anthropic-agent-skills

A marketplace package containing example tools for working with Excel, Word, PowerPoint, PDF files, and several other agent tasks.

In plain words
What is it for?
Use its document tools to process office files and PDFs, or use its examples for visual design, web testing, communications, MCP building, and skill creation.
Why use it?
It provides ready-made examples for common document work and for building or testing agent skills.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add cdeistopened/skill-stack
agentmods
npx agentmods add plugins/cdeistopened/skill-stack/marketplace
Clone the repo
git clone --depth 1 https://github.com/cdeistopened/skill-stack

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin 91% copy Near-identical to another mod in the catalogue.
Security

Grade A, and why

anthropic-agent-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 yesterday.

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.

Origin

This is a copy

91% identical to anthropic-agent-skills — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/anthropic-skills/.claude-plugin/marketplace.json · 46 lines

What it actually says

{
  "name": "anthropic-agent-skills",
  "owner": {
    "name": "Keith Lazuka",
    "email": "[email protected]"
  },
  "metadata": {
    "description": "Anthropic example skills",
    "version": "1.0.0"
  },
  "plugins": [
    {
      "name": "document-skills",
      "description": "Collection of document processing suite including Excel, Word, PowerPoint, and PDF capabilities",
      "source": "./",
      "strict": false,
      "skills": [
        "./skills/xlsx",
        "./skills/docx",
        "./skills/pptx",
        "./skills/pdf"
      ]
    },
    {
      "name": "example-skills",
      "description": "Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling",
      "source": "./",
      "strict": false,
      "skills": [
        "./skills/algorithmic-art",
        "./skills/brand-guidelines",
        "./skills/canvas-design",
        "./skills/doc-coauthoring",
        "./skills/frontend-design",
        "./skills/internal-comms",
        "./skills/mcp-builder",
        "./skills/skill-creator",
        "./skills/slack-gif-creator",
        "./skills/theme-factory",
        "./skills/web-artifacts-builder",
        "./skills/webapp-testing"
      ]
    }
  ]
}
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. yesterday First seen · 46 lines scan A 1a6cc07d4420

Subscribe to this mod's changes

anthropic-agent-skills is a plugin published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. It is 91% identical to anthropic-agent-skills, differing in 10 lines, and is treated as a copy.