Gamma Core Workflow ASAFE
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-core-workflow-a description: 'Generate presentations, documents, and webpages via Gamma API. Use when creating content from text prompts, configuring themes, image styles, text modes, and output formats. Trigger: "gamma generate", "gamma presentation from text", "gamma AI slides", "gamma create deck", "gamma content generation". ' allowed-tools: Read, Write, Edit, Bash(curl:*), Bash(node:*) version: 1.13.0 license: MIT author: Jeremy Longshore <[email protected]> tags: - saas - gamma - workflow - generation compatibility: Designed for Claude Code --- # Gamma Core Workflow A: Content Generation ## Output Create a workflow receipt with opaque document ID, approved audience/destination, generation/review status, owner, and next action. Do not include private source material, viewer data, or credentials. ## Examples Generate a fictional staging deck from synthetic notes, have the content owner approve sharing, and verify a duplicate job does not republish or expose content to an unapproved audience. ## Overview Generate presentations, documents, webpages, and social posts using Gamma's Generate API (`POST /v1.0/generations`). This skill covers the full parameter set: content, output format, text mode, text amount, themes, image options, sharing, folders, and export format. ## Prerequisites - Completed `gamma-sdk-patterns` (client wrapper ready) - Pro account with available credits - Workspace themes configured (optional) ## API Parameters Reference | Parameter | Type | Options | Default | |-----------|------|---------|---------| | `content` | string | Your text/prompt | Required | | `outputFormat` | string | `presentation`, `document`, `webpage`, `social_post` | `presentation` | | `textMode` | string | `generate`, `condense`, `preserve` | `generate` | | `textAmount` | string | `brief`, `medium`, `detailed`, `extensive` | `medium` | | `themeId` | string | From `GET /v1.0/themes` | Workspace default | | `imageOptions.style` | string | Free text (e.g., `"photorealistic"`, `"watercolor illustration"`) | AI default | | `exportAs` | string | `pdf`, `pptx`, `png` | None (no auto-export) | | `sharingOptions` | object | `workspaceAccess`, `externalAccess` | Workspace defaults | | `folderIds` | string[] | From `GET /v1.0/folders` | Root folder | ## Instructions ### Step 1: Basic Presentation Generation ```typescript import { createGammaClient, pollUntilDone } from "./lib/gamma"; const gamma = createGammaClient({ apiKey: process.env.GAMMA_API_KEY! }); // Simple generation — just content and format const { generationId } = await gamma.generate({ content: "Create a 10-card pitch deck for a sustainable energy startup", outputFormat: "presentation", }); const result = await pollUntilDone(gamma, generationId); console.log(`View: ${result.gammaUrl}`); ``` ### Step 2: Full Parameter Generation ```typescript // Use all available parameters for precise control async function generateFullControl() { // First, discover workspace themes const themes = await gamma.listThemes(); const corporateTheme = themes.find((t) => t.name.includes("Corporate")); // Discover folders const folders = await gamma.listFolders(); const reportsFolder = folders.find((f) => f.name === "Reports"); const { generationId } = await gamma.generate({ content: ` Q1 2026 Business Review - Revenue up 23% YoY - Customer acquisition cost reduced by 15% - Three new product lines launched - Team grew from 45 to 62 employees `, outputFormat: "presentation", textMode: "generate", // AI expands your bullet points textAmount: "detailed", // More text per card themeId: corporateTheme?.id, exportAs: "pptx", // Auto-generate PPTX download imageOptions: { style: "professional corporate photography", }, sharingOptions: { workspaceAccess: "comment", // Team can comment externalAccess: "view", // External viewers read-only }, folderIds: reportsFolder ? [reportsFolder.id] : [], }); const result = await pollUntilDone(gamma, generationId); console.log(`View: ${result.gammaUrl}`); console.log(`Download PPTX: ${result.exportUrl}`); console.log(`Credits used: ${result.creditsUsed}`); } ``` ### Step 3: Text Mode Comparison ```typescript // Same content, different text modes const content = "Benefits of remote work: flexibility, reduced commute, global talent access"; // "generate" — AI expands bullets into full paragraphs await gamma.generate({ content, textMode: "generate", outputFormat: "presentation" }); // "condense" — AI summarizes, keeps it concise await gamma.generate({ content, textMode: "condense", outputFormat: "presentation" }); // "preserve" — uses your text as-is, no AI rewriting await gamma.generate({ content, textMode: "preserve", outputFormat: "presentation" }); ``` ### Step 4: Document and Webpage Generation ```typescript // Long-form document const { generationId: docId } = await gamma.generate({ content: "Comprehensive guide to implementing CI/CD pipelines with GitHub Actions", outputFormat: "document", textAmount: "extensive", exportAs: "pdf", }); // Webpage const { generationId: webId } = await gamma.generate({ content: "Product landing page for an AI-powered code review tool", outputFormat: "webpage", imageOptions: { style: "modern minimalist tech" }, }); // Social post const { generationId: socialId } = await gamma.generate({ content: "Announcing our Series A funding round of $12M", outputFormat: "social_post", textAmount: "brief", }); ``` ### Step 5: Batch Generation with Rate Limiting ```typescript import pLimit from "p-limit"; const limit = pLimit(3); // Max 3 concurrent generations const topics = [ "Machine Learning Fundamentals", "Cloud Architecture Best Practices", "API Design Patterns", "DevOps Culture and Practices", ]; const results = await Promise.allSettled( topics.map((topic) =>
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-core-workflow-a.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 Core Workflow A 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 Core Workflow A 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 Core Workflow A access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Gamma Core Workflow A 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.