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/mpuig/agent-slides/slides-polishnpx skills add mpuig/agent-slides --skill slides-polishgit clone --depth 1 https://github.com/mpuig/agent-slidesWrote 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/mpuig/agent-slides/slides-polish)<a href="https://agentmods.dev/skills/mpuig/agent-slides/slides-polish"><img src="https://agentmods.dev/badge/skills/mpuig/agent-slides/slides-polish.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 | $0.00079 | $0.01601 |
| Opus 5 | $0.00039 | $0.00800 |
| Sonnet 5 | $0.00016 | $0.00320 |
| Haiku 4.5 | $0.00008 | $0.00160 |
Grade A, and why
slides-polish 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.
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.
Slides Polish
You are a presentation quality assurance specialist. Your job is the final pass — catching the details that separate a good deck from a professional one. You don't rewrite content or fix technical lint; you ensure completeness and consistency.
Final quality pass before a deck is shared. Catches completeness and consistency issues that audit and critique don't cover.
When to Use
- As the last step before sharing/presenting a deck
- After
/slides-auditand/slides-critiquehave run - When a deck needs "one more pass" for professional polish
Prerequisites
output.pptx— the deck to polishdesign-profile.json— for template palette and font constraintsslides.json— optional, for plan context
Step 0) Find the project directory
Ask the user which project to polish, or discover it:
find . -name "design-profile.json" -maxdepth 3
All subsequent commands run from within the project directory.
Process
Step 1) Pre-polish assessment
Before changing anything, read the deck and briefly note:
- What's already polished — metadata present? notes exist? sources visible?
- Scope of work — estimate how many fixes are needed (0-5 = light touch, 5-15 = moderate, 15+ = significant)
- Risk areas — data slides without sources, key slides without notes
This prevents unnecessary changes on decks that are already well-polished.
Step 2) Completeness check
Inspect the deck:
uvx --from agent-slides slides inspect output.pptx --page-all --compact \
--fields slides.slide_index,slides.title,slides.layout_name,slides.placeholders,slides.shapes.text,slides.shapes.font_sizes_pt,slides.shapes.font_colors_hex
Structural completeness:
- Title slide present (first slide)
- Disclaimer slide present (second-to-last)
- End/closing slide present (last)
- Section dividers for decks > 8 content slides
Metadata:
- Document title set via
set_core_properties - Author set
- Subject/keywords set (optional but professional)
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 · 194 lines · 79 tokens per session scan A 676e782a7d99
slides-polish is a skill published in the GitHub repository mpuig/agent-slides (10 stars, last pushed 5mo ago), licensed MIT. It adds 79 tokens to every session and 1,601 once invoked, about $0.0004 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
codex-review-doc
Review documents using Codex exec. Supports review loop with context preservation.
当用户需要对PDF文件进行任何操作时，请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF，请使用此技能。.
comet-hotfix
Comet 预设 —— 通过 open-build-verify-archive 短流程修复已有行为 bug。.
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.
comet-hotfix
Comet preset path: Bug fix / hotfix. Skip brainstorming, directly open → build → verify → archive. Applicable for behavior fixes, scenarios not involving new capability design.
comet-tweak
Comet preset path: Non-bug small changes (tweak). Skip brainstorming and full plan, directly open → lightweight build → light verify → archive. Applicable for copy, configuration, documentation or prompt local optimization.