weights-and-biases

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/weights-and-biases/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, mostly-executable W&B reference with strong code coverage and real reference files, but it over-inlines detail that belongs in the references and lacks validation checkpoints in its batch workflows.

Suggestions

Move the full sweep-strategy and integration examples into references/sweeps.md and references/integrations.md, keeping only a concise Quick Start inline and linking in-context at the relevant sections rather than only in the footer.

Add verification steps to batch operations, e.g. after wandb.log_artifact() confirm the artifact state, and after wandb.agent() check run status.

De-duplicate the repeated wandb.init/wandb.log boilerplate by defining one canonical pattern and reusing it, trimming the Best Practices subsections to non-obvious advice only.

Dimension	Reasoning	Score
Conciseness	Mostly code with little concept padding, but the wandb.init/wandb.log boilerplate repeats across Quick Start, PyTorch, Core Concepts, Sweeps, Artifacts, and Integrations, and the five 'Best Practices' subsections add self-evident bulk that could be tightened.	3 / 5
Actionability	Executable, copy-paste-ready code throughout covering tracking, sweeps, artifacts, and HF/Lightning/Keras integrations, with only minor gaps like undefined stubs (train_epoch, validate, build_model).	4 / 5
Workflow Clarity	Sequences (init→log→finish; sweep define→train→agent) are clear, but there are no validation checkpoints or feedback loops — e.g., verifying a run logged successfully or confirming an artifact uploaded — which matters for the batch-like sweep and artifact operations.	3 / 5
Progressive Disclosure	Good section structure and three real one-level-deep reference files exist, but references are only listed in a 'See Also' footer without in-context pointers, and substantial detail (sweep strategies, integrations, visualization) is inlined in SKILL.md rather than pushed to those references.	3 / 5
	Total	13 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinctive, naming four concrete W&B capabilities with natural trigger terms. Its main weakness is the absence of an explicit 'Use when...' clause, leaving the activation context only implied.

Suggestions

Add an explicit trigger clause, e.g. 'Use when tracking ML experiments, tuning hyperparameters, or managing a model registry with Weights & Biases.'

Include the spelled-out name 'Weights & Biases' alongside 'W&B' so users who say the full name still match.

Tighten the trailing 'collaborative MLOps platform' tagline or fold collaboration into a concrete action to keep every phrase earning its place.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Track ML experiments with automatic logging', 'visualize training in real-time', 'optimize hyperparameters with sweeps', 'manage model registry' — giving comprehensive coverage of the W&B domain.	5 / 5
Completeness	Has a clear 'what' (four concrete capabilities) but no explicit 'Use when...' trigger clause, so 'when' is only weakly implied — the missing-trigger-guidance cap at 3 applies.	3 / 5
Trigger Term Quality	Strong natural terms ('ML experiments', 'training', 'hyperparameters', 'sweeps', 'model registry', 'W&B') that users would say, but the description omits the spelled-out 'Weights & Biases' and lacks a few common synonyms.	4 / 5
Distinctiveness Conflict Risk	The W&B / collaborative-MLOps niche is clear with distinctive triggers ('W&B', 'model registry', 'sweeps') and minimal conflict risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (591 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/weights-and-biases/SKILL.md
Commit: d5ae560

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.