skills/beam/beam-tools/get-beam-agent-graph/SKILL.md
Fetch and save Beam.ai agent graph JSON via API. Load when user says "get agent graph", "fetch beam graph", "download agent graph", "beam agent graph", "get graph for agent", or provides a workspace ID and agent ID to retrieve the graph structure.
npx skillsauth add beam-ai-team/beam-next-skills get-beam-agent-graphInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Fetch agent graph JSON from Beam.ai API and save to local storage with meaningful filename.
This skill is read-only for Beam state. Before fetching or saving a graph, show the workspace ID, agent ID, API host, output directory, and whether an existing file may be overwritten. Require explicit user approval in the current turn before writing graph JSON to disk or sharing it outside the local workspace. Do not update, publish, run, or delete Beam agents from this skill.
This skill retrieves the complete agent graph structure from Beam.ai including nodes, edges, configurations, and metadata. It authenticates with the Beam API, fetches the graph for a specific agent, and stores it locally for analysis, backup, or documentation purposes.
Key Features:
04-workspace/beam-graphs/Time Estimate: 1-2 minutes
Check if BEAM_API_KEY exists in .env:
grep "BEAM_API_KEY" ../.env
If missing:
[ERROR] BEAM_API_KEY not found in .env
Please add your Beam API key to .env:
BEAM_API_KEY=your-key-here
Ask user to provide their Beam API key and add it to .env file.
Required inputs:
Ask user if not provided:
To fetch the agent graph, I need:
1. Workspace ID: <uuid>
2. Agent ID: <uuid>
Please provide both IDs.
Run the get_agent_graph.py script:
python3 03-skills/get-beam-agent-graph/scripts/get_agent_graph.py <workspace_id> <agent_id>
Optional: Specify custom output directory:
python3 03-skills/get-beam-agent-graph/scripts/get_agent_graph.py <workspace_id> <agent_id> --output ./custom/path
The script will:
/auth/access-token to get access token/agent-graphs/{agentId} to fetch graph04-workspace/beam-graphs/{filename}.jsonOn success:
[SUCCESS] Agent graph saved to: 04-workspace/beam-graphs/AgentName_162e7c30_graph_20260105_143022.json
Read the saved file to confirm:
cat 04-workspace/beam-graphs/<filename>.json | head -20
Show user:
For detailed API documentation, see references/api-reference.md.
Quick reference:
Step 1: Get Access Token
POST https://api.beamstudio.ai/auth/access-tokenx-api-key: <BEAM_API_KEY>access_tokenStep 2: Get Agent Graph
GET https://api.beamstudio.ai/agent-graphs/{agentId}Authorization: Bearer <token>, x-workspace-id: <workspace_id>Filename pattern:
{AgentName}_{agentId_first8}graph_{timestamp}.json{agentId}_graph_{timestamp}.jsonExample filenames:
TrueSearch_Scheduler_162e7c30_graph_20260105_143022.json
162e7c30-0d95-49ab-af99-7eef872a2d0d_graph_20260105_143022.json
Storage location:
04-workspace/beam-graphs/
Common errors:
| Error | Cause | Solution | |-------|-------|----------| | BEAM_API_KEY not found | Missing from .env | Add to .env file | | 401 Unauthorized | Invalid API key | Check BEAM_API_KEY value | | 404 Not Found | Invalid agent ID | Verify agent ID is correct | | 403 Forbidden | No workspace access | Check workspace ID and permissions |
For API details: See references/api-reference.md
scripts/get_agent_graph.py - Main script to fetch and save agent graphs
references/api-reference.md - Beam API documentation
About Beam API Authentication:
About Storage:
04-workspace/beam-graphs/--output flagAbout Graph Data:
tools
Build a Palantir-shape, PDF-native use-case proposal document for a sophisticated enterprise account: research-grounded use cases (each with description, challenge, impact, value), an operating-graph ontology page, a recommended PoC with a week-by-week plan, and a closing page that asks for one decision. Load when a client asks us to 'propose high-impact use cases', requests a use-case presentation/catalog for a function (finance, HR, ops), or when a technical evaluation team will review candidates to pick a PoC. NOT for single-account cold outreach (use prospect-brief), full process diagnostics (use operating-diagnostic), or priced proposals (use proposal-creation).
development
Convert Beam Figma slide designs into high-fidelity, editable HTML presentation decks. Use when Codex is asked to audit Figma slides, extract slide templates, rebuild Beam slides as HTML decks, decide whether Figma imagery should be exported or rebuilt in HTML/CSS, create Beam/Prism-compatible deck templates, or improve fidelity of existing Beam HTML slide rebuilds.
development
Use the Beam AI reusable slide library: individual HTML slide templates extracted from Beam Figma rebuilds, kept separate from deck themes and full deck templates. Load when the user asks for a slide library, specific Beam slide patterns, reusable Figma-inspired slides, Prism slide-library items, or slide-level HTML templates.
development
Use Beam AI deck and report design packs, HTML templates, and curated examples to create sales decks, customer intro decks, RPO decks, and DIN A4 use-case proposal reports. Load when the user asks for Beam-branded presentation templates, Prism-compatible deck templates, Beam report templates, customer intro decks, commercial proposals, or reusable HTML deck/report examples.