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

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/ml-training/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.

The body is a rich, actionable code reference but is verbose and redundantly inlines content that duplicates the provided reference files. It lacks validation checkpoints for batch sweep operations.

Suggestions

Move the full Sweeps, Artifacts, and Integrations sections into the existing reference files, keeping only concise overviews in SKILL.md to reduce redundancy.

Add validation/verification steps around batch sweep runs (e.g., checking run status and metric feasibility before launching count=50 trials).

Remove marketing stats and the Pricing section, which do not aid Claude in executing the skill.

Dimension	Reasoning	Score
Conciseness	Mostly code-driven and useful, but padded with marketing stats ('200,000+ ML practitioners', '10.5k+ stars'), a Pricing section, and redundant wandb.init/sweep examples that could be trimmed.	3 / 5
Actionability	Abundant copy-paste-ready code covering tracking, PyTorch, sweeps, artifacts, and integrations; minor gaps from undefined placeholder functions like train_epoch() and build_model().	4 / 5
Workflow Clarity	Rough sequences exist (init -> log -> finish; define sweep -> train -> agent) but no validation checkpoints, and sweeps (count=50) is a batch operation, capping workflow clarity at 3.	3 / 5
Progressive Disclosure	See Also references are real and one level deep, but full Sweeps/Artifacts/Integrations sections are inlined redundantly alongside those reference files instead of being split out.	3 / 5
	Total	13 / 20 Passed

Description

71%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 action-oriented with good trigger terms, but it omits an explicit 'when to use' clause, which caps completeness. It is clearly distinct as a W&B/MLOps skill with minor overlap risk.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when tracking ML experiments, running hyperparameter sweeps, or managing a model registry with W&B').

Include common synonyms such as 'WandB' and 'experiment tracking' to broaden trigger-term coverage.

Tighten the trailing 'collaborative MLOps platform' tagline, which adds little trigger value.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions ('Track ML experiments with automatic logging', 'visualize training in real-time', 'optimize hyperparameters with sweeps', 'manage model registry') in third person, giving comprehensive coverage.	5 / 5
Completeness	Clearly states what the skill does but lacks any 'Use when...' trigger clause, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Strong natural terms (ML experiments, hyperparameters, sweeps, model registry, MLOps, W&B) but omits common synonyms like 'WandB' and the phrase 'experiment tracking'.	4 / 5
Distinctiveness Conflict Risk	W&B-anchored niche with specific triggers (sweeps, model registry), though 'Track ML experiments' could overlap with other experiment-tracking skills.	4 / 5
	Total	16 / 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 (603 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: synthetic-sciences/openscience
Path: backend/cli/skills/ml-training/weights-and-biases/SKILL.md
Commit: 7dabbf0

Reviewed: ~8 hours 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.