hugging-face-trackio

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.

Quality

87%

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

Quality

Content

86%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.

Well-structured, actionable overview that offloads detail to two real reference files and gives executable examples for both interfaces. The only weak spot is minor verbosity in framing lines and missing verification checkpoints.

Suggestions

Trim the opening tagline and 'Key concept' framing to save tokens — the table and code already convey the same information.

Add a brief verification step after logging (e.g., confirm the run appears via 'trackio list runs --project my-project --json') to close the logging workflow loop.

Clarify in the minimal retrieval example that 'trackio get metric' returns summary stats plus series values so the output shape is unambiguous.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes Claude's competence without explaining ML/logging concepts; the opening tagline and 'Key concept' labels add minor over-explanation that could be trimmed.	4 / 5
Actionability	Provides copy-paste ready executable code (trackio.init/log/finish) and concrete CLI commands (list/get/show/sync) with the --json flag, covering the common logging and retrieval cases.	5 / 5
Workflow Clarity	Clear init→log→finish and list→get sequences are present, and the operations are non-destructive so the validation cap does not apply; minor checkpoint guidance (e.g., verifying a run appears after finish) is absent.	4 / 5
Progressive Disclosure	Clear overview with two one-level-deep reference files (logging_metrics.md, retrieving_metrics.md) that both exist and are well-signaled via a comparison table and inline links, with detail appropriately split out.	5 / 5
	Total	18 / 20 Passed

Description

88%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.

A strong, third-person description that clearly states capabilities and an explicit 'Use when' trigger covering both interfaces. Minor gains possible by adding common synonyms (e.g., 'experiment tracking', 'monitor training runs').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Track and visualize ML training experiments', 'logging metrics during training (Python API)', 'retrieving/analyzing logged metrics (CLI)', 'real-time dashboard visualization, HF Space syncing, and JSON output' — with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Track and visualize ML training experiments...') and when ('Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI)') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keywords users would say ('logging metrics during training', 'retrieving/analyzing logged metrics', 'ML training experiments'), but missing a few synonyms/variations like 'experiment tracking' or 'monitor training'.	4 / 5
Distinctiveness Conflict Risk	Names Trackio and HF Spaces niche with distinct triggers, but 'experiment tracking' / 'metrics logging' could overlap with related skills like wandb or tensorboard integrations.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/other/hugging-face-trackio/SKILL.md
Commit: a820c2f

Reviewed: ~17 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.