Name: domino-data-sdk
Rating: 92.8 (1 reviews)
Author: dominodatalab

domino-data-sdk

Use the domino-data Python SDK (dominodatalab-data) for programmatic data access in Domino. Covers DataSourceClient for SQL queries and object storage, DatasetClient for dataset files, TrainingSets for ML data versioning, Feature Store, and VectorDB (Pinecone) integration. Use when querying data sources, downloading datasets, managing training sets, or working with vector databases in Domino.

1.11x

Quality

—

Does it follow best practices?

Impact

100%

1.11x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and highly actionable, with executable examples for every component, but it presents these as disconnected quick starts without validation checkpoints for batch/database operations, and its 'Related Documentation' links point to files that are not present in the skill bundle.

Suggestions

Add explicit validation/verification steps (e.g. confirm a training-set version was created, verify query row counts, check uploaded object existence) to the batch and database operations so workflow clarity can reach the top anchor.

Provide the referenced DATA-SOURCES.md, DATASETS.md, TRAINING-SETS.md, and VECTORDB.md files (or remove the broken links) so progressive-disclosure navigation is real rather than dangling.

Collapse the per-component Quick Start blocks into a single concise overview and move detailed per-client examples into the referenced detail files to better separate overview from depth.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean, executable code blocks and a compact component table, with only minimal inline commentary that earns its place; it does not re-explain concepts Claude already knows, matching the lean/efficient anchor.	3 / 3
Actionability	Each component is demonstrated with complete, copy-paste-ready Python (e.g. DataSourceClient query + to_pandas, DatasetClient.download with max_workers, create_training_set_version), plus executable pip/poetry install commands, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The content is organized as independent per-component quick starts rather than a sequenced multi-step process, and operations that are batch/DB-like (training-set versioning, uploads, SQL queries) lack any explicit validation or verify-checkpoint step, capping it at the listed-but-gaps anchor rather than 3.	2 / 3
Progressive Disclosure	A dedicated 'Related Documentation' section signals one-level-deep references, but the referenced files (DATA-SOURCES.md, DATASETS.md, TRAINING-SETS.md, VECTORDB.md) do not exist in any bundle directory, so the references are dangling and the substantial inline quick-starts could be better split, fitting the some-structure anchor rather than the clean one-level-deep anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 names concrete SDK components and capabilities and pairs them with an explicit 'Use when' trigger clause covering natural user phrasing. It is specific, complete, and clearly niche-scoped to Domino data access.

Dimension	Reasoning	Score
Specificity	Names multiple concrete capabilities and components — 'DataSourceClient for SQL queries and object storage', 'DatasetClient for dataset files', 'TrainingSets for ML data versioning', 'Feature Store', and 'VectorDB (Pinecone) integration' — matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	It explicitly answers both 'what' (covers the enumerated SDK components) and 'when' via the explicit 'Use when...' trigger clause, satisfying the top anchor for both what AND when.	3 / 3
Trigger Term Quality	The 'Use when querying data sources, downloading datasets, managing training sets, or working with vector databases in Domino' clause gives good coverage of natural terms a user would actually say, alongside specific terms like 'SQL queries', 'object storage', and 'Pinecone'.	3 / 3
Distinctiveness Conflict Risk	It is scoped tightly to the domino-data SDK within Domino, with distinct triggers unlikely to fire for unrelated skills, matching the clear-niche anchor.	3 / 3
	Total	12 / 12 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
relative_links	Relative link issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: dominodatalab/domino-claude-plugin
Commit: 64f4433

Reviewed: 1 day 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.