avibe-bot/askill/build-a-skill

Claude Code and agent skill by avibe-bot/askill

Trust tier 2
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when creating or modifying a skill: follow SKILL.md rules, define commands and dependencies, validate locally, version correctly, and publish

Install

npx vskill@latest install avibe-bot/askill/build-a-skill

SKILL.md

Build a Skill

Use this skill when creating or updating a skill that must work with askill CLI and registry conventions.

Authoring Standard

A valid skill requires one entry file:

  • SKILL.md (required)

Optional supporting files:

  • scripts/ for executable commands
  • assets/ for templates or reference material

Recommended layout:

text
my-skill/
├── SKILL.md
├── scripts/
│ └── main.js
└── assets/

Minimal SKILL.md Template

markdown
---
name: my-skill
slug: my-skill
description: One-line purpose of the skill
version: 0.1.0
---
# My Skill
## Overview
What this skill does and when to use it.
## Usage
Step-by-step instructions the agent can execute.

Frontmatter Rules

Required:

  • name - lowercase letters/numbers/hyphens only
  • description - concise summary

Strongly recommended:

  • version - valid semver (1.0.0, 1.1.0-beta.1)
  • slug - publish identifier (@author/slug)

Optional:

  • author, tags, dependencies, commands, repository, license

Dependencies format:

  • Published: @author/skill-name or @author/skill-name@^1.2.0
  • Indexed GitHub: gh:owner/repo@skill-name or gh:owner/repo/path

Commands format:

yaml
commands:
analyze:
run: node scripts/analyze.js
description: Analyze current repository
_setup:
run: npm ci
description: Install command dependencies

Write for Agents, Not Humans

Your markdown body should be executable guidance:

  • include clear preconditions
  • include exact commands
  • include expected outputs/artifacts
  • include failure handling and recovery paths

Good instruction pattern:

  1. Check prerequisites
  2. Run command
  3. Verify output
  4. Handle common failures

Development Loop (Local)

Use this loop while building:

bash
# 1) scaffold
askill init ./my-skill
# 2) validate schema/fields
askill validate ./my-skill/SKILL.md
# 3) install locally for testing
askill add ./my-skill -a claude-code -y
# 4) run commands
askill run my-skill:<command>
# 5) inspect installed state
askill list

When iterating quickly, reinstall with askill add ./my-skill -y after changes.

Publish Workflow

Publishing uses slug as publish intent.

bash
askill login --token ask_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
askill whoami
askill publish ./my-skill

Alternative (publish from GitHub SKILL.md URL):

bash
askill publish --github https://github.com/owner/repo/blob/main/path/to/SKILL.md

Important:

  • askill publish requires name, slug, and valid semver version
  • local publish uses logged-in user as author
  • GitHub URL publish uses repo owner as author (supports org namespace)
  • successful publish creates canonical slug @author/<slug>
  • bump version before republishing updates
  • askill submit <github-url> requests indexing and can trigger slug-driven publish flows

Quality Checklist Before Release

  • askill validate passes with no errors
  • all documented commands exist in frontmatter
  • command descriptions are present and specific
  • prerequisites are explicit and testable
  • instructions avoid hardcoded agent paths
  • at least one end-to-end example is included

Common Mistakes to Avoid

  • vague instructions like "run the script"
  • missing run or description in commands
  • undocumented prerequisites (runtime/tooling)
  • relying on unpublished assumptions instead of explicit steps
  • hardcoding .claude/skills/... paths instead of askill run

Maintenance Guidance

For updates:

  1. change skill behavior/instructions
  2. bump semver in version
  3. validate locally
  4. republish

For breaking changes, increment major version.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
6
Repository forks
1
Repository npm downloads, 7 days
39
7-day trend score
22

Stars and forks are for the whole GitHub repository, not this skill alone. Downloads are for the repository's npm package. Refreshed 17 Mar 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/avibe-bot/askill/build-a-skill/badge)](https://verified-skill.com/skills/avibe-bot/askill/build-a-skill)

Something wrong with this skill or its page? Tell us.