Gamma Migration Deep DiveSAFE
Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.
Overview
Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.
4f83675ca38aOBSERVED · 2026-10-08Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: gamma-migration-deep-dive description: 'Deep dive into migrating to Gamma from other presentation platforms. Use when migrating from PowerPoint, Google Slides, Canva, or other presentation tools to Gamma. Trigger with phrases like "gamma migration", "migrate to gamma", "gamma import", "gamma from powerpoint", "gamma from google slides". ' allowed-tools: Read, Write, Edit, Bash(node:*) version: 1.13.0 license: MIT author: Jeremy Longshore <[email protected]> tags: - saas - gamma - migration compatibility: Designed for Claude Code --- # Gamma Migration Deep Dive ## Output Record source/target scope, mapping decision, staging and canary results, aggregate reconciliation, approver, and rollback state without copying content or viewer data. ## Examples Migrate a fictional presentation in staging, compare approved metadata and route behavior, introduce an unknown field, and confirm the canary stops for review. ## Current State !`npm list 2>/dev/null | head -10` ## Overview Migrate presentation workflows from PowerPoint, Google Slides, Canva, or other platforms to Gamma's AI-powered generation. Gamma takes a fundamentally different approach -- instead of manually placing slides, you provide content and Gamma generates the presentation. Migration is about converting your content pipeline, not your slide files. ## Prerequisites - Gamma API access (Pro+ plan) - Source presentations accessible for content extraction - Node.js 18+ for migration scripts - Completed `gamma-install-auth` setup ## Migration Approaches | Approach | When to Use | Effort | |----------|-------------|--------| | Content extraction + regeneration | Lots of text-heavy presentations | Medium | | Import via Gamma UI | One-off migration of key decks | Low | | Template recreation | Repeatable presentation formats | Medium | | Parallel operation | Gradual transition over time | Low | **Key insight:** You don't "import" slides into Gamma. You extract content from old presentations and regenerate them using Gamma's AI. This often produces better results than the originals. ## Instructions ### Step 1: Inventory Source Presentations ```typescript // scripts/inventory-presentations.ts import { readdir, stat } from "node:fs/promises"; import { join, extname } from "node:path"; interface PresentationInfo { path: string; format: string; sizeMB: number; lastModified: Date; } async function inventoryPresentations(dir: string): Promise<PresentationInfo[]> { const entries = await readdir(dir, { recursive: true }); const presentations: PresentationInfo[] = []; for (const entry of entries) { const ext = extname(entry).toLowerCase(); if ([".pptx", ".ppt", ".key", ".pdf", ".md"].includes(ext)) { const fullPath = join(dir, entry); const info = await stat(fullPath); presentations.push({ path: fullPath, format: ext, sizeMB: info.size / (1024 * 1024), lastModified: info.mtime, }); } } console.log(`Found ${presentations.length} presentations:`); const byFormat = presentations.reduce((acc, p) => { acc[p.format] = (acc[p.format] || 0) + 1; return acc; }, {} as Record<string, number>); console.log("By format:", byFormat); return presentations; } ``` ### Step 2: Extract Content from PowerPoint ```typescript // scripts/extract-pptx.ts // Use 'pptx-parser' or 'officegen' to extract text content import JSZip from "jszip"; import { readFile } from "node:fs/promises"; import { DOMParser } from "xmldom"; async function extractPptxContent(pptxPath: string): Promise<string[]> { const buffer = await readFile(pptxPath); const zip = await JSZip.loadAsync(buffer); const slides: string[] = []; const slideFiles = Object.keys(zip.files) .filter((f) => f.match(/ppt\/slides\/slide\d+\.xml$/)) .sort(); for (const slideFile of slideFiles) { const xml = await zip.file(slideFile)!.async("string"); const doc = new DOMParser().parseFromString(xml); // Extract all text elements const textNodes = doc.getElementsByTagName("a:t"); const texts: string[] = []; for (let i = 0; i < textNodes.length; i++) { const text = textNodes[i].textContent?.trim(); if (text) texts.push(text); } slides.push(texts.join("\n")); } return slides; } // Convert extracted content to Gamma prompt function slidesToGammaPrompt(slides: string[], title: string): string { let prompt = `${title}\n\n`; slides.forEach((content, i) => { prompt += `Slide ${i + 1}:\n${content}\n\n`; }); return prompt; } ``` ### Step 3: Batch Migration Script ```typescript // scripts/migrate-to-gamma.ts import { createGammaClient } from "../src/client"; import { pollUntilDone } from "../src/poll"; import pLimit from "p-limit"; const gamma = createGammaClient({ apiKey: process.env.GAMMA_API_KEY! }); const limit = pLimit(2); // Max 2 concurrent generations interface MigrationItem { title: string; content: string; sourceFile: string; } async function migrateBatch(items: MigrationItem[]) { const results = await Promise.allSettled( items.map((item) => limit(async () => { console.log(`Migrating: ${item.title}`); const { generationId } = await gamma.generate({ content: item.content, outputFormat: "presentation", textMode: "condense", // AI condenses extracted text exportAs: "pptx", // Get PPTX for comparison }); const result = await pollUntilDone(gamma, generationId); return { title: item.title, sourceFile: item.sourceFile, gammaUrl: result.gammaUrl, exportUrl: result.exportUrl, creditsUsed: result.creditsUsed, }; }) ) ); // Report const succeeded = results.filter((r) => r.status === "fulfilled"); const failed = results.filter((r) => r.status === "rejected"); console.log(`\nMigration complete: ${succeeded.length} succeeded,
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
4f83675ca38afull audit observations/trust-audit/skill/jeremylongshore__gamma-migration-deep-dive.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 4f83675ca38a | SAFE | B | 89 | first audit |
Questions
What does the Gamma Migration Deep Dive skill do?
Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.
Is Gamma Migration Deep Dive safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Gamma Migration Deep Dive access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Gamma Migration Deep Dive work with?
Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (4f83675ca38a), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.