Experimental Rehearsal Presentation — AI skill for Claude Code
Auditing a field-experiment proposal with an AI agent: a real Claude Code session, console on the left, commentary on the right.
How to install Experimental Rehearsal Presentation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open ericcgladstone-maker/experimental-rehearsal-presentation and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Experimental Rehearsal Presentation does
Auditing a field-experiment proposal with an AI agent: a real Claude Code session, console on the left, commentary on the right. Replies and tool output verbatim; the organization and proposal are fictional.
Alternatives in AI
- Guizang Ppt Skill — AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts 24.9k ★
- CodeIsland — Real-time AI coding agent status panel in your MacBook notch — live status, approvals & replies for 13 AI tool 2.3k ★
- Humanize Ppt — AST-based outline director for human-centered AI presentation workflows 934 ★
README
Auditing a field-experiment proposal with an AI agent
Eric Gladstone · research walkthrough · independent work · September 2026. The presentation's own header reads "Experimental rehearsal · Proposal audit".
A real Claude Code session, presented as it was worked through. The Claude Code console is on the left and my commentary is on the right. The session reviews a proposed field experiment in 23 steps. It starts by reconstructing what the proposal commits to. It then audits assignment, measurement, timing, precision and cost. Next it rehearses possible results before any data exist, simulates worlds the design cannot tell apart, repairs the design, and retests the repair. It ends with a funding decision under stated conditions.
- Live: https://experimentalrehearsal.eric-c-gladstone.workers.dev
- Also at: https://graystoneindustries.co/talks/ (embedded)
What is verbatim and what is editorial
The questions are mine. Claude's replies and tool output are verbatim, from one continuous session (Claude Code 2.1.282, Opus 5.5), recorded 24–25 September 2026. Timing, grouping into parts, focus, and the commentary on the right are editorial.
The organization, its proposal and its background materials are fictional, written for this demonstration. The session ran in an isolated directory, and local paths and account names are removed from the published data.
Use
Open it and step with ← →. Use shift+← → to move between sections and space to play. A− / A+ (or the - and = keys) change the terminal text size. URL options: `?s=&b=` opens at a given point, `?play=1` autoplays, `?t=` sets the terminal size, and `?embed=1` fills its frame for embedding.
Run locally with any static server, for example `python3 -m http.server 4690 --directory public`.
Files
`public/` is the whole site: `index.html`, `app.js`, `style.css`, `data/session.js` (the session, as the page plays it), `data/walkthrough.js` (the commentary), self-hosted Geist fonts
Related Skills
Kivun Terminal Wsl
Claude Code with Hebrew, Arabic and Persian rendered correctly. Most terminals have no bidirectional text engi
Fidelis
Zero-LLM agent memory for Claude Code and AI agents: local-first BM25, dense-vector, and reciprocal-rank-fusio
Baileys Skill
High-accuracy Baileys knowledge base for AI coding agents (Claude Code, OpenCode, Codex, Antigravity, and more
Dsh Auto Evolve
A self-evolving plugin for DeepSeek Harness (dsh). It observes how the agent runs, proposes improvements to it
LLM Bidding System
Auction router and supervised patch proposal workflow for LLM coding agents
Love Video
Turn travel photos into AI-generated emotional videos (proposal/birthday/anniversary). A Claude Code skill pow
Related Agents
Drafting Agent
Template-filling agent for any stage. Use when one named template needs a first complete draft from supplied e
Script Writer
Specialist agent for writing speaker notes (presentation scripts) for Quarto RevealJS decks - paper reviews, c
Slides Maker
Use when experiment findings, a research argument, or project onboarding material needs a presentation artifac