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.
npx skills add magnus919/agent-skills --skill documentsgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/skills/magnus919/agent-skills/documents)<a href="https://agentmods.dev/skills/magnus919/agent-skills/documents"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/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/skills/magnus919/agent-skills/documents"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/documents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00105 | $0.02118 |
| Opus 5 | $0.00053 | $0.01059 |
| Sonnet 5 | $0.00021 | $0.00424 |
| Haiku 4.5 | $0.00011 | $0.00212 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documents — PDF, Word, Excel & PowerPoint Skill
One skill for the four most common document formats. All four share a single
agent workflow — structured content in, render-ready, validated artifact out —
so they live in ONE family skill with per-format references, following the
epub precedent. Load the shared workflow below, then pull the per-format
reference for the format you are actually touching.
| Format | Extension | Reference (load on demand) |
|---|---|---|
.pdf |
references/pdf.md | |
| Word | .docx |
references/word.md |
| Excel | .xlsx |
references/excel.md |
| PowerPoint | .pptx |
references/powerpoint.md |
| All formats | — | references/output-quality.md |
Generation templates for each format live in templates/, and the validation script with per-format fixtures lives in scripts/.
When to use
Load this skill when the task involves any of the four formats:
- Generate: build a report, memo, spreadsheet, or deck from structured content (markdown, JSON, data tables, outlines).
- Edit: modify an existing document's content, layout, or metadata in place.
- Extract: pull text, tables, or structure out of an existing file.
- Convert: move content between formats or from a data source into a document.
- Validate: check that a produced artifact is structurally sound and will render correctly before it is delivered.
When not to use
- Ebooks and EPUB — use the
epubskill; it owns the EPUB container, reading order, and package validation. - Images, video, and other media — this skill covers document formats only; route media production to the appropriate media skills.
- Code and API documentation sites — use the technical-documentation and documentation-site conventions, not office documents.
- Data pipelines — moving or transforming raw data belongs to
data-engineering; Excel here is a deliverable format, not a data store. - Office documents to Markdown — converting an existing office document
(docx, xlsx, pptx, pdf, odt, rtf, epub, csv) to GitHub-Flavored Markdown
belongs to the
anydocskill; this skill owns generation, editing, and validation, not document-to-markdown extraction.
What ships with it
17 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.
- evals/evals.json 8.6 KB
- fixtures/sample.docx 972 B
- fixtures/sample.pdf 600 B
- fixtures/sample.pptx 1.7 KB
- fixtures/sample.xlsx 1.6 KB
- README.md 4.3 KB
- references/excel.md 3.9 KB
- references/output-quality.md 4.5 KB
- references/pdf.md 4.9 KB
- references/powerpoint.md 3.6 KB
- references/word.md 3.7 KB
- scripts/validate-documents.py 19 KB runs code
- templates/excel-template.md 1.6 KB
- templates/pdf-template.md 1.7 KB
- templates/powerpoint-template.md 1.7 KB
- templates/word-template.md 1.8 KB
- tests/test_validate_documents.py 9.0 KB runs code
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.
- 9d ago First seen · 194 lines · 105 tokens per session scan A 210e8572af3b
documents is a skill published in the GitHub repository magnus919/agent-skills (75 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 2,118 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 2026-08-30.
Other skills, from other repositories
smart-data-collection
A workflow for extracting structured information from images and documents such as PDFs, Word files, and spreadsheets, then storing it in a database.
tencent-docs
A skill for creating, reading, editing, searching, and managing Tencent Docs, an online document and spreadsheet service.
meta-multi-format-export-pack
From one piece of source content, render four deliverables: .docx report, .pptx slides, .xlsx data, and an HTML/PDF public version.
superlinked-docs
Offload document, image, and structured-output work to the Superlinked inference cluster: convert PDF/DOCX/PPTX/XLSX/HTML/scans to clean markdown, describe an image (caption + tags), or produce schema/grammar-constrained JSON off the cluster — instead of ingesting the file directly, which can reduce the tokens billed…
markdown-converter
Convert binary documents (PDF, DOCX, XLSX, PPTX, HTML, EPUB, images) to clean LLM-friendly Markdown using Microsoft's markitdown Python tool. Use when a user attaches a binary file and you need to read its contents.
lark-base
A guide for managing Lark Base, Feishu's spreadsheet-like database and workspace tool. It covers tables, fields, records, views, formulas, forms, dashboards, applications, workflows, and permissions.