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 darellchua2/opencode-config-template --skill pptx-template-modifier-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote 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/darellchua2/opencode-config-template/pptx-template-modifier-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/pptx-template-modifier-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/pptx-template-modifier-skill.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.04017 |
| Opus 5 | $0.00022 | $0.02008 |
| Sonnet 5 | $0.00009 | $0.00803 |
| Haiku 4.5 | $0.00004 | $0.00402 |
Grade A, and why
pptx-template-modifier-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 4d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
I am the pptx-template-modifier-skill (Capability B). When the base template.pptx is missing a layout that a slide needs, I extend the template by borrowing/cloning a layout into a derived template_new.pptx, which the pptx-generate-slide-skill engine then renders against.
I do not fill templates myself. Normal filling is the pptx-generate-slide-skill skill's job. I am invoked only when the base template is missing a layout a slide needs.
Clone policy (the default is missing-only). resolve_and_clone / plan_resolution take a clone_on argument (issue #47, "option A"):
clone_on="missing"(default) — clone only when a slide_type's layout is genuinely missing/unknown. Over-limit content (body larger than its placeholder) is NOT cloned under this policy; it is logged as a warning and handled by the density downshift inpptx-subagent(Stage 2).clone_on="any"— also clone for over-limit content (the original Capability B behaviour). Opt-in; the agent never passes this.
The 4 stakeholder steps
My pipeline mirrors the four steps a human designer performs:
- Read the template — resolve the render contract via
ppt_builder.get_render_contract(US-4.1: prefers the embedded JSON, falls back to the P0 introspection enginetemplate_introspector) to get the full contract: layouts, placeholder fingerprints,content_area_in2, theme, slide size. - Read the Slide Master —
template_reader.read_master()reads master-level placeholders + theme (on top of the contract). - Understand the requirement —
constraint_checker.evaluate_slide()estimates the content area a slide needs (from its word count) and compares it against the layout'scontent_area_in2, yielding a fits / over-limit verdict. It also flags aslide_typewhose layout is missing. - Missing → create — when a slide_type's layout is missing (the default
clone_on="missing"policy),state_machine.plan_resolution()plans a clone; P4'slayout_creatorperforms the actual XML/part clone intotemplate_new.pptx. Under the default policy over-limit slides are not cloned (option A) — only missing-layout slides are.
What ships with it
21 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.
- scripts/constraint_checker.py 4.3 KB runs code
- scripts/container_check.py 10 KB runs code
- scripts/contrast_check.py 15 KB runs code
- scripts/designer_promoter.py 39 KB runs code
- scripts/layout_creator.py 8.9 KB runs code
- scripts/master_cloner.py 8.2 KB runs code
- scripts/pptx_validate.py 8.8 KB runs code
- scripts/state_machine.py 12 KB runs code
- scripts/tests/conftest.py 1.6 KB runs code
- scripts/tests/test_clone_reembed.py 1.7 KB runs code
- scripts/tests/test_constraint_checker.py 4.1 KB runs code
- scripts/tests/test_container_check.py 4.9 KB runs code
- scripts/tests/test_contrast_check.py 11 KB runs code
- scripts/tests/test_layout_creator.py 8.3 KB runs code
- scripts/tests/test_master_background.py 7.8 KB runs code
- scripts/tests/test_master_cloner.py 12 KB runs code
- scripts/tests/test_masterless_guards.py 3.1 KB runs code
- scripts/tests/test_p0_regression.py 8.0 KB runs code
- scripts/tests/test_state_machine.py 4.7 KB runs code
- scripts/tests/test_vision_extractor.py 10 KB runs code
- scripts/vision_extractor.py 15 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.
- 4d ago First seen · 183 lines · 44 tokens per session scan A b92a026ac3ab
pptx-template-modifier-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 4,017 once invoked, about $0.0002 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 2026-09-03.
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…
guizang-ppt-skill
A tool that creates slide-deck images from content by first making an outline and then rendering each slide. It supports multiple visual styles and is designed for decks people can read and share.
slidev
Use when the user wants to create slides, build a presentation or talk, make a deck or pitch, export slides to PDF, work with an existing slides.md, run slidev dev mode, or build a static slide site. Also applies when the user mentions "presentation", "keynote", "talk", "lecture", "deck", "slide deck", or asks to turn…
presentation-forge
A workflow for creating editable PowerPoint presentations and related visual outputs from topics, documents, slides, templates, or images. It supports Chinese business reports and can use generated visual assets.
dayan-deck
A method for making an editable HTML slide presentation from an outline, notes, document, or verified facts. Each slide has a clear job, and the deck is designed for an audience and a set presentation length.
pptx-manipulation
This skill enables programmatic creation, editing, and manipulation of Microsoft PowerPoint (.pptx) presentations using the python-pptx library. Create professional slides with text, shapes, images, charts, and tables without manual editing.