talksmith:pptx-learn

A learning tool for presentation decks that studies corrections a person made in Keynote or PowerPoint. It uses those changes to suggest reusable layout rules for future decks.

In plain words
What is it for?
Use it after a strict deck has been hand-corrected to analyze recurring changes to positions, sizes, fonts, and fills. It can run automatically after deck merging or be started when needed.
Why use it?
It separates general template problems from one-off adjustments, so accidental changes do not become rules that harm later presentations.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/veigap/talksmith/pptx-learn
Any agent
npx skills add veigap/talksmith --skill pptx-learn
Clone the repo
git clone --depth 1 https://github.com/veigap/talksmith

Made for: Claude Code, Codex.

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,291 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00090 $0.02291
Opus 5 $0.00045 $0.01145
Sonnet 5 $0.00018 $0.00458
Haiku 4.5 $0.00009 $0.00229

Measured 2d ago against content hash 032f4513e14d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

talksmith:pptx-learn 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (learn_patterns.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/pptx-learn/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

talksmith:pptx-learn — Learn strict patterns from human edits

Talksmith renders a strict deck; the presenter opens it in Keynote/PowerPoint and hand-corrects positions, sizes, fonts, and fills. Those corrections are the best possible signal for what the generator should have done. This skill turns a deck's real edits into declarative conformance patterns the strict renderer can apply next time.

This is an LLM-heavy analysis, not a mechanical diff. The Python measures; the LLM decides. A geometry delta is only evidence — the value is in the reasoning the measurement can't supply:

  • Why did the presenter make this change? (e.g. "the template floats divider titles too high above the dead space")
  • Does it generalize? A recurring delta can still be a content-specific one-off — the human nudged three titles because those titles were long, not because all titles should move. Recurrence count can't tell a template rule from a coincidence; only judgement (ideally seeing the before/after slides) can. Promoting a coincidence as a rule would degrade every future deck, so this filter is the point of the skill.
  • What decision does it encode, stated as a rule with a defensible rationale.

The Python (learn_patterns.py) exists to keep that reasoning grounded — the LLM never invents a delta the diff didn't measure — and to do the counting/aggregation cheaply. But the analysis is the LLM's job.

strict-only. Free-form and html-strict render their own layouts and are never judged against a fixed template, so there is nothing to learn against. If the render being reconciled was not strict, this skill no-ops and says so.

The two decks it compares

What Where
Baseline (B) — as generated The deck Talksmith produced, before any human touched it geometry snapshot output/final.generated.geometry.json (written at strict render — see md-to-deck SKILL.mdOutput)
Edited (A) — human-corrected The .pptx the presenter edited and handed to reconcile the deck path passed to talksmith:pptx-extract

Read the full file on GitHub · 84 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 84 lines · 90 tokens per session scan A 032f4513e14d

Subscribe to this mod's changes

talksmith:pptx-learn is a skill published in the GitHub repository veigap/talksmith (10 stars, last pushed 4d ago), licensed MIT. It adds 90 tokens to every session and 2,291 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens