---
title: "Weave Instrumentation: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/wandb-weave-instrument/
description: "Adds Weave tracing to Python or TypeScript agents one path at a time, with read-back checks of the stored spans."
---

# Weave Instrumentation: review, setup & limitations · Undominated.ai

> Adds Weave tracing to Python or TypeScript agents one path at a time, with read-back checks of the stored spans.

[← Explore all skills](/skills/)

OBSERVABILITY / Weights & Biases

# Weave Instrumentation

Adds Weave tracing to Python or TypeScript agents one path at a time, with read-back checks of the stored spans.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/wandb/skills/tree/4efbb9fd82e8076cbe5d2332167b19f2bba90d85/skills/weave-instrument)

SOURCE REVIEW

 Reviewed 2026-10-13
 Evidence 3 linked sources
 Publisher Weights & Biases
 Licence [Apache-2.0 ↗](https://github.com/wandb/skills/blob/4efbb9fd82e8076cbe5d2332167b19f2bba90d85/LICENSE)
 Revision 4efbb9fd82e8
 [Read what was—and wasn’t—checked ↓](#review)

“Add Weave tracing to Python or TypeScript agents and LLM applications. Use when asked to instrument model calls, tools, or agent turns with Weave.”

 [Weights & Biases · upstream description ↗](https://github.com/wandb/skills/blob/4efbb9fd82e8076cbe5d2332167b19f2bba90d85/skills/weave-instrument/SKILL.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - The file stops before any edit when no valid W&B login exists, forbids running wandb login in the agent session, and says not to read, print or ask for an API key.
- It treats empty results, failed queries and unavailable checks as unverified rather than passes, and says an init banner or successful flush is not proof of delivery.

### A good fit for

 - Instrumenting model calls, tool calls and agent turns with Weave
- Checking that emitted spans match the actual execution before extending tracing

### Weigh up before choosing

 - Mechanism choice and verification rely on six reference files that were not opened for this review.
- The README marks the skill experimental and lists SDK floors (Python >=3.13, weave >=0.52.41). The install command does not pin this revision.
- The file says it was adapted from wandb/weave at commit c003a2f. That upstream copy was not compared.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - skills/weave-instrument/SKILL.md (login check, mechanism choice, incremental implementation, verification)
- README.md (requirements table, skill table, installation)
- LICENSE Apache-2.0 text

### Our findings

 - Turn, LLM, tool and subagent spans are checked by gen_ai.operation.name values invoke_agent, chat and execute_tool.
- The file requires preserving provider tool-call IDs and closing spans on failure.

### Not established by this review

 - The installer was not run, and the skill was not executed against a project or service. No W&B project was contacted.
- The references/ files and the upstream wandb/weave copy were not opened.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

[Upstream setup instructions ↗](https://github.com/wandb/skills/blob/4efbb9fd82e8076cbe5d2332167b19f2bba90d85/README.md)

DOCUMENTED COMMAND

 npx skills add wandb/skills Copy command ↗

Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.

 - The README documents npx skills add wandb/skills and selecting one skill with --skill <name>; the skill table names this skill weave-instrument.
- The command does not pin revision 4efbb9fd82e8076cbe5d2332167b19f2bba90d85. Compare the installed SKILL.md and references with that revision.
- Set up the W&B login yourself in a separate terminal; the skill tells the agent not to collect the key in chat.

### Before you start

 - Node.js and npm for the documented Skills installer
- A W&B account and an application that can reach the target entity/project

### Compatibility

Agent Skills-compatible hosts · Claude Code · Codex · Weave Python and TypeScript SDKs

### Implementation

Python · TypeScript

### Host-mediated application code and W&B trace uploads

 - Edits application code to initialise Weave and add spans.
- Sends trace data, including model inputs and outputs, to the configured W&B entity/project once credentials exist.

### Cost model

Source is Apache-2.0. W&B Weave ingestion and storage can incur charges. Those charges were not measured.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Skill definition ↗](https://github.com/wandb/skills/blob/4efbb9fd82e8076cbe5d2332167b19f2bba90d85/skills/weave-instrument/SKILL.md) Checked 2026-10-13 https://github.com/wandb/skills/blob/4efbb9fd82e8076cbe5d2332167b19f2bba90d85/skills/weave-instrument/SKILL.md Supports: summary, upstreamDescription, whySelected, limitations, access, review
- [Install instructions and skill index ↗](https://github.com/wandb/skills/blob/4efbb9fd82e8076cbe5d2332167b19f2bba90d85/README.md) Checked 2026-10-13 https://github.com/wandb/skills/blob/4efbb9fd82e8076cbe5d2332167b19f2bba90d85/README.md Supports: install, compatibility
- [Repository licence ↗](https://github.com/wandb/skills/blob/4efbb9fd82e8076cbe5d2332167b19f2bba90d85/LICENSE) Checked 2026-10-13 https://github.com/wandb/skills/blob/4efbb9fd82e8076cbe5d2332167b19f2bba90d85/LICENSE Supports: license

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Arize Instrumentation Health ↗ Read-only audit of exported Arize spans for nine instrumentation defects, including missing token counts behind empty cost dashboards.](/skills/arize-ai-arize-instrumentation-health/)[### Grafana Alloy ↗ Write a Grafana Alloy pipeline, validate it before running it, and treat an unhealthy component on the local UI as the failure.](/skills/grafana-alloy/)[### Grafana Tempo ↗ Local and Helm setup notes plus TraceQL for a Tempo tracing backend.](/skills/grafana-tempo/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
