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 dfk1352/LibreOffice-skills --skill libreoffice-impressgit clone --depth 1 https://github.com/dfk1352/LibreOffice-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/dfk1352/libreoffice-skills/libreoffice-impress)<a href="https://agentmods.dev/skills/dfk1352/libreoffice-skills/libreoffice-impress"><img src="https://agentmods.dev/badge/skills/dfk1352/libreoffice-skills/libreoffice-impress/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/dfk1352/libreoffice-skills/libreoffice-impress"><img src="https://agentmods.dev/badge/skills/dfk1352/libreoffice-skills/libreoffice-impress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.02919 |
| Opus 5.5 | $0.00022 | $0.01168 |
| Sonnet 5.5 | $0.00011 | $0.00584 |
| Haiku 4.5 | $0.00005 | $0.00292 |
Grade A, and why
libreoffice-impress 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 2mo 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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LibreOffice Impress
Use the bundled impress modules for UNO-backed Impress presentation work.
All paths must be absolute. Bundled modules live under scripts/ in this
skill directory, so set PYTHONPATH=<skill_base_dir>/scripts.
If setup or runtime issues appear, check references/troubleshooting.md.
API Surface
# Non-session utilities
create_presentation(path)
get_slide_count(path)
export_presentation(path, output_path, export_format) # formats: "pdf", "pptx"
snapshot_slide(doc_path, slide_index, output_path, width=1280, height=720)
# Session (primary editing API)
ImpressSession(path) -> context manager
ImpressSession methods:
get_slide_count() -> int
get_slide_inventory(target: ImpressTarget) -> dict[str, object]
add_slide(index=None, layout="BLANK")
delete_slide(target: ImpressTarget)
move_slide(target: ImpressTarget, to_index)
duplicate_slide(target: ImpressTarget)
delete_item(target: ImpressTarget)
read_text(target: ImpressTarget) -> str
insert_text(text, target: ImpressTarget | None = None)
replace_text(target: ImpressTarget, new_text)
format_text(target: ImpressTarget, formatting: TextFormatting)
insert_list(items: list[ListItem], ordered: bool, target: ImpressTarget | None = None)
replace_list(target: ImpressTarget, items: list[ListItem], ordered: bool | None = None)
insert_text_box(slide: ImpressTarget, text, placement: ShapePlacement, name=None)
insert_shape(slide: ImpressTarget, shape_type, placement: ShapePlacement, fill_color=None, line_color=None, name=None)
insert_image(slide: ImpressTarget, image_path, placement: ShapePlacement, name=None)
replace_image(target: ImpressTarget, image_path=None, placement: ShapePlacement | None = None)
insert_table(slide: ImpressTarget, rows, cols, placement: ShapePlacement, data=None, name=None)
update_table(target: ImpressTarget, data)
insert_chart(slide: ImpressTarget, chart_type, data, placement: ShapePlacement, title=None, name=None)
update_chart(target: ImpressTarget, chart_type=None, data=None, placement: ShapePlacement | None = None, title=None)
insert_media(slide: ImpressTarget, media_path, placement: ShapePlacement, name=None)
replace_media(target: ImpressTarget, media_path=None, placement: ShapePlacement | None = None)
set_notes(target: ImpressTarget, text)
get_notes(target: ImpressTarget) -> str
list_master_pages() -> list[str]
apply_master_page(target: ImpressTarget, master_target: ImpressTarget)
set_master_background(target: ImpressTarget, color)
import_master_page(template_path) -> MasterPageImportResult
patch(patch_text, mode="atomic") -> PatchApplyResult
export(output_path, export_format)
reset()
close(save=True)
# Standalone patch utility
patch(path, patch_text, mode="atomic") -> PatchApplyResult
What ships with it
14 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.
- references/troubleshooting.md 3.2 KB
- scripts/colors.py 4.6 KB runs code
- scripts/constants.py 180 B runs code
- scripts/exceptions.py 748 B runs code
- scripts/impress/__init__.py 736 B runs code
- scripts/impress/core.py 2.6 KB runs code
- scripts/impress/exceptions.py 2.7 KB runs code
- scripts/impress/patch.py 15 KB runs code
- scripts/impress/session.py 52 KB runs code
- scripts/impress/snapshot.py 6.0 KB runs code
- scripts/impress/targets.py 23 KB runs code
- scripts/patch_base.py 12 KB runs code
- scripts/session.py 2.6 KB runs code
- scripts/uno_bridge.py 9.1 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.
- 2mo ago First seen · 371 lines · 54 tokens per session scan A bd344216b909
libreoffice-impress is a skill published in the GitHub repository dfk1352/LibreOffice-skills (7 stars, last pushed 10d ago), licensed MIT. It adds 54 tokens to every session and 2,919 once invoked, about $0.0002 per session on Opus 5.5. 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.
libreoffice-impress compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| libreoffice-impressdfk1352/LibreOffice-skills | Skill | 7 | 10d ago | MIT | A | 54 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| gogopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 20 | Claude Code, Codex |
| boxNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 14 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| material-organizerOrkas-AI/Orkas | Skill | 9.0k | yesterday | MIT | A | 3 | Claude Code, Codex |
| recipe-save-email-attachmentsgoogleworkspace/cli | Skill | 32k | 4d ago | Apache-2.0 | A | 20 | Claude Code, Codex |