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 agentmods add skills/qiuy-collab/autoflow.skill/presentation-skillnpx skills add qiuy-collab/AutoFlow.skill --skill presentation-skillgit clone --depth 1 https://github.com/qiuy-collab/AutoFlow.skillWrote 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/qiuy-collab/autoflow.skill/presentation-skill)<a href="https://agentmods.dev/skills/qiuy-collab/autoflow.skill/presentation-skill"><img src="https://agentmods.dev/badge/skills/qiuy-collab/autoflow.skill/presentation-skill.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00411 |
| Opus 5 | $0.00014 | $0.00205 |
| Sonnet 5 | $0.00006 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
presentation-skill 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 6d 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
AutoFlow Presentation Skill
This is the curated local route from siril9/presentation-skill. It keeps the
upstream skill's core contract while exposing only files that are checked into
this integration and can be verified by AutoFlow.
Non-negotiable workflow
- Treat
outline.json, evidence, data, and figure sources as the source of truth. - Build through the checked-in renderer; do not write one-off
python-pptxorpptxgenjsscripts in a task workspace. - Keep text, charts, tables, and shapes editable where practical.
- Run geometry/design QA before delivery and perform rendered visual review when the runtime supports it.
- Never install dependencies or call a remote package during a deck task. A
missing runtime is a
blockedcapability, not permission to improvise.
Supported local surface
Quick deck generation:
python scripts/presentation_adapter.py build \
--outline <outline.json> --output <deck.pptx> --style-preset <preset>
Strict structural QA:
python scripts/presentation_adapter.py qa \
--input <deck.pptx> --outdir <qa-dir> --skip-render
Inventory and source extraction are available for existing decks. The adapter
reports exact missing dependencies before executing any renderer or QA command.
The renderer needs Node.js plus pptxgenjs; strict QA needs Python plus
python-pptx; rendered image review additionally needs a working office/PDF
conversion chain.
Read the task-specific references under references/ rather than loading the
entire upstream corpus. AutoFlow's VISUAL_STOP remains authoritative: a PPT
step is not consumable by Word or package until the assembled deck is shown and
approved.
What ships with it
29 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.
- AUTOFLOW_ADAPTER.md 790 B
- integration_manifest.json 1.1 KB
- LICENSE 1.0 KB
- package.json 9.9 KB
- references/editing.md 12 KB
- references/model_adaptive_workflow.md 3.9 KB
- references/outline_schema.md 44 KB
- references/pptxgenjs.md 7.6 KB
- references/renderer_role_contracts_v2.json 38 KB
- references/reproducible_workflow.md 5.1 KB
- references/visual_qa_prompt.md 4.5 KB
- scripts/build_deck_pptxgenjs.js 62 KB runs code
- scripts/design_rules_qa.py 21 KB runs code
- scripts/design_tokens.py 20 KB runs code
- scripts/extract_outline.py 4.1 KB runs code
- scripts/inventory.py 10 KB runs code
- scripts/layout_lint.py 38 KB runs code
- scripts/presentation_adapter.py 11 KB runs code
- scripts/qa_gate.py 20 KB runs code
- scripts/render_mermaid.py 8.9 KB runs code
- scripts/render_slides.py 8.6 KB runs code
- scripts/visual_qa.py 7.7 KB runs code
- templates/pptxgenjs/presets.js 5.6 KB runs code
- templates/pptxgenjs/README.md 8.1 KB
- templates/pptxgenjs/role_layout_contracts.js 4.3 KB runs code
- templates/pptxgenjs/slides.js 278 KB runs code
- UPSTREAM_DESIGN.md 13 KB
- UPSTREAM_SKILL.md 13 KB
- UPSTREAM.md 780 B
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.
- 6d ago First seen · 50 lines · 28 tokens per session scan A 3f894ff0d08e
presentation-skill is a skill published in the GitHub repository qiuy-collab/AutoFlow.skill (2 stars, last pushed 20d ago), licensed MIT. It adds 28 tokens to every session and 411 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
ppt-master
AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable Brand/Style/Layout/Deck workspaces, filling native PPTX templates, and enhancing finished PPTX files. Use when the user asks to create, generate, reconstruct, regenerate, beautify, redesign…
document-generation
Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. Use when someone needs a deliverable rather than an answer — a change record to attach to a CR, an audit workbook for a compliance reviewer, a…
codex-ppt
Generate visually unified image-based PPT/PPTX decks from articles, reports, papers, notes, or outlines.
office-artifacts
Use when creating, opening, reading, or editing Office artifacts such as LibreOffice-native ODT/ODS/ODP files and compatibility DOCX/XLSX/PPTX files with the officeartifact tool.
presentations
Use when building, theming, or exporting a presentation deck — pitch, sales, keynote, board/QBR, leave-behind one-pager — from slide structure to a token-based theme to PDF or editable PPTX (Marp, Slidev, python-pptx). NOT the words (that is marketing), NOT the visual tokens (that is design), NOT the investor story…
document-processing-expert
Read, generate and modify office documents and PDFs from code: PDF extraction and forms, Word documents, Excel workbooks and PowerPoint decks. Use when the user mentions PDF, DOCX, XLSX, PPTX, Word, Excel, PowerPoint or spreadsheets, wants data extracted from documents, needs a report or invoice generated as a file…