tensorboard

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

Quality

73%

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/tensorboard/SKILL.md

Quality

Content

65%

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

The content is highly actionable with rich executable examples, but it is verbose with redundant dual-framework coverage and lacks validation checkpoints. Progressive disclosure is present but undermined by inline duplication of material that also lives in the reference files.

Suggestions

Trim parallel PyTorch/TensorFlow duplication by showing one framework inline and linking the other to references/integrations.md.

Remove marketing statistics and consolidate the inline Profiling and Advanced sections into references/profiling.md and references/visualization.md, keeping only a concise overview in SKILL.md.

Add explicit validation checkpoints to the training-loop example (e.g. verify logs appear, confirm metrics render) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but it is very long with parallel PyTorch/TensorFlow coverage of each topic plus marketing fluff ("20M+ downloads/year \| GitHub Stars: 27k+"); it could be tightened and partly offloaded to the references.	2 / 3
Actionability	Provides numerous complete, executable, copy-paste-ready code blocks for scalars, images, histograms, graphs, profiling, and full training loops in both PyTorch and TensorFlow.	3 / 3
Workflow Clarity	Sequences such as the install/launch flow and training loops are present and clear, but there are no explicit validation checkpoints or feedback loops, leaving the level-3 bar unmet.	2 / 3
Progressive Disclosure	Three reference files exist and are signaled in the "See Also" section, but substantial content (profiling, visualization, integrations) is duplicated inline rather than split out, and the main body is a large monolithic block.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 lists several concrete capabilities tied to a clearly-named tool, with good natural trigger terms. Its main weakness is the absence of an explicit 'Use when...' clause, which caps completeness at 2.

Suggestions

Append an explicit trigger clause, e.g. "Use when visualizing training metrics, comparing runs, or profiling ML models with TensorBoard."

Consider adding common variation terms users might say (e.g. "loss curves", "experiment tracking", "training logs").

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: "Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance", matching the anchor for enumerating several concrete actions.	3 / 3
Completeness	Clearly states what the skill does but has no "Use when..." clause or explicit trigger guidance, so completeness is capped at 2 per the rubric guidelines; it does not reach the level-3 bar of explicitly answering when to use it.	2 / 3
Trigger Term Quality	Contains natural terms an ML practitioner would say ("training metrics", "compare experiments", "model graphs", "TensorBoard"), giving good coverage rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Names a specific tool ("TensorBoard - Google's ML visualization toolkit") with a clear niche, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 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 (631 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/tensorboard/SKILL.md
Commit: 52845c3

Reviewed: about 13 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.