shield_lock
JinDaGe
← Back to skills
extension
Category: AI Agent CapabilitiesNo API key required

publish-skill

Use when creating a new skill and publishing it to a GitHub repo for installation via npx skills add. Covers scaffold, spec compliance, skill-judge evaluation, commit, push, and install verification. Keywords: publish skill, add skill to repo, npx skills init, share skill, agentic-tools, skills.sh.

personAuthor: jakexiaohubgithub
open_in_newRepositorydownloadDownload package

Publish Skill

When to Use

Load this skill when the user request matches the frontmatter description for Publish Skill.

Add a new skill to acedergren/agentic-tools and make it installable via npx skills add.

Workflow

1. Scaffold

cd ~/Projects/agentic-tools/skills
npx skills init <skill-name>
# Creates skills/<skill-name>/SKILL.md

2. Write the skill

Edit skills/<skill-name>/SKILL.md. Frontmatter must have exactly two fields:

---
name: skill-name-with-hyphens   # lowercase, letters/numbers/hyphens, ≤64 chars
description: "Use when [trigger conditions]. [WHAT]. Keywords: ..."
---

Description rules — all three required:

  • WHAT: what does it do?
  • WHEN: starts with "Use when..."
  • KEYWORDS: searchable terms at the end

3. Evaluate before committing

Run /skill-judge on the new skill. Target ≥ 84/120 (C grade) before pushing.

Key checks:

  • No "What is X" explanations Claude already knows
  • Has explicit NEVER list with reasons
  • SKILL.md < 300 lines (heavy reference → references/ subdir)
  • No extra frontmatter fields (license, metadata, version)

4. Commit and push

git add skills/<skill-name>/
git commit -m "feat(skills): add <skill-name> skill"
git push origin main

5. Verify installable

npx skills add acedergren/agentic-tools@<skill-name> -g -y

If the skill isn't found, check:

  • Directory name matches name field in frontmatter
  • SKILL.md is at skills/<skill-name>/SKILL.md (not nested deeper)

Install Commands for This Repo

# Single skill
npx skills add acedergren/agentic-tools@<skill-name> -g

# All skills
npx skills add acedergren/agentic-tools --all -g -y

# List available without installing
npx skills add acedergren/agentic-tools -l

NEVER

  • Never push a skill without running /skill-judge first — a skill that fails evaluation won't trigger correctly because its description lacks WHAT/WHEN/KEYWORDS
  • Never use extra frontmatter fields — only name and description are valid; license, metadata, version cause parse errors in some agents
  • Never put "When to use" only in the body — the agent only reads the description to decide whether to load; body content is invisible at trigger time
  • Never name a skill with spaces or special chars — my skill! breaks install; use my-skill

Arguments

$ARGUMENTS: Optional user-provided target, path, environment, symptom, or constraint. When empty, infer the narrowest safe scope from the current repository context and ask only if multiple high-impact choices remain.