avibe-bot/askill/build-a-skill
Claude Code and agent skill by avibe-bot/askill
- community
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-skillSKILL.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 commandsassets/for templates or reference material
Recommended layout:
Minimal SKILL.md Template
Frontmatter Rules
Required:
name- lowercase letters/numbers/hyphens onlydescription- 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-nameor@author/skill-name@^1.2.0 - Indexed GitHub:
gh:owner/repo@skill-nameorgh:owner/repo/path
Commands format:
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:
- Check prerequisites
- Run command
- Verify output
- Handle common failures
Development Loop (Local)
Use this loop while building:
When iterating quickly, reinstall with askill add ./my-skill -y after changes.
Publish Workflow
Publishing uses slug as publish intent.
Alternative (publish from GitHub SKILL.md URL):
Important:
askill publishrequiresname,slug, and valid semverversion- 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
versionbefore republishing updates askill submit <github-url>requests indexing and can trigger slug-driven publish flows
Quality Checklist Before Release
askill validatepasses 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
runordescriptionin commands - undocumented prerequisites (runtime/tooling)
- relying on unpublished assumptions instead of explicit steps
- hardcoding
.claude/skills/...paths instead ofaskill run
Maintenance Guidance
For updates:
- change skill behavior/instructions
- bump semver in
version - validate locally
- 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
- SKILL.md in the repositoryCheckingskills/build-a-skill/SKILL.md
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
[](https://verified-skill.com/skills/avibe-bot/askill/build-a-skill)