Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add veigap/talksmith/plugin install talksmithWrote 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/veigap/talksmith/polish-images)<a href="https://agentmods.dev/skills/veigap/talksmith/polish-images"><img src="https://agentmods.dev/badge/skills/veigap/talksmith/polish-images.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 | $0.00000 | $0.02205 |
| Opus 5 | $0.00000 | $0.01103 |
| Sonnet 5 | $0.00000 | $0.00441 |
| Haiku 4.5 | $0.00000 | $0.00220 |
Grade C, and why
talksmith:polish-images scanned grade C with 1 finding 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 7d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- generate-image: right | the vertigo of scale — how small a single choice feels against a whole system --> How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
talksmith:polish-images — Mechanical generate-image extraction + final.md rewrite
The sibling of talksmith:polish-ascii: same shape, same Step-6 discipline, different block. Where polish-ascii extracts ```ascii fences for the diagram-illustrator, this skill extracts <!-- generate-image: … --> directives for the image-illustrator, and rewrites each into an aside image reference. The per-block slide-context scanner is shared — both skills sys.path-import skills/_shared/_context.py, so a directive's context bundle (slide_title, slide_content_prose, speaker_notes, section_title, section_goal, talk_thesis, presentation_language) is computed by exactly the same code that feeds the diagram renders.
Always operates on final.md. Step 6 begins with the editor copying draft.md → final.md; every invocation of this skill targets final.md. draft.md is read-only from Step 6 onward.
The directive
Authored by the editor into draft.md (see editor.md) on a sparse-text slide where an atmospheric image improves the slide:
<!-- generate-image: right | the vertigo of scale — how small a single choice feels against a whole system -->
<side>—leftorright(defaultrightif omitted). Which edge the full-bleed aside column sits on.<description>— a short, high-level idea of the emotion + concept the image should evoke (not a literal scene — the aside is realized as a symbolic editorial illustration). It stays concise and presenter-editable indraft.md; the image-illustrator enriches it into a full generation prompt at Step 6 (that enrichment is not stored indraft.md). The directive may span multiple lines up to the closing-->.
Canonical Step 6 sequence
Mirrors polish-ascii; the image-illustrator role owns the judgement steps.
What ships with it
1 file 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.
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.
- 7d ago First seen · 80 lines · 0 tokens per session scan C 1ecf1b3ca3eb
talksmith:polish-images is a skill published in the GitHub repository veigap/talksmith (10 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,205 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
wowerpoint
Turn one document into a kawaii NotebookLM slide-deck PDF. Use for "wowerpoint this", "make a deck about ", "turn this report into slides", or any request to render a single document as shareable narrative slides.
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…
deck-ljg-present
A presentation template that converts an outline or Markdown document into large, poster-like slides while keeping the original wording, order, and content. It uses black, red, or yellow colour themes and assigns document elements to slide layouts.
powerpoint
Create designed, editable PowerPoint .pptx presentations with PptxGenJS. Use when the user asks to create, generate, update, or inspect a deck, slide deck, presentation, or .pptx file.
skill-deck
Generate slide deck presentations from briefs — use when you need slides, pitch decks, or visual summaries.
powerpoint
PowerPoint slide deck generation and management using python-pptx with YAML-driven content and styling.