tensorboard

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

Quality

66%

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 ./bundled/skills/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 body is highly actionable with extensive executable examples and correctly signals real one-level-deep references, but it is verbose and repetitive and reads more as an API catalog than a sequenced workflow. Tightening the main file and offloading detail to the existing references would raise conciseness and progressive disclosure.

Suggestions

Consolidate the repeated SummaryWriter imports and overlapping scalar-logging examples (Quick Start vs. Core Concepts 2) to cut length and repetition.

Move the large inline catalogs (Advanced Features, Integration Examples) into the existing reference files, leaving the main file a lean overview pointing to them.

Frame the Quick Start as an explicit numbered sequence with a verification checkpoint (e.g., confirm TensorBoard is reachable at http://localhost:6006) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	At ~620 lines the body is padded with repetitive boilerplate (SummaryWriter is re-imported in nearly every section and scalar logging is shown in overlapping sections), though it mostly shows code rather than explaining concepts Claude already knows.	2 / 3
Actionability	It provides abundant copy-paste-ready, executable code for SummaryWriter usage, TensorFlow callbacks, embeddings, profiling, and full training loops.	3 / 3
Workflow Clarity	The Quick Start offers an install-then-log-then-launch path, but the body is a feature catalog rather than a sequenced workflow with explicit checkpoints for the multi-step setup it describes.	2 / 3
Progressive Disclosure	The "See Also" section signals three one-level-deep references (visualization.md, profiling.md, integrations.md), all verified to exist, but the main file carries a heavy inline catalog that could itself be pushed into those references.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 distinct, naming a concrete tool and several concrete actions, but it lacks an explicit "Use when..." trigger clause and relies on capability verbs rather than a spread of natural trigger phrasings. It is strong on what the skill does but weaker on when to invoke it.

Suggestions

Add an explicit "Use when..." trigger clause (e.g., "Use when tracking training metrics, comparing experiment runs, or profiling model performance with TensorBoard") to lift completeness to 3.

Include common natural trigger variations users would say ("track training loss", "monitor experiments", "tensorboard dashboard") to improve trigger term quality.

Drop the marketing suffix "Google's ML visualization toolkit" — it adds tokens without aiding invocation.

Dimension	Reasoning	Score
Specificity	"Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance" lists multiple specific concrete actions rather than vague language.	3 / 3
Completeness	It clearly answers what the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Terms like "TensorBoard", "training metrics", and "experiments" are natural, but the description reads as a capability list and omits common trigger variations a user would actually utter (e.g., "track training loss", "monitor experiments").	2 / 3
Distinctiveness Conflict Risk	"TensorBoard - Google's ML visualization toolkit" names a specific, well-known tool with a clear niche, making it unlikely to trigger for an unrelated skill.	3 / 3
	Total	10 / 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 (630 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/tensorboard/SKILL.md
Commit: f627ab5

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.