publish-skills

publish-skills is a skill for Claude Code from mr-kelly/skills. It costs 153 tokens per session (3,582 once invoked), scanned A, original, MIT.

A workflow for publishing agent skills and MCP servers to public marketplaces and registries. MCP servers are services that let agents use external tools or data.

In plain words
What is it for?
Use it to scan tracked files, validate a skill repository, create a release, connect supported marketplaces, and prepare an MCP server for the official registry.
Why use it?
It helps prevent private data and secrets from being published accidentally and guides the checks needed before making a repository public.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

Part of the mr-kelly-skills plugin — 25 skills shipped together

Good fit Use it to scan tracked files, validate a skill repository, create a release, connect supported marketplaces, and prepare an MCP server for the official registry.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mr-kelly/skills/publish-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 mr-kelly/skills --skill publish-skills
Clone the repo
git clone --depth 1 https://github.com/mr-kelly/skills

Made for: Claude Code.

Or install mr-kelly-skills, the plugin that ships this one along with the rest of its 25 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 publish-skills

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mr-kelly/skills/publish-skills"><img src="https://agentmods.dev/badge/skills/mr-kelly/skills/publish-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,582 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 $0.00153 $0.03582
Opus 5 $0.00077 $0.01791
Sonnet 5 $0.00031 $0.00716
Haiku 4.5 $0.00015 $0.00358

Measured 9d ago against content hash be7b3dfa2ba6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

publish-skills 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 9d ago.

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/publish-skills/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish Skills

Publish a repo of agent skills (the open SKILL.md format) to the agent-skills marketplaces. The repo is the unit of publishing: make it public, validate, cut a release, and the auto-indexers (skills.sh, SkillsMP, claudeskills.info) pick it up. Then optionally wire the Claude /plugin marketplace and submit to the curated stores.

Golden rule: security first. These repos often carry a local App-in-Skill with real data (emails, ledgers, tokens). Never publish it. Confirm private data is gitignored and scan tracked files before anything goes public.

Run steps in order. Stop and surface anything a step can't resolve safely.


Step 1 — Security scan (blocking)

Publishing is outward-facing and hard to reverse. Verify BEFORE any push/release.

# 1a. Private runtime state must be gitignored, never tracked
grep -nE '\.data/|\.cache/|config\.local|\.env|exports/' .gitignore    # expect these ignored
git ls-files | grep -iE '\.data/|\.cache/|config\.local|\.env|\.pem|\.key' && echo "!!! TRACKED PRIVATE FILE — stop" || echo "clean: no private files tracked"

# 1b. Scan tracked files for real secrets / PII (tune patterns per repo)
git ls-files | while read f; do
  grep -HnaiE '(sk_live|sk_test|pk_live|bearer [A-Za-z0-9]|-----BEGIN|api[_-]?key["'"'"' :=]+[A-Za-z0-9]{16})' "$f" 2>/dev/null
done | grep -vE 'example\.com|_env"|password_env|api_key_env|REPLACE_WITH' | head
  • Config templates must use example.com, Your Name, and *_env references — never real hosts, addresses, or key values.
  • Third-party skills the user installed (e.g. a tracked .agents/skills/<other>/) must NOT be republished — untrack + gitignore them: git rm -r --cached .agents && printf '\n.agents/skills/\n' >> .gitignore

Only proceed when 1a and 1b are clean.

Step 2 — Validate & fix (gh skill)

GitHub's official tooling validates against the agentskills.io spec and discovers skills/*/SKILL.md, */SKILL.md, and plugins/{scope}/skills/*/SKILL.md.

Read the full file on GitHub · 212 lines

Files

What ships with it

1 file 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. 9d ago First seen · 212 lines · 153 tokens per session scan A be7b3dfa2ba6

Subscribe to this mod's changes

publish-skills is a skill published in the GitHub repository mr-kelly/skills (5 stars, last pushed yesterday), licensed MIT. It adds 153 tokens to every session and 3,582 once invoked, about $0.0008 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 2026-09-03.

Related

Other skills, from other repositories

slide-sage

Create or enhance a data-rich, single-file HTML slide deck or pitch deck. Use when the user asks for a new presentation, to convert a PowerPoint (.pptx) or PDF into an HTML deck, or to improve an existing HTML presentation. Not for native PowerPoint editing or high-fidelity PPTX export.

rhnfzl/slide-sage · 68 tokens

write-literature-review

Iterative literature-review workflow for a research topic. Use this skill to draft up to 10 search keywords, build a seed set from OpenAlex title-and-abstract matches, expand by backward and forward citations, screen candidates by title and abstract, repeat until no new relevant papers remain, rank the final set…

Zsun79/LitReviewSkill · 95 tokens

baoyu-comic

A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.

JimLiu/baoyu-skills · 61 tokens

baoyu-diagram

Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…

JimLiu/baoyu-skills · 146 tokens

playwright-cli

Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…

testdino-hq/playwright-skill · 64 tokens

agent-wiki

Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.

Dianel555/DSkills · 89 tokens