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

95%

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

100%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.

An exemplary SKILL.md body: it disambiguates the two interfaces up front with a table, gives minimal executable examples for each, states only the non-obvious key concepts, and cleanly defers all detail to two real, one-level-deep reference files. No weaknesses found.

Dimension	Reasoning	Score
Conciseness	Lean and efficient across ~55 lines: no explanation of concepts Claude already knows, and every line carries non-obvious information (e.g., 'pass space_id — metrics sync to a Space dashboard so they persist after the instance terminates'; 'Add --json for programmatic output suitable for automation and LLM agents').	5 / 5
Actionability	Fully executable, copy-paste-ready Python and CLI examples cover the common cases (init/log/finish setup and list/get retrieval), and every command referenced is concrete with no pseudocode.	5 / 5
Workflow Clarity	Both workflows are explicitly sequenced (init → log → finish for logging; list → get → show/sync for retrieval), with interface selection disambiguated by a task table and task-matched sections. No destructive or batch operations, so no validation cap applies.	5 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to references/logging_metrics.md and references/retrieving_metrics.md (both verified to exist); details are appropriately split out and the inline content is minimal but sufficient to start.	5 / 5
	Total	20 / 20 Passed

Description

92%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 description that states concrete capabilities, gives explicit 'Use when' triggers for both interfaces, and stays concise with no fluff. The only weakness is modest synonym coverage in its trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Track and visualize ML training experiments', 'logging metrics during training', 'retrieving/analyzing logged metrics', 'real-time dashboard visualization, HF Space syncing, and JSON output for automation' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Clearly answers both 'what' (track/visualize ML training experiments with Python API and CLI interfaces) and 'when' ('Use when logging metrics during training... or retrieving/analyzing logged metrics') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage with natural phrases users would say ('logging metrics during training', 'ML training experiments', 'retrieve metrics'), but a few natural synonyms and variations are missing (e.g., 'experiment tracking', 'monitor training', 'loss curves').	4 / 5
Distinctiveness Conflict Risk	Clear niche (Trackio, ML experiment tracking) with distinct triggers tied to metric logging/retrieval tasks; minimal conflict risk with other skills.	5 / 5
	Total	19 / 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
metadata_version	'metadata.version' is missing	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/other/hugging-face-trackio/SKILL.md
Commit: 8d99f34

Reviewed: 8 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.