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/luccapinto/agentic-data-kit/generating-pptxnpx skills add luccapinto/agentic-data-kit --skill generating-pptxgit clone --depth 1 https://github.com/luccapinto/agentic-data-kitWhat 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 | $0.00098 | $0.00694 |
| Opus 5 | $0.00049 | $0.00347 |
| Sonnet 5 | $0.00020 | $0.00139 |
| Haiku 4.5 | $0.00010 | $0.00069 |
Grade A, and why
generating-pptx 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: generating-pptx
Produce a native, editable PowerPoint with python-pptx. Every element is a real PowerPoint
object — editable text, shapes, native charts (backed by embedded data you can edit in
PowerPoint), and tables. This is the right path when the deliverable must be .pptx and editable;
for HTML decks, interactive sites, or designed PDFs use building-html-presentations.
Why not HTML→PPTX? Exporting an HTML deck to PPTX (e.g. Marp
--pptx) embeds each slide as a flat image — not editable.python-pptxbuilds the real OOXML, so charts and text stay live.
Setup
pip install python-pptx
Build it
scripts/build_pptx.py is a working generator — a brand-themed sales deck with a title slide,
agenda, KPI slide, native charts (clustered column, line, pie), a table slide, and a closing.
Run it, then adapt:
python .claude/skills/generating-pptx/scripts/build_pptx.py --out deck.pptx
Adapt by editing the DATA, BRAND, and the build() slide calls — not the helpers.
What python-pptx gives you (the palette)
- Native charts (editable, with embedded Excel data):
COLUMN_CLUSTERED,COLUMN_STACKED,BAR_CLUSTERED,LINE,LINE_MARKERS,PIE,DOUGHNUT,XY_SCATTER,AREA,RADAR. UseCategoryChartDatafor category charts andXyChartDatafor scatter. - Tables via
slide.shapes.add_table(rows, cols, ...)— style cells, headers, number formats. - Text via placeholders or
add_textbox→text_frame→ paragraphs/runs (font, size, color, bold). - Shapes / KPI cards via
add_shape(MSO_SHAPE.ROUNDED_RECTANGLE, ...)with fill + text. - Brand: set
RGBColorfrom yourDESIGN.mdtokens; reuse one accent + semantic colors.
Rules
- Map brand from DESIGN.md — colors, and font name if defined. Keep one accent.
- Native charts over images — let the user edit data in PowerPoint.
- Never invent data — use provided numbers; mark placeholders. Add a source line per data slide.
- 16:9 by default (
Inches(13.333) × Inches(7.5)). - Action-title style: the slide title states the insight, not just the topic.
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 · 46 lines · 98 tokens per session scan A 9b9f6be1ddd8
generating-pptx is a skill published in the GitHub repository luccapinto/agentic-data-kit (7 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 694 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
release-dbt-mcp
Release a new version of dbt-mcp to PyPi.
apm-issue-autopilot
Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…
cross-squad-communication
Protocol for sending queries, delegating tasks, and sharing context between independent Squad instances across different repositories.
apm-usage
Activate when the user asks about APM (Agent Package Manager): installing, configuring, authoring, or troubleshooting AI-agent packages, dependencies, compilation, MCP servers, policy, or any apm CLI command.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
error-recovery
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.