What is wandb-project-analyst?

An analysis guide for Weights & Biases (W&B), a service that stores machine-learning runs, model files, evaluations, and AI application traces.

Use it to compare runs and models, inspect training histories and settings, diagnose failed traces, review evaluations and artifacts, and prepare findings.

It helps explain what happened in a project using recorded evidence instead of guesswork. It also keeps observed results separate from interpretations and recommendations.

wandb-project-analyst — Skill for Claude Code by happyhappy-jun

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add happyhappy-jun/writing-driven-autoresearch --skill wandb-project-analyst

Clone the repo

git clone --depth 1 https://github.com/happyhappy-jun/writing-driven-autoresearch

Made for: Claude Code.

Or install ralphthon-icml, the plugin that ships this one along with the rest of its 8 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/happyhappy-jun/writing-driven-autoresearch/wandb-project-analyst/github.svg)](https://agentmods.dev/skills/happyhappy-jun/writing-driven-autoresearch/wandb-project-analyst)

Your own site

<a href="https://agentmods.dev/skills/happyhappy-jun/writing-driven-autoresearch/wandb-project-analyst"><img src="https://agentmods.dev/badge/skills/happyhappy-jun/writing-driven-autoresearch/wandb-project-analyst/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/happyhappy-jun/writing-driven-autoresearch/wandb-project-analyst"><img src="https://agentmods.dev/badge/skills/happyhappy-jun/writing-driven-autoresearch/wandb-project-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 766 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00096	$0.00766
Opus 5.5	$0.00038	$0.00306
Sonnet 5.5	$0.00019	$0.00153
Haiku 4.5	$0.00010	$0.00077

Measured 2mo ago against content hash e4a4e3f6484a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wandb-project-analyst scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

ralphthon-icml/skills/wandb-project-analyst/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

W&B Project Analyst

Use W&B MCP as the primary interface for reading and analyzing data already stored in W&B. Ground conclusions in retrieved run, trace, evaluation, and artifact evidence.

Operating Rules

Identify the entity, project, time range, metric, and comparison target from the request or discover missing scope with MCP.
Probe unfamiliar Models projects and infer unfamiliar Weave schemas before querying them.
Use summary-level trace data for broad analysis and full trace payloads only for a small set of relevant traces.
Prefer purpose-built history, comparison, diagnosis, and evaluation tools over manual broad queries.
Distinguish observed facts from inferences and recommendations. Include run ids, trace ids, artifact versions, timestamps, or W&B links when available.
Confirm full retrieval for broad rankings instead of assuming the newest page is complete.
Do not persist an analysis run or create a W&B Report unless the user explicitly asks to save or publish the findings.
Never request, print, or store the value of WANDB_API_KEY.
Use the official wandb-primary skill when available for W&B SDK patterns or as a fallback when an MCP capability is unavailable.

Workflow

Normalize the analytical question and target W&B project.
Verify MCP access. If the entity or project is unknown, discover it before proceeding.
Select the product surface:
- Models runs: probe keys, then query runs, histories, comparisons, or diagnoses.
- Weave traces: infer the schema, then count or query traces and resolve roots when needed.
- Evaluations: use evaluation summaries before raw trace analysis.
- Artifacts and Registry: list, inspect, and compare explicit versions.
Retrieve only the fields and time range needed to answer the question.
Compute or synthesize the answer, checking denominators, missing data, and baseline comparability.
Return evidence, caveats, and the next useful investigation.
If explicitly requested, log computed analysis values and create a W&B Report.

Read the full file on GitHub · 70 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/mcp-analysis-workflows.md 2.6 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 70 lines · 96 tokens per session scan A e4a4e3f6484a

Subscribe to this mod's changes

wandb-project-analyst is a skill published in the GitHub repository happyhappy-jun/writing-driven-autoresearch (23 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 96 tokens to every session and 766 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metrics

wandb-project-analyst next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
wandb-project-analysthappyhappy-jun/writing-driven-autoresearch	Skill	23	3mo ago	Apache-2.0	A	96	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code