tensorboard

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

Quality

63%

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

62%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 highly actionable with executable, copy-paste-ready code for both PyTorch and TensorFlow and a clean section structure that offloads depth to three real reference files. Weaknesses are redundancy between the body and references and the absence of explicit validation/feedback steps for batch logging operations.

Suggestions

Add a short validation/checkpoint step after logging runs (e.g. launch TensorBoard and confirm scalars appear before training continues) to lift workflow clarity above 3.

De-duplicate content that already lives in references/visualization.md (scalar/histogram/image/embedding recipes) so the body stays a lean overview and references stay one level deep.

Trim introductory lines that restate what TensorBoard/libraries are, trusting Claude's existing knowledge.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-forward sections, but there is notable redundancy (scalar/histogram/image logging appear in SKILL.md and again in references/visualization.md) and some restating of basics Claude already knows.	3 / 5
Actionability	Provides copy-paste-ready, executable PyTorch and TensorFlow snippets covering the common logging, profiling, and comparison cases with concrete commands and APIs.	5 / 5
Workflow Clarity	Sequences are implicit through grouped code examples, but there are no explicit validation/verification checkpoints; since logging is a batch operation over many epochs, the missing feedback loop caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Clear overview with a 'See Also' section pointing to real one-level-deep reference files (visualization.md, profiling.md, integrations.md), though substantial content (e.g. full embedding/PR-curve recipes) is duplicated inline rather than only in references.	4 / 5
	Total	15 / 20 Passed

Description

63%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, enumerating several concrete TensorBoard capabilities and naming the toolkit. Its main weakness is the absence of an explicit 'Use when...' trigger clause, leaving the 'when to use' guidance implicit.

Suggestions

Add an explicit trigger clause, e.g. 'Use when visualizing training runs, debugging model weights/distributions, comparing experiments, or profiling performance with TensorBoard.'

Include common synonyms or file hints users say (e.g. 'logs', 'event files', '.tfevents', 'SummaryWriter') to broaden trigger-term coverage.

Mention images/text/PR-curve visualization to round out capability coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Visualize training metrics', 'debug models with histograms', 'compare experiments', 'profile performance') with minor gaps in coverage such as images/text/PR curves.	4 / 5
Completeness	A clear 'what' is present via enumerated capabilities, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('training metrics', 'compare experiments', 'profile performance') plus framework keywords, but lacks common synonyms like 'logs' or '.tfevents'.	4 / 5
Distinctiveness Conflict Risk	TensorBoard is a clearly named, niche toolkit with distinct triggers and minor overlap risk with general experiment-tracking skills.	4 / 5
	Total	15 / 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 (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: d5ae560

Reviewed: 9 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.