write-script-python3

MUST use when writing Python scripts.

Quality

51%

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

71%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, code, and well-reasoned decision rules backed by validation feedback loops. Its main weakness is structure: a monolithic ~800-line wmill SDK reference is inlined in SKILL.md rather than split into a one-level-deep reference file. Moving that surface into references/ would materially improve both conciseness and navigation.

Dimension	Reasoning	Score
Conciseness	The instructional top section is efficient and assumes competence, but ~800 lines of inlined wmill SDK signatures with repetitive Args/Returns docstrings could be tightened or externalized, matching 'mostly efficient but includes some content that could be tightened.'	3 / 5
Actionability	Concrete copy-paste-ready commands (wmill script preview/run/generate-metadata) and executable code (main, TypedDict resources, S3 ops, preprocessor) cover the common cases fully.	5 / 5
Workflow Clarity	Clear decision logic for preview vs run vs sync push with validation feedback loops (dry-run scoping, diff-and-report version bumps, explicit-deploy gating); not a strictly numbered sequence, so minor gaps remain.	4 / 5
Progressive Disclosure	Section headers give structure, but the bulk of the file is an ~800-line inline SDK API reference that belongs in a separate reference file; no bundle files exist to offload it, matching 'content that should be separate is inline'.	3 / 5
	Total	15 / 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 a bare trigger clause: it says when to invoke the skill but not what the skill does or what makes it distinct. It reads as a generic Python-scripting hook rather than a Windmill-specific skill. The strongest fix is naming the actual capabilities (structure main/resource types, run/preview via wmill, sync metadata) and scoping triggers to Windmill.

Suggestions

Add a 'what' clause naming concrete capabilities, e.g. 'Structure Python scripts with main/TypedDict resources, run and preview them via the wmill CLI, and keep generated metadata in sync.'

Narrow the trigger to the actual niche and add synonyms a user would say, e.g. 'Use when writing, previewing, or deploying Python scripts on Windmill (wmill).'

Mention wmill/Windmill explicitly so the description does not collide with general-purpose Python skills.

Dimension	Reasoning	Score
Specificity	The phrase 'writing Python scripts' names the domain clearly but provides zero concrete actions (no mention of structuring main, resource types, wmill CLI, metadata sync), matching the anchor that names the domain with only minimal/absent actions.	2 / 5
Completeness	It gives a clear 'when' ('MUST use when writing Python scripts') but entirely omits the 'what' — no statement of what the skill does — matching the anchor where only 'when' is present without 'what'.	2 / 5
Trigger Term Quality	'writing Python scripts' is a natural phrase a user would say, but it is the only keyword and omits synonyms (Python, scripts, wmill, Windmill, automation), matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'writing Python scripts' is very broad and would fire for any Python-script task, with no Windmill/wmill narrowing, so it carries high overlap risk with many Python 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 (972 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: 7915540

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.