tensorboard

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

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/tensorboard/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 TensorBoard reference with concrete dual-framework code and valid one-level references, but it is over-long due to framework duplication and inlines material that already lives in the bundled reference files.

Suggestions

Collapse the dual PyTorch/TensorFlow examples: show one framework inline and defer the other to references/integrations.md to cut roughly half the code length.

Move the inlined Performance Profiling and Integration Examples sections into references/profiling.md and references/integrations.md, leaving SKILL.md as an overview with pointed links.

Remove marketing stats ('20M+ downloads/year', '27k+ stars') and repeated '# Launch:' comments; assume Claude's competence per the conciseness rubric.

Dimension	Reasoning	Score
Conciseness	Mostly actionable code but noticeably padded: every feature is duplicated across PyTorch and TensorFlow, '# Launch:' lines and the '27k+ stars'/'20M+ downloads' marketing stats repeat, so it could be tightened beyond the minor-trim bar of score 4.	3 / 5
Actionability	Concrete, mostly-executable TensorBoard API calls covering the common cases (scalars, images, histograms, graphs, embeddings, hparams, PR curves, profiling), but snippets depend on placeholder helpers (train_epoch, validate, model, train_loader) so they are not fully copy-paste ready.	4 / 5
Workflow Clarity	The integration training loops show a clear sequence (setup, log graph, train, log metrics, close) but contain no validation or verification checkpoints, matching the score-3 anchor rather than the checkpointed score-4 anchor.	3 / 5
Progressive Disclosure	References are clearly signaled in 'See Also' and point to real files, but full Performance Profiling and Integration Examples sections are inlined in SKILL.md while those exact topics have dedicated reference files, so content that should be separate remains inline.	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-rich with a clear tool niche, but it omits any 'Use when...' trigger guidance, which caps completeness and slightly weakens trigger-term and distinctiveness scores.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g. 'Use when the user wants to visualize training metrics, track experiments, debug models, or profile ML performance').

Include common synonyms and artifacts users mention, such as 'loss curves', 'experiment tracking', and '.tfevents' log files, to improve trigger-term coverage.

Tie the actions to specific TensorBoard features (Scalars, Histograms, Projector, HParams, Profiler) to sharpen distinctiveness against generic experiment-tracking tools.

Dimension	Reasoning	Score
Specificity	Lists five concrete actions ('Visualize training metrics', 'debug models with histograms', 'compare experiments', 'visualize model graphs', 'profile performance') — comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Has a clear 'what' (five actions plus the TensorBoard toolkit label) but no 'Use when...' clause or equivalent trigger guidance, so per the rubric cap it cannot exceed 3.	3 / 5
Trigger Term Quality	Good natural keywords (training metrics, experiments, profile performance, TensorBoard) but missing common synonyms and file extensions (e.g. 'loss curves', 'experiment tracking', '.tfevents'), so it falls short of the comprehensive score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	Naming the specific tool (TensorBoard) gives a clear niche with minimal conflict, but the generic actions ('compare experiments', 'profile performance') overlap with related tracking/profiling skills and the missing trigger clause keeps it below 5.	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 (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: 04797e6

Reviewed: 3 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.