write-script-bigquery

MUST use when writing BigQuery queries.

Quality

61%

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 ./system_prompts/auto-generated/skills/write-script-bigquery/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 body is highly actionable with concrete commands and complete, copy-paste SQL examples, and it sequences the workflow with real validation checkpoints and deploy gating. Its main weakness is conciseness: the preview-vs-run guidance is repeated across three sections and the metadata section is wordy.

Suggestions

Consolidate the preview-vs-run intent guidance into a single section; it currently recurs in the command list, the "Preview vs run" section, and the "After writing" section.

Tighten the "Keep metadata in sync" paragraph, which restates the import-propagation and dry-run points that could be trimmed without losing signal.

Normalize heading levels (the body mixes a ## "CLI Commands" section with a # "BigQuery" section) so the overview navigation is consistent.

Dimension	Reasoning	Score
Conciseness	The body is dense with Windmill-specific operational knowledge Claude would not know, but the preview-vs-run intent is repeated across three sections and the "Keep metadata in sync" paragraph is wordy, fitting anchor 3's "mostly efficient but includes some unnecessary explanation or could be tightened".	3 / 5
Actionability	It provides fully executable, copy-paste-ready commands (`wmill script preview`, `wmill generate-metadata --dry-run`, `wmill generate-metadata rehash`, `wmill resource-type list --schema`) and complete SQL examples covering @name parameters, S3Object input, and S3 streaming, matching anchor 5's "fully executable; copy-paste ready code or commands; specific examples cover the common cases".	5 / 5
Workflow Clarity	The write→preview→generate-metadata→diff→deploy sequence is clear with explicit validation checkpoints (dry-run, lock diff, reporting version bumps) and deploy gating, so it is not capped under the destructive/batch rule; it lands at anchor 4 because the flow is distributed across sections rather than one consolidated checklist.	4 / 5
Progressive Disclosure	With no bundle files present, all content is inline but well-organized under clear headers with one-level-deep external references (`AGENTS.wmill.md`, the `preview` skill) clearly signaled, matching anchor 4's "good structure; most content appropriately placed; references mostly clear"; a minor heading-level inconsistency (## CLI Commands vs # BigQuery) keeps it from 5.	4 / 5
	Total	16 / 20 Passed

Description

48%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 a terse, specific trigger that clearly signals when to use the skill, but it omits any explicit statement of what the skill does and lists no concrete capabilities. Adding a "what" clause (e.g., the @name parameter syntax, S3 streaming, metadata sync it covers) would lift specificity and completeness.

Suggestions

Add a concrete "what" clause naming the skill's capabilities, e.g. "Generates BigQuery scripts using @name parameters, S3Object inputs, and S3 streaming directives."

Expand trigger terms with natural synonyms users say, such as "SQL", "GCP", or "Google BigQuery", to improve keyword coverage.

Keep the explicit "Use when..." trigger but pair it with the capability list so both what and when are answered explicitly.

Dimension	Reasoning	Score
Specificity	"MUST use when writing BigQuery queries" names the BigQuery domain and one minimal action (writing), matching anchor 2's "Names the domain but actions are minimal or generic" like "Processes PDF files"; it does not list multiple concrete capabilities.	2 / 5
Completeness	The description provides an explicit, strong "when" ("MUST use when writing BigQuery queries") but the "what" is only implied by the trigger object rather than stated as a capability; it sits between anchor 2 (only when, no what) and anchor 4, landing at 3 because the trigger is concrete yet the what is not separately elaborated.	3 / 5
Trigger Term Quality	"writing BigQuery queries" is a natural phrase a user would say, but coverage lacks common synonyms (SQL, GCP, Google BigQuery), fitting anchor 3's "some relevant keywords but missing common variations or synonyms".	3 / 5
Distinctiveness Conflict Risk	BigQuery is a specific technology with a distinct trigger, giving a clear niche with only minor overlap risk against generic SQL/database query skills, matching anchor 4's "mostly distinct; minor overlap risk with closely related skills".	4 / 5
	Total	12 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: windmill-labs/windmill
Path: system_prompts/auto-generated/skills/write-script-bigquery/SKILL.md
Commit: 74af4ed

Reviewed: about 19 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.