into step-by-step workflows with checkpoints
  • Add error handling and troubleshooting entries for known failure modes
  • Generate a prioritized editing plan after automated checks report failures
  • Validate tags, versioning, and relative paths before external distribution

FAQ

It checks required metadata fields, naming conventions, forbidden XML tags, length limits, and other automated validity rules.

How do I fix missing or vague triggers?

Embed trigger words directly in the description using the pattern: WHAT it does + WHEN to use + trigger keywords, and ensure the description remains under the length limit.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
skill-improver skill by atrislabs/atris | VeilStrat