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.
git clone --depth 1 https://github.com/CHENyiru3/AI-Skills-CollectionsWrote 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.
[](https://agentmods.dev/plugins/chenyiru3/ai-skills-collections/documents)<a href="https://agentmods.dev/plugins/chenyiru3/ai-skills-collections/documents"><img src="https://agentmods.dev/badge/plugins/chenyiru3/ai-skills-collections/documents/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.
<a href="https://agentmods.dev/plugins/chenyiru3/ai-skills-collections/documents"><img src="https://agentmods.dev/badge/plugins/chenyiru3/ai-skills-collections/documents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
documents 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 3d 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.
What it actually says
{
"name": "documents",
"description": "Document processing — OfficeCLI, Excel, Word, PowerPoint, PDF, web design, and collaboration",
"source": "./skills-market/documents",
"strict": false,
"skills": [
"./collaboration/doc-coauthoring",
"./collaboration/internal-comms",
"./design/algorithmic-art",
"./design/brand-guidelines",
"./design/canvas-design",
"./design/frontend-design",
"./design/scientific-figure-polish",
"./design/theme-factory",
"./design/web-artifacts-builder",
"./design/webapp-testing",
"./formats/docx",
"./formats/pdf",
"./formats/pptx",
"./formats/xlsx",
"./media/imgur-cli",
"./media/slack-gif-creator",
"./office/officecli",
"./office/officecli-docx",
"./office/officecli-pptx",
"./office/officecli-xlsx"
]
}What it installs
The manifest is a name and a version. 20 skills travel with it, and installing the plugin installs all of them — 965 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill imgur-cli A 74 tokens
- Skill officecli A 53 tokens
- Skill scientific-figure-polish A 68 tokens
- Skill officecli-docx A 45 tokens
- Skill officecli-pptx A 44 tokens
- Skill officecli-xlsx A 43 tokens
- Skill docx A 49 tokens
- Skill pptx A 47 tokens
- Skill xlsx A 46 tokens
- Skill webapp-testing A 35 tokens
- Skill internal-comms A 43 tokens
- Skill doc-coauthoring A 44 tokens
- Skill algorithmic-art A 48 tokens
- Skill brand-guidelines A 42 tokens
- Skill pdf A 42 tokens
- Skill slack-gif-creator A 51 tokens
- Skill frontend-design A 45 tokens
- Skill theme-factory A 41 tokens
- Skill canvas-design A 41 tokens
- Skill web-artifacts-builder A 64 tokens
What ships with it
1 file beside marketplace.json#documents 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.
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.
- 3d ago Changed · +1 lines e354b8867e07
- 1mo ago First seen · 27 lines scan A 7845cb157947
documents is a plugin published in the GitHub repository CHENyiru3/AI-Skills-Collections (2 stars, last pushed 3d 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
documents compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| documentsCHENyiru3/AI-Skills-Collections | Plugin | 2 | 3d ago | MIT | A | — | Claude Code |
| kordoc marketplacechrisryugj/kordoc | Plugin | 3.0k | today | MIT | A | — | Claude Code |
| document-skillsanthropics/skills | Plugin | 195k | today | none | A | — | Claude Code |
| kordocchrisryugj/kordoc | Plugin | 3.0k | today | MIT | A | — | Claude Code |
| daymade-docsdaymade/claude-code-skills | Plugin | 1.5k | today | MIT | A | — | Claude Code |
| anthropic-office-skillsfcakyon/claude-codex-settings | Plugin | 1.2k | today | Apache-2.0 | A | — | Claude Code |
| openai-office-skillsfcakyon/claude-codex-settings | Plugin | 1.2k | today | Apache-2.0 | A | — | Claude Code |