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/p47phoenix/claude-plugins/presentationnpx skills add P47Phoenix/Claude-Plugins --skill presentationgit clone --depth 1 https://github.com/P47Phoenix/Claude-PluginsWrote 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/p47phoenix/claude-plugins/presentation)<a href="https://agentmods.dev/skills/p47phoenix/claude-plugins/presentation"><img src="https://agentmods.dev/badge/skills/p47phoenix/claude-plugins/presentation.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 | $0.00114 | $0.02683 |
| Opus 5 | $0.00057 | $0.01341 |
| Sonnet 5 | $0.00023 | $0.00537 |
| Haiku 4.5 | $0.00011 | $0.00268 |
Grade A, and why
presentation 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 yesterday.
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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Presentation Composer
Design Principle: Compose, Don't Create
This skill is a mini-orchestrator, not a content creator. The Composer assembles contributions from delivery team roles (PO, Data Analyst, Developer, Architect, QA) into a cohesive presentation. Each contributing role loads its own skill to produce domain-accurate content. The Composer shapes tone, flow, density, and format — the team creates the content.
Context isolation: Contributing roles run as sub-agents with only their relevant artifacts. The Composer reads their draft outputs from disk. No role's full context leaks into another.
Signal: SKILL_LOADED: presentation
Phase 1: Type Detection
Detect type from user request using keyword matching. If ambiguous, ask — never guess.
| Type | Keywords | Detail |
|---|---|---|
| Sprint Review | "sprint review", "what we delivered", "sprint demo", "end of sprint" | references/types/sprint-review.md |
| Feature Pitch | "pitch", "propose", "sell this feature", "why we should build" | references/types/feature-pitch.md |
| Stakeholder Update | "status update", "executive update", "progress report", "stakeholder" | references/types/stakeholder-update.md |
| Technical Deep-Dive | "technical presentation", "architecture overview", "deep dive", "how it works" | references/types/technical-deep-dive.md |
| Investor Pitch | "investor pitch", "fundraising deck", "pitch to investors" | references/types/investor-pitch.md |
| Roadmap | "roadmap", "quarterly plan", "what's coming next" | references/types/roadmap.md |
| Product Demo | "product demo", "feature demo", "show what we built", "demo for publisher" | references/types/product-demo.md |
| Onboarding | "onboarding", "project handoff", "team orientation", "getting started" | references/types/onboarding.md |
| Retrospective Summary | "retro summary", "retrospective presentation", "what we learned" | references/types/retrospective-summary.md |
Pipeline Auto-Detection (when type not explicit)
What ships with it
24 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.
- references/data-visualization.md 5.2 KB
- references/flow/assemble.md 1.0 KB
- references/flow/compose.md 8.4 KB
- references/flow/content-gate.md 1.7 KB
- references/flow/draft.md 1.6 KB
- references/flow/review-gate.md 1.6 KB
- references/flow/user-review.md 3.1 KB
- references/formats/marp.md 426 B
- references/formats/paste-ready.md 333 B
- references/formats/pptx.md 805 B
- references/formats/structured-markdown.md 372 B
- references/marp-templates.md 4.3 KB
- references/narrative-patterns.md 23 KB
- references/slide-structure.md 11 KB
- references/types/feature-pitch.md 512 B
- references/types/investor-pitch.md 562 B
- references/types/onboarding.md 758 B
- references/types/product-demo.md 811 B
- references/types/retrospective-summary.md 1.1 KB
- references/types/roadmap.md 683 B
- references/types/sprint-review.md 557 B
- references/types/stakeholder-update.md 521 B
- references/types/technical-deep-dive.md 505 B
- scripts/generate_pptx.py 15 KB runs code
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.
- yesterday First seen · 186 lines · 114 tokens per session scan A eaf280c2c857
presentation is a skill published in the GitHub repository P47Phoenix/Claude-Plugins (2 stars, last pushed 3mo ago), licensed MIT. It adds 114 tokens to every session and 2,683 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…