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/veigap/talksmith/pptx-learnnpx skills add veigap/talksmith --skill pptx-learngit clone --depth 1 https://github.com/veigap/talksmithWhat 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 | $0.00090 | $0.02291 |
| Opus 5 | $0.00045 | $0.01145 |
| Sonnet 5 | $0.00018 | $0.00458 |
| Haiku 4.5 | $0.00009 | $0.00229 |
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.
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 — 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.md → Output) |
| Edited (A) — human-corrected | The .pptx the presenter edited and handed to reconcile |
the deck path passed to talksmith:pptx-extract |
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.
- 2d ago First seen · 84 lines · 90 tokens per session scan A 032f4513e14d
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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…
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.
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.