agentmods.dev

better-skill-publish

better-skill-publish is a skill for Claude Code from psylch/better-skills. It costs 104 tokens per session (1,241 once invoked), scanned A, original, MIT.

A packaging tool that turns an agent skill into a complete GitHub repository for sharing through skills.sh. It creates the files and folder structure a distributable skill needs.

In plain words
What is it for?
Use it to package a skill, collect its publishing details, optionally start Git version control, and optionally create the GitHub repository.
Why use it?
It removes the manual work of preparing documentation, license, configuration, and repository files before publishing a skill.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: names the AskUserQuestion tool.

Part of the better-skills plugin — 3 skills shipped together

not rated 5repo 6mo ago A scan 104 tokens original MIT

Good fit Use it to package a skill, collect its publishing details, optionally start Git version control, and optionally create the GitHub repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/psylch/better-skills/better-skill-publish
View source ↗ psylch/better-skills
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add psylch/better-skills --skill better-skill-publish
Clone the repo
git clone --depth 1 https://github.com/psylch/better-skills

Made for: Claude Code.

Or install better-skills, the plugin that ships this one along with the rest of its 3 skills.

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 better-skill-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/psylch/better-skills/better-skill-publish/github.svg)](https://agentmods.dev/skills/psylch/better-skills/better-skill-publish)
Your own site
<a href="https://agentmods.dev/skills/psylch/better-skills/better-skill-publish"><img src="https://agentmods.dev/badge/skills/psylch/better-skills/better-skill-publish/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 better-skill-publish

Your own site · 80×15
<a href="https://agentmods.dev/skills/psylch/better-skills/better-skill-publish"><img src="https://agentmods.dev/badge/skills/psylch/better-skills/better-skill-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,241 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 $0.00104 $0.01241
Opus 5 $0.00052 $0.00620
Sonnet 5 $0.00021 $0.00248
Haiku 4.5 $0.00010 $0.00124

Measured 11d ago against content hash c6d2f9e3f5a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

better-skill-publish 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/publish.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/better-skill-publish/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Publish

Language

Match user's language: Respond in the same language the user uses.

Overview

Package a agent skill into a complete, distributable GitHub repository. Generates all the surrounding files (README, LICENSE, plugin.json, marketplace.json) and optionally creates the GitHub repo.

How It Works

  1. Identify the skill to publish
  2. Optionally review first with better-skill-review
  3. Collect publishing metadata through dialogue
  4. Generate the repository structure with publish.py
  5. Optionally initialize git and create GitHub repo

Dialogue Flow

Progress:

  • Step 1: Identify the skill
  • Step 2: Pre-publish validation
  • Step 3: Collect metadata
  • Step 4: Generate repository
  • Step 5: Post-generation

Step 1: Identify the Skill

Accept the skill location in multiple forms:

Input Detection Action
Directory with SKILL.md Direct path Use as-is
SKILL.md file path Path ends in SKILL.md Use parent directory
Current directory No input, cwd has SKILL.md Auto-detect

Step 2: Pre-Publish Validation

Check for better-skill-review availability:

  1. First try: {SKILL_DIR}/../better-skill-review/scripts/validate.py
  2. Fallback: ~/.agents/skills/better-skill-review/scripts/validate.py

If found, suggest running validation:

python3 <validate.py path> run --path <skill-path>

If there are failures, recommend fixing them before proceeding. Warnings are acceptable.

If better-skill-review is not available, offer:

  • A) Install it: npx skills add psylch/better-skills@better-skill-review -g -y
  • B) Continue without it (quick manual check: verify SKILL.md exists with valid frontmatter)
  • C) Cancel

Step 3: Collect Metadata

Use AskUserQuestion to gather:

  1. GitHub owner/org — Default: try to infer from git config user.name or gh api user -q .login. Ask user to confirm or change.

  2. Repository name — Default: <skill-name>-skill (e.g., cors-audit-skill). Suggest the convention but let user override.

Read the full file on GitHub · 170 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 170 lines · 104 tokens per session scan A c6d2f9e3f5a5

Subscribe to this mod's changes

better-skill-publish is a skill published in the GitHub repository psylch/better-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 104 tokens to every session and 1,241 once invoked, about $0.0005 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.

Building agentsClaude CodeGit and workflowskill
Related

Other skills, from other repositories

clawhub-production-release

Run and verify ClawHub production deploys and stable ClawHub CLI npm releases. Use when deploying backend or frontend changes to clawhub.ai, dispatching the Deploy workflow, publishing a stable CLI tag, checking release prerequisites, or proving the exact production SHA and workflow outcome.

openclaw/clawhub · 62 tokens

dev-workflow

The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.

iflytek/skillhub · 35 tokens

pr-submission

PR title format, commit conventions, and pre-PR checklist for SkillHub. Use when preparing or reviewing pull requests.

iflytek/skillhub · 28 tokens

pr-body

A tool that reviews all commits on the current branch and creates or updates a pull request title and description. A pull request is a proposed code change submitted for review.

alibaba/anolisa · 68 tokens

devops/changelog-generation

A method for creating a CHANGELOG, a document that records what changed in each software release. It reads Git commit history and release-pipeline reports, then groups changes using common commit and changelog conventions.

echoVic/boss-skill · 36 tokens

odoo-commit

Guides Odoo-style commit creation following official Odoo git guidelines. Drafts [TAG] module: short description messages, checks whether to amend or create a new commit, stages files explicitly, commits via git commit -F, and keeps local history clean before PRs. Auto-invokes for commit-related requests in Odoo…

unclecatvn/agent-skills · 82 tokens