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 ShaftHQ/SHAFT_ENGINE --skill technical-presentationsgit clone --depth 1 https://github.com/ShaftHQ/SHAFT_ENGINEWrote 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/shafthq/shaft_engine/technical-presentations)<a href="https://agentmods.dev/skills/shafthq/shaft_engine/technical-presentations"><img src="https://agentmods.dev/badge/skills/shafthq/shaft_engine/technical-presentations/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shafthq/shaft_engine/technical-presentations"><img src="https://agentmods.dev/badge/skills/shafthq/shaft_engine/technical-presentations.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.01084 |
| Opus 5.5 | $0.00016 | $0.00434 |
| Sonnet 5.5 | $0.00008 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
technical-presentations 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical presentations
Judgement cards for decks that teach or explain technical work. Mechanics (pptx editing, rendering, upload) belong to the host's slide tools; this skill owns pedagogy and design. Load ONE card file below, not all.
Hard rules
- Never modify the owner's source files. Every new version goes in a new file: copy, then edit the copy.
- Never remove content from an existing deck. In the owner's own files,
only add or update: hide unwanted slides (Google Slides: Slide ›
Skip slide; pptx
show="0") and move unwanted text verbatim into the speaker notes. In a new copy, a slide that has a replacement may be deleted only when its text is kept verbatim in the replacement's speaker notes; no replacement means hide. - Editable output. Real text boxes, native charts and shapes, web or Google fonts only; never text baked into an image.
- Brand hook. Use the project's brand palette file if present (for
example
palette.md,brand.md, or a theme file the owner names); check its pairs against card 9. No palette file: neutral theme plus one accent. Never invent brand colours. - No learner or audience personal data on slides, notes, or recordings; aggregate it.
First: retrieve
python3 .chaos-engine/tool.py retrieve --store mempalace "<deck> slides decision feedback": prior owner rules, feedback, rejected styles.python3 .chaos-engine/tool.py retrieve --store graphify "<topic> code examples": the real code and names the slides must match.- Record
retrieve: usedorskipped(<reason>).
Card index
| # | Card | Rule | File |
|---|---|---|---|
| 1 | Audience and outcome | One audience, one "by the end you can" per section. | plan |
| 2 | Story arc | ABT per section; alternate what is / what could be. | plan |
| 3 | Storyboard | Layout per slide first, then copy to fit. | plan |
| 4 | One idea | One idea per slide; passes the 3-second glance test. | slide |
| 5 | Assertion-evidence | Claim title (sentence, ≤2 lines) over visual evidence. | slide |
| 6 | Multimedia | Mayer: coherence, signaling, redundancy, contiguity; Appear/Fade builds only. | slide |
| 6a | Media treatment | Screenshots untinted and framed; diagrams redrawn natively; decor duotoned; logos greyscale. | slide |
| 7 | Code slides | ≤8 lines, ≥24 pt mono, highlight active line, reveal by copies. | technical |
| 8 | Data slides | One message per chart; takeaway in the title. | technical |
| 9 | Type and contrast | WCAG 4.5:1 text, 3:1 large text and marks; never colour alone. | technical |
| 10 | Retrieval checks | Recall at start; checkpoint every 7-10 slides; interaction every 5-7. | teach |
| 11 | Worked examples | Worked, then faded, then solo. | teach |
| 12 | Voice and demos | Humour tied to the point; demos rehearsed with a reset. | teach |
| 13 | Refactor a deck | New file; replace with notes, or hide. | review |
| 14 | Review | Reject the anti-pattern list; render and look. | review |
| 15 | Gotchas | Skipped slides still export to PDF; check glyphs in a real Google upload; Drive replace changes the id. | review |
What ships with it
6 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.
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 · 65 lines · 39 tokens per session scan A 5b6664803cc3
technical-presentations is a skill published in the GitHub repository ShaftHQ/SHAFT_ENGINE (417 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,084 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-20.
Other skills, from other repositories
java-exercise-generator
A Java exercise coach for test-automation engineers. The description does not provide further details about how it teaches or generates exercises.
hps-memphis-pop
A pop-culture retrospective on how 1980s design language shaped today's apps — the scenes, the turning point, and the takeaway. Built as a decision-grade story deck for talk audience, design community.
html-ppt-zhangzara-playful
A retail sales-floor training on consultative selling — the flow, the role-plays, and the daily habit that lifts conversion. Built as a decision-grade professional training deck for store associates, floor managers.
html-ppt-zhangzara-retro-windows
An IT security-awareness training on spotting phishing — the tells, the drill, and what to do in the first 60 seconds. Built as a decision-grade professional training deck for all employees.
show-me
Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
demo-setup
Repeatable HVE Core demo setup that simulates DT Coach sessions with a customer persona and scaffolds a hi-fi prototype - Brought to you by microsoft/hve-core.