Langgraph Agent Design
Design or review a LangGraph agent workflow. Use when: creating a graph, choosing state schema, nodes, tools, checkpoints, interrupts. Do not use: for simple chains, non-agent patterns.
Install
$ agentstack add skill-woliveiras-geremmyas-langgraph-agent-design ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-woliveiras-geremmyas-langgraph-agent-design) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
LangGraph Agent Design
Design LangGraph workflows around explicit state, resumability, and controlled side effects.
Process
- Define the agent goal, entrypoint, terminal states, and user-visible output.
- Define the state schema before nodes and edges.
- List tools and side effects, including authorization and idempotency needs.
- Split nodes by responsibility: read state, do one step, return state updates.
- Choose persistence/checkpointer strategy for long-running or resumable work.
- Add
interrupt()points for human-in-the-loop decisions. - Define retry, resume, cancellation, and failure behavior.
- Plan tests for node behavior, graph routing, checkpoints, interrupts, and
tool errors.
Rules
- Keep interrupt order deterministic inside each node.
- Do not hide mutable state outside the graph state unless it is a real external
system.
- Do not make non-idempotent tool calls without audit and recovery strategy.
- Prefer simple graphs until the workflow needs branches, persistence, or HITL.
Output
- State schema outline
- Node and edge map
- Tool and side-effect inventory
- Checkpoint/HITL strategy
- Test plan
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: woliveiras
- Source: woliveiras/geremmyas
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.