write-script-python3

MUST use when writing Python scripts.

Quality

42%

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-python3/SKILL.md

Quality

Content

52%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 Python authoring guidance and CLI decision flow are concrete and well-sequenced, but the skill is dominated by an enormous inlined SDK API dump that should live in a separate reference file. Token efficiency and progressive disclosure suffer as a result.

Suggestions

Move the wmill SDK function reference (lines ~186-935) into a separate references/ file and keep only the handful of methods actually needed for script authoring inline.

Trim or collapse the per-function Args/Returns docstrings to signatures plus a one-line purpose, since Claude can call the SDK from signatures.

Add an explicit validate-fix-retry loop for the deploy path (e.g. preview fails -> fix -> re-preview -> only then deploy) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	Roughly 730 of 930 lines are an inlined dump of the entire wmill SDK API with full docstrings, which is heavily padded reference material that does not earn its place in the overview; the top sections are tighter but the bulk is noticeably verbose.	2 / 5
Actionability	Core tasks ship copy-paste-ready code (main, TypedDict resources, imports, preprocessor, S3 ops) and concrete CLI commands, with only minor gaps in the SDK section where entries are signatures rather than full runnable examples.	4 / 5
Workflow Clarity	There is a clear decision flow for preview vs run vs generate-metadata vs deploy with explicit intent rules and checkpoints (dry-run inspection, diff regenerated locks, preview before deploy, deploy only on explicit ask), though no explicit validate-fix-retry loop.	4 / 5
Progressive Disclosure	No bundle reference files exist, yet the entire wmill SDK API reference is inlined in SKILL.md instead of being split into a separate REFERENCE.md; external references (AGENTS.wmill.md, preview skill, SDK docs) are mentioned but the bulk content that belongs in its own file is not disclosed progressively.	2 / 5
	Total	12 / 20 Passed

Description

32%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 essentially a bare trigger clause with no statement of what the skill does, and it omits the Windmill context that would distinguish it. It reads as a guard ('MUST use when writing Python scripts') rather than a capability description.

Suggestions

Add a 'what' clause naming the actual capabilities, e.g. 'Scaffolds and iterates on Windmill Python scripts: defines main/resources, syncs metadata, previews and runs via wmill.'

Include the Windmill trigger term so the skill is distinguishable from generic Python skills and conflict risk drops.

Add natural synonyms/extensions such as '.py', 'Python code', or 'wmill script' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Python scripts') and a single generic activity ('writing') but lists no concrete actions such as scaffolding, metadata sync, or preview/run, matching the anchor 'Names the domain but actions are minimal or generic'.	2 / 5
Completeness	The 'when' is explicit ('MUST use when writing Python scripts') but there is no 'what' — the description never says what the skill actually does (Windmill script authoring, metadata, preview/run), matching the anchor 'only when is present without what'.	2 / 5
Trigger Term Quality	'writing Python scripts' is a phrase users would naturally say, but coverage is limited to that single expression, missing common variations and synonyms such as '.py', 'Python code', or 'script'.	3 / 5
Distinctiveness Conflict Risk	'writing Python scripts' is very broad and never mentions Windmill, so it would collide with any generic Python authoring skill, matching 'Very broad; high overlap risk with many similar skills'.	2 / 5
	Total	9 / 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
skill_md_line_count	SKILL.md is long (937 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: windmill-labs/windmill
Path: system_prompts/auto-generated/skills/write-script-python3/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.