bigquery-public

Run read-only SQL against BigQuery public datasets with local result capture, cost safeguards, and reproducibility outputs.

Quality

72%

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 ./skills/bigquery-public/SKILL.md

Quality

Content

75%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 content is highly actionable with concrete, copy-paste-ready commands and a clear sequenced workflow, but it is held back by triple restatement of the same pipeline and the absence of an explicit validation feedback loop.

Suggestions

Collapse the Core Capabilities, Workflow, and Algorithm/Methodology sections into a single canonical pipeline to remove the triple restatement and tighten conciseness.

Add an explicit validation feedback loop in the workflow (e.g. "If validation rejects the query, report the mutating statement found and ask the user to reformat before retrying").

Consider moving the CLI reference or output-structure detail into a separate reference file to strengthen progressive disclosure now that the body exceeds 50 lines.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the same pipeline is restated three times (Core Capabilities, Workflow, and Algorithm/Methodology), which is more than minor redundancy and keeps it below the efficient 4 anchor.	3 / 5
Actionability	Copy-paste-ready CLI commands cover the common cases (inline SQL, SQL file, preview, list-tables, describe, demo, ClawBio runner) with concrete flags and example queries, matching the fully-executable 5 anchor.	5 / 5
Workflow Clarity	A clear 5-step sequence (Validate, Authenticate, Execute, Discover, Generate) with validation and default cost safeguards is present, but there is no explicit validate-fail-then-fix feedback loop, leaving a minor checkpoint gap below the 5 anchor.	4 / 5
Progressive Disclosure	The single SKILL.md is well-organized with clear section headers and signaled script references in code blocks, but no bundle files exist and the file is longer than 50 lines, so it does not fully meet the simple-skill exception for a 5.	4 / 5
	Total	16 / 20 Passed

Description

70%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 occupies a distinct, low-conflict niche, but it lacks an explicit "Use when..." trigger clause, which caps its completeness and leaves trigger-term coverage short of comprehensive.

Suggestions

Append a "Use when..." clause naming concrete trigger phrases, e.g. "Use when the user asks to query BigQuery public data, run read-only SQL against public datasets, or estimate query cost."

Add natural synonyms users actually say ("query public data", "public dataset SQL") to broaden trigger-term coverage beyond "SQL" and "BigQuery public datasets".

Make the final actions more verb-concrete (e.g. "captures results locally", "enforces byte-billed caps", "records reproducibility metadata") to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Run read-only SQL", "local result capture", "cost safeguards", "reproducibility outputs") but "cost safeguards" and "reproducibility outputs" are slightly abstract compared to fully concrete verbs, so it sits below the comprehensive 5 anchor.	4 / 5
Completeness	Provides a clear "what" but no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms "BigQuery public datasets", "SQL", and "read-only", giving good keyword coverage, but misses common phrasings a user might say such as "query public data" or synonyms, keeping it below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	"BigQuery public datasets" with read-only SQL is a clear, narrow niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: ClawBio/ClawBio
Path: skills/bigquery-public/SKILL.md
Commit: d30153a

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.